http://www.informatik.uni-trier.de/~ley/db/conf/kdd/kdd2000.html
KDD 2000
http://doi.acm.org/10.1145/347090.347105	12	Data Selection for Support Vector Machine Classifiers	academic acta adult advances algorithms appear applications applied approximation arbitrary astronomical automated available bartlett blumer boston bradley bureau burges california cambridge census cherkassky classi company complementarity computational computer computing concave concepts conference dantzig data databases dataset david department discovery discrimination editor editors ehrenfeucht erentiable extensions feature ferris festschrift fifteenth fischer francisco from galaxy general generalized guide haussler heidelberg hill html hummphreys icml information informs international jersey john journal kaufmann klaus kluwer know large learning least ledge letters linear machine machines madison mangasarian march margin massive math mathematica mathematical mathematics mathprog mathworks matlab mcgraw methods minimization mining mitchell mlearn mlrepository morgan mulier murphy musicant natick nature networks neural nondi nonlinear norm occam october odewahn operations optimization pages pang paral parsimonious pattern pennington philadelphia physica plane polyhedral press princeton problems proceedings processing prog programming publicly publishers razor recognition references report reports repository research riedmueller ritter rosen schae scholkopf schuurmans sciences selection separating shavlik siam smola software solution sons springer star statistical stockwell street support tech technical technology techreports theory tutorial university user vapnik vector verlag vietnamica warmuth wiley wisc wisconsin with york zumach
http://doi.acm.org/10.1145/347090.347195	73	Incremental Quantile Estimation for Massive Tracking	algorithms annals annual applied approximate approximation arthur ballot basel bell birkhauser cahill carolina chapter chen cient comments computer computing contributions data databases david dedicated detecting distribution edition ehind eleventh ercentile estimating estimation fraud function information institute interface investigating jagopalan journal labs lagging lamb limited linder lindsay line losing lucent manku mathematical medians memory method monitoring monro munro north order other pages pass paterson pfanzagl pinheiro procedure proceedings quantile quantiles raleigh real recursive reducting reference references robbins science scienti selection sequential siam sigmod sorting space state statistical statistics stochastic storage symposium technical technologies theoretical tierney transaction university unknown verlag weide wiley with without workload world york
http://doi.acm.org/10.1145/347090.347181	64	Cross-sell: A Fast Promotion-Tunable Customer-item Recommendation Method Based on Conditionally Independent Probabilities	academic after agrawal algorithmic algorithms also alternative american analysis analyst approach april artificial association august automated available bayesian behavioural boosting borchers boston breese building california chan chapman chile collaborative computer conference corporation data databases david deck department diamonds diego discovery elkan empirical engineering estimating fast fifth filtering ford fourteenth framework from grouplens hall heckerman herlocker http impact imputation income incomplete intelligence international invasive john journal july kadie kaufmann kitts knowledge konstan large learning little london madison madow mate medical methods mining minnesota missing morgan multiple multivariate office olsen overview paper patent perceptions performing personalization perspective predictive press primer problems procedures proceedings profiles profiling references report research riedl robinson rough rubin rules sample santiago schafer scheuren science searches section sons soul srikant stat statistical summit survey surveys system technical trademark uncertainty university usage user variance very vignette wiley with working workshop years
http://doi.acm.org/10.1145/347090.347100	8	An Empirical Analysis of Techniques for Constructing and Searching K-Dimensional Trees	across addition advances advantageous agricultural agriculture algorithm algorithmica algorithms amount analysis appears artificial asci associative attributes automated available based because bendat bentley berlin berthold best binary biomedical both bratko browsing build calculations cambridge case clustering cohn communications completing computer conclusion conference contrast control cost data database deng department desirable different dimensional dimensions directory disk distance distributed distribution distributor dnload dzeroski efficient electronic examined expect expected exploiting extract fast figure file finding finkel fisher fnic foodcomp francisco friedman from hand human hybrid implicate implications indexing information instance instancebased intelligence intelligent international introductory irrelevant john joint journal kaufmann kdtrees kearns laboratory large leaf learning leaves lecture like likely limit lists logarithmic machine machines matches mathematical measurement memory method methods minimize mixture model moore morgan most multidimensional multiresolution must nearest neighbor neural nodes noisy notes novel number nutrient optimizing other particularly piersol preferred press procedures proceedings processing producer pruning random reduce reduced reference references refinements release report required research reside robot sample science search searches searching secondary sectors seems semiautomated service setting severalfold single situations sixteenth sizes small software solla sons springer sproull standard states statistical strong structure studies study such symposium systems talbert technical techniques terms third time tolerating transactions tree trees tuples tutorial undirected united university usda used users using verlag very visited washington weak weiss when where which wiley will with woolson would york
http://doi.acm.org/10.1145/347090.347126	26	Explicitly Representing Expected Cost: An Alternative to ROC Representation	aaai academic accuracy adaptive additional advantage advantages again against algorithms allows also alternative although analysis another approach appropriate arti avenue based belmont between blake breiman brunk calculation california case cation charles choose cial class classes classi clear clearer combining common commonly comparing comparison conclusions conference cost costs cult data databases decision demonstrated detection diagnostic dimensional dimensions disadvantage discovery distributions domingos dual dualities duality ease easy ective eleventh environments erence estimation evaluating evaluation expected explicitly extend fact fawcett fifteenth fifth figure francisco fraud friedman from function functions future general hand have high higher holte however html human hume ideas illinois images imprecise improved increases induction intel interesting international into introduction investigated irvine jected jority journal kaufmann know kohavi kubat large learning ledge left lift ligence limitation limitations line ling little lusted machine main maintain makes making many matwin measuring medical menlo merit merz metacost method methods metrics might mining misclassi mlearn mlrepository more morgan murphy national normalised notions notoriously number olshen operating optimal other outside over pages paper park pazzani performance pickett point press probability procedure proceedings provost quadratically quantitative radar range readily reducing references regression repository representation representations represents research right robust satellite science second selection sensitive should shown shows sides signal situation sonar space spills spring stone such swets switch systems than that theory there third this thomas three time trees under understandability university unnecessary used user using visualise visualization visually wadsworth whether which while with work would york
http://doi.acm.org/10.1145/347090.347128	27	Multi-Level Organization and Summarization of the Discovered Rules	aaai about adomavicius agrawal algorithms allows analysis applications applied artificial aspects association associations attention attributes autonomous based bayardo belief beyond bowker cases chapman cikm classification closely colorful complexity compton concise conclusion constrained constraintbased constraints context contingency continuous daily data databases decision dense deviations discovered discovering discovery discretization domain dong driven efficient embedded enables everitt exception exceptions expert exploratory fashion fast fayyad feng finding first focus from general gunopulos hall hartley hierarchical html http hussain icde ieee ijcai individual information integrating intelligence intelligible interesting interestingness interval intuitive irani item jansen john kaufmann klemetinen know knowledge kohavi lakshmanan large learning learnt level library list lives long machine maintenance makes manages mani manley mannila matheus merz method mining mlearn mlrepository more morgan multi multiple murphy neighborhood novel online optimizations organization organize overall padmanabhan pakdd paper pattern patterns pazzani personalization pfleger piatesky picture post practical practice present principles profiling program proposed pruning quinlan references related reliable repository representation ronkainen rule rules search seeking sets shankle shapiro show sigmod silberschatz simple special srikant strategy summaries summarize summarizing suzuki system systems tables talk technique tedd terms than that then think this through toivonen tools trans tree trees tuzhilin unexpected unexpectedness user using validation valued verkamo very vldb what which with
http://doi.acm.org/10.1145/347090.347102	10	Ongoing Management and Application of Discovered Knowledge in a Large Regulatory Organization: A Case Study of the Use and Impact of NASD Regulation’s Advanced Detection System (ADS)	aaai ability acknowledgments actions activity addressed advanced also appear application applications applied approaches aung available basis because becomes behavior better bias break brill business candidate challenges changes close components comprehensive comprehensively concentrating conclusion conference considered consistently continuing cooperation criteria data david demonstrated dennis department described detection develop developing different discovery discusses distinguishing domain domains driven dybala effective effectively effectiveness enabled entire experts explicit explicitly fawcett fayyad fifth forward foster framework fraud from functions further goldberg gregory groups handbook have helped henry identity implement incorporating increased inductive innovations integral integrated integration interest interesting international into issues james jensen kirkland kloesgen knowledge large magazine make makes manage management managing market measure methods mining models monitoring more multiple nasd nasdaq nasdr necessity need needed normal noticing ongoing only operations opportunity opposed organization over overview paper part people perform perspective perspectives piatesky ping practical press problem proceedings process processes project proposals provide provides provost reference references regulation regulatory report required responsible resultant risk roger samples scientificallybased second senator shapiro shyr sigkdd significance significantly staff statistical step success suggests support surveillance system systems taken team technical technology that these this thorough thoroughly time tomasz towards tracking true ultimate unifying unique usama used users validation verification when with work would zytkow
http://doi.acm.org/10.1145/347090.347112	16	Efficient search for association rules	aaai admissible advances agrawal alamitos algorithm altos analysis application approach apriori aronis arti assiociation association associations australasian based bases bayardo berlin between blackard borgelt bound branch buchanan business cambridge carbonell cation chen cial cient ciio clark class classi clearwater collins colorado comparison computer conf conference constraint correlated cover data databases decision dense department discovery discriminant ective editors enumeration etzioni fast fayyad february fifth forest fort from fuzzy generating graph gunopulos hash homogeneous http ieee ijcai imielinski inclusive induction inductive intel interesting international intl items january joint journal kaufmann know knowledge large learning ledge ligence lists lnai machine magdeburg management mannila massive melbourne menlo methodology michalski mining mitchell morgan morishita most nakaya navathe networks neural niblett nineteenth omiecinski opus pages paper paral parallel park philip piatetsky predicting pres press proceedings production provost pruning quinlan references research rule rules rymon sample savasere scale school science sciences search seattle second segal sets shapiro sigkdd sigmod smyth society software space springer srikant state stern swami systematic systems tenth theory thesis through toivonen tool tools trees types university unordered using uthurusamy verkamo verlag very volume webb working workshop york
http://doi.acm.org/10.1145/347090.347125	25	A Framework for Specifying Explicit Bias for Revision of Approximate Information Extraction Rules	aaai advances after appelt approach approximate approximately artificial assimilation august aumann based bases basis bear berlin bias boston califf california categorization chambery changing circle classification cohen collections combining compiling comprehensive computer concept conference cornell correct correcting craven dagan data decision department description detecting detroit dipasquo distributions document domain eighth eleventh errors evanston evolution examples explanation explicit explore extract extraction fastus february feldman feng finite first fisher france free freitag fresko from graphs high hirsh hobbs huffman ijcai incremental induction inductive information intelligence international into irvine israel issue ithaca jiis joint journal kaufman keyword kibler kinar knowledge koppel landau language large learning lehnert level lindell liphstat lipshtat logical machine mahoney march match mateo mccallum mccarthy message mining mitchell mooney morgan multistrategy national natural networks neural nigam noordewier notes november omission order ourston pages pattern patterns pazzani pkdd precision prior probabilistic proceedings processing processor quinlan rajman real references refinement relational relationships report results revise revising revision richards riloff rosenfeld rule rules schler science segre semi sgen shavlik slattery soderland special spring springer stanford state structured symbolic symposium systems technical techniques term text theories theory thesis tools towell transactions trees trend tyson umass understanding university used using utility visualization visualizing wermter wide wogulis working workshop world yehuda zamir zilberstein
http://doi.acm.org/10.1145/347090.347161	46	Unsupervised Bayesian Visualization of High-Dimensional Data	aaai about according accurate advanced advances afterwards agrawal also although analysis appear application approach arti available based bayda bayes bayesian berlin blake both case cation chapman chat choice cial class classi collins colored computations computing conclusions concrete conference consequently considered considering criteria cunningham data databases demonstrate described dimensional discovering discovery discussed distance distributions division domain duda ectively editor editors empirically european even ewcbr examples experiments expert fact feature formal fourth framework friedman gave geiger general goal goldszmidt good graphical grunwald hall hart have heckerman here hidden high highdimensional html http icml idea illustrating images inference information instance intel interesting international introduction jective jensen john kaufmann keogh know kohonen kontkanen labels lahtinen laskey latent lauritzen learning lecture ledge ligence ligent local london machine manner mapping maps matching mateo meant measure measures measuring meek menlo merz method methods metric microsoft mining mlearn mlrepository model models more morgan multivariate myllymaki naive neapolitan network networks ning notes observations obtained only organizing pages paper park pattern pearl performed performing piatetskyshapiro plausible pool prade precisely predictions predictive press primary probabilistic probabilities problem proceedings process produced producing proposed publicly publishers purpose quality random reasoning redmond reduction references regression report repository research respect resulting results royal saitta sammon scene scheme selection self sets shenoy silander simple smyth software sons spiegelhalter springer stat statistics stolorz structure structures study suggest suggested supervised surprising systems technical technique technology tested that their thirteenth this tirri tutorial type uncertainty underlying unsupervised used using verlag visual visualization visualizations visualizing volume well were wiley with workshop would york
http://doi.acm.org/10.1145/347090.347179	62	Automating Exploratory Data Analysis for Efficient Data Mining	aaai academic addison algorithm analysis annals annealing anytime approach approaches artificial asker attributes bayesian belmont boosting boston breiman cambridge case classification classifier cleaning clustering cognitition component comprehensive computations conceptual conf continuous cover data derthick detection devaney direct discovering discretization discretizing efficient egan elements elkan engineering environment examples exploration exploratory exponentially fayyad feature features filter foundation francisco friedman ginneken glannery guyon hall haykin hertz hill huan icml ijcai information intelligence interactive interval introduction irani irrelevant john jolliffe kaufmann kira kluwer kohavi koller kolojejchick krogh kullback learning leibler lerning ling machine maclin many marketing massive mateo mathematical matic mcgraw menlo methods mining mitchel morgan multi natl networks neural numerical olshen optimal otten palmer park pattern patterns perception pfleger prentice press principle probabilistic problem problems programs quinlan reading recipes references regression rendell report river roth saddle sahami schurmann selection sept series setiono sets signal smyth solution solutions sons springer statistical statistics stone study subset sufficiency technical tenth teukolsky theory thomas toward traditional training trees tukey ucsd unified univ upper valued vapnik venusian verlag vettering view visualization vulcano wadsworth wesley while wiley with wolpert wrappers york
http://doi.acm.org/10.1145/347090.347153	38	Scaling up Dynamic Time Warping for Datamining Applications	aaai accurate acoustics addison agrawal algorithm allows application applied approach approximate artificial asia assp automatic average baselli bases basis bell berndt between bifurcation bioprocesses both bycycle caiani california cardiac cardiology cdsweb cerutti chemical chiba class classes classification clifford cliffs clustering cohen comprehensible computer computers conf conference continuous correctly crema curves cycle cylinder data database databases dataset davis debregeas dendrogram denis department derriere descriptions detection differentiating difficulty dimensionality discovery discrete distance distorted dynamic edits efficient engineering englewood enhanced euclidean example experiment extraction face faloutsos fast fault feature feedback figure filling find first form from fundamentals funnel gavrila gesture gollmer hall hebrail http human ieee indexing industries information intelligence interactive international interpretation irvine jagadish japan juang kadous kaufmann keogh knowledge kohonen kruskall kyoto large learned learning left liberman library line local machine macromolecules malliani management manganaris mannila manolopoulos maps matching members metric mining minneapolis modelbased models morgan movement multivariate multiview muzzupappa noise oates optimization pacific pattern patterns pazzani pdtw peuclidean phases pieruzzi planning porta posten prentice presence press probabilistic proc process programming qual queries rabiner ranganathan recognition reduction references relevance renganathan repository representation representations retrieval rule saito sakoe sawhney scaling scheme schmill school science scientific search seattle separate september sequences series seventh shatkay shim sigmod signal similar similarity simple single smyth society speech spoken statistical statistics string strip subsequence supervised supervision symmetric technique template temporal thesis time times towards track tracking trans translation turiel under university using ustrasbg vanderbilt ventricular vldb volume warped warping warps washington wesley which with word workshop yale zdonik
http://doi.acm.org/10.1145/347090.347103	11	Small is Beautiful: Discovering the Minimal Set of Unexpected Patterns	aaai advances agrawal analysis analyze applications artificial association autonomous based bayardo belief beliefs berger chakrabarti chen classification conf conference constraint constraints data database databases dataset decision defining dense description diff discovered discovering discovery dissertation dmkd doctoral driven engineering etzion exception execution fast fayyad fifth figure first fourth from general generalization grouping gunopulos hatonen icde ieee impressions intelligence interesting interestingness international issue issues item jajodia klemetinen know knowledge lakshmanan large learned learning length logic machine makes management mannila measure measures method mined mining minzoomur mitchell mlnet most multiple national number padmanabhan patterns philadelphia piatetsky post practice press primitive proc proceedings pruning quantitative ramamritham records references relational reliable research ronkainen rule rules sample sarawagi scalability search shah shapiro shows sigkdd sigmod silberschatz sipada size smyth special springer srikant statistics subjective subramonian sudarshan summarizing support surprising suzuki systems tables temporal third thirteenth times toivonen transactions tuzhilin unexpected unexpectedness university using uthurusamy varying verkamo very what with workshop york
http://doi.acm.org/10.1145/347090.347154	39	IntelliClean : A Knowledge-Based Intelligent Data Cleaner	accuracy achieved action alerts algorithm also although applications approximately arti automatically available based boston challenges check cial cient cleaning cleansing company comparison conclusion conference criteria data database databases dataset date dbms dbmsmag dealing detecting dexa digit dilemma dirty discovery dmreview domain duplicate duplicates during easy ective ectively edid edition editorial elds elkan errors exact experiment expert fast figure forgy form format found framework friedman generic giarratano handle have hernandez herzberg hill http identi include including incremental independent inspection intel international introduction issues java jects jess kimball know knowledge large ledge ligence ling linois management manner manual many marked master match matching maydanchik merge mining monge nric online outlined pages pairs paper patient patterns perform precision preprocessing presented principles print problem proceedings processed processing programming provides publishing purge raised recall records references representation research resolved rest results rete revealed review riley rule rules runtime sandia screening seconds september shell shown sigmod size specifying stage still stolfo strategies subset system systems table textual that thesis this those took total tucson uncertainty university value violations waller warehousing were which window with workshop
http://doi.acm.org/10.1145/347090.347134	30	Interactive Exploration of Very Large Relational Datasets through 3D Dynamic Projections	arizona asimov associative audio automatic becker bentley binary blake buja cabrera cave class commun computational computer computing controls cook cruz data databases defanti dhillon dimensional environment experience friedman grand graphical high html http ieee information infovis interface jection jections journal kenyon keogh learning machine manual merz mlearn mlrepository modha multidimensional neira phoenix proc pursuit references relational rendering repository sandin science search searching siam spangler statistical statistics structure symp symposium tool tour trees tukey used viewing virtual visual visualization visualizing volume
http://doi.acm.org/10.1145/347090.347189	70	Mining The Stock Market: Which Measure Is Best ?	aapl adaptive adbe adsk aerospace agrawal agricultural airlines algorithms aluminum amat amount analysis aone auto automobiles baeza banking banks based been beverages biotechnology bollobas broadcasting brokerage building cable cant capital care center chemicals cient cluster clustering clusterings cmcsk communications companies comparison computational computer computers coms conference construction consumer containers csco data databases defense dell derivatives designing discovery distributors diversi document domestic drilling ective editors electric electrical electronics engineering entertainment equipment exploration faloutsos fast figure finance financial finding fitb focused fodo foods footwear fourth frakes from gaming geometric geometry global gold gunopulos hall hardware health homebuilding hotels household housewares huang imaging information insurance intc integrated intensive international investment iron klac larsen lecture leisure line linear lodging machinery mannila manolopoulos manufacturing markets matching medical mendelzon metals methods mining modeling money multi natural networking networks neural nncm noise normalization normfd notes novl ntrs orcl paper parts pcar peripherals personal photography piecewise pmtc post power prcurve prentice presence printing problems proc processing production products publishing queries query radio railroads ranganathan recent references regional related renganathan report research restaurants retail retrieval rule savings sawhney scaling science search semiconductor semiconductors separated sequence series services sets shim sial sigmod signi similar similarity smyth software specialty springer steel structures subsequence sunw supplies swami symposium table tcoma teaching telecommunications telephone television text textiles there time tlab tobacco translation truckers trucks using verlag vldb waste weigend well work workshop yates
http://doi.acm.org/10.1145/347090.347171	56	Data Mining Solves Tough Semiconductor Manufacturing Problems	activity allows anyone assurance berlin biometrics boston case computer control cordex data databases discovery easy engineer engineering extension factors feature gardner given group guide helsinki highly hill identified impact independent induction influencing input interfaces interpret introduction john kaufman kaufmanns knowledge kohonen kramer kulikowski large learn learning leivian machine maps mateo mcgraw means mitchell mixed montgomery morgan motorola multiple needs numbers organized organizing output participant perform peterson problem proceedings process programs quality quinlan range recommended references reliability replications reports response results rule screening self software sons springerverlag statistical stuart study systems team technology tests that this tool tools types unequal university upgraded user variables weiss wiley with workshop wsom
http://doi.acm.org/10.1145/347090.347159	44	Multivariate Discretization of Continuous Variables for Set Mining	addison admissible agrawal algorithm algorithms annals archive arti association associations attributes bakan based bayardo between bias california cance categorical cation change cial cient ciently classi computer conf conover continuous contrast data databases detecting discovery discretization dougherty edition entropy enumeration erences error fayyad features friedman from generalizations group http imielinski information intel interval irani irvine items john joint journal kaufmann know kohavi large learning ledge letin library ligence long machine management massive miller mining morgan multi multivariate nonparametric note opus over pages patterns pazzani practical principles proc programs psychological quanti quantitative quinlan rafsky reasoning references relational representation research review rules rymon sahami sample science search sedgewick sets sigkdd sigmod signi smirnov sommer sons srikant stability statistics supervised swami systematic tables technical test tests third through tools turney under university unordered unsupervised using valued wald webb wesley wiley wolfowitz yang
http://doi.acm.org/10.1145/347090.347099	7	Mining IC Test Data to Optimize VLSI Testing	aaai able abnormal academic algorithm although artificial based bayesian behavior cheeseman circuit classification computer concluding conference control cost could criterion current data decision decisiontheoretic demonstrated dempster department detect detecting detects diego dietterich directions dissertation doctoral does edition effective either enough exhaustive existing experiments fabrication following fountain four freeman from functional furthermore greedy guide handbook have hence hill improvements incomplete integrated intelligence journal just kaufmann kelly laird learning level likelihood machine magazine manufacturing mateo maximum mcgraw menlo methods microchip mined model more morgan national near optimal optimizing oregon paper park performing policy practical predictions press problems proceedings process processing produce produced profit quality references reflect remarks research responds royal rubin science self semiconductor seventh shown society specifically stage state statistical statistics still stochastic stopping stutz substantial taylor test testing than that them theoretic theory these third this thoroughly university value vlsi wafers well york zant zorich
http://doi.acm.org/10.1145/347090.347123	23	Efficient Clustering of High-Dimensional Data Sets with Application to Reference Matching	aaai academic access addison advances aggregation akaike algorithm algorithms alvey american analysis anderberg annealing apparatus appear application applications approaches approximately april august automatic automating available axford balltree based bentley berkeley best bibliographic birch bollacker bradley buckley california cation cient citation citeseer classi cluster clustering clusters comparison compression computer conf conference construction data database databases detecting deterministic digital discovery division domain duplicate dynamically editors elkan employing entropy expected fast fayyad fcsm felligi finkel five friedman from giles hernandez hirsh http hylton identifying ieee income increasing incremental independent indexing information institute integrating internal international internet james journal kennedy kilss know kruskal language large lawrence learning ledge libraries linkage livny logarithmic machine macromolecules management masters matches matching math maximization mccallum merge merging method mining mixture model modeling monge moore mulitple multiresolution nding nesamoney neural newcombe nigam omohundro optimization overlapping pages patent pedersen portals practice press principle problem problems proc proceedings processing publication purge ramakrishnan record records references regression reina related rennie report retrieval revenue rose salton sankaran sanko scaling science second sequence service sets seymore sigmod snowbird society software sources statistical statistics stolfo sunter suresh system systems technical techniques term text theory thesis third time toolkit tras trees tukey using very vital weighting wesley whril with wong workshop zhang
http://doi.acm.org/10.1145/347090.347172	57	Genome Scale Prediction of Protein Functional Class from Sequence using Data Mining	aaai aberystwyth able acad acid acids acknowledgements actual against agrawal albert algorithm algorithms alignments alone altschul analysis annotation approach approaches apweiler ashwin assignment automatic bairoch bank based better between bioinformatic biol biological biology biotechnology blast blattner brenner brown causation centre chemical chimeras chothia class classes classification classifications classifier clearly cole coli combined comm common comparison complete complicated compounds computer computing conclusion conference conserved consortium control convergent cost currently data databank database databases deciphering dehaspe demonstrated derisi described designing detection determination determined determining discover discovered discovery discussion distant distributions diverse dominant douglas duda dynamic each effective efficient eisenberg elegans errors escherichia evidence evolution evolutionary exist existence experiment experimental explanation exploring expression extendable fact factor families favour fawcett figure finding fold forcing forms forward found fourth frames frawley frequent from full function functional functions gapped gene general generation genes genetic genetics genome genomic genomics german given goffeau groups hart have heckerman henikoff here high hill homology horizontal however html http hubbard human hypothesis importance important imprecise improved increase inductive information insight instance interest intermediate international into investigating investigation isolation iyer john kaufmann kell kibler king knowledge koonin kremer laboratory learning life like lipman list little logic look machine machines make mannila many mappings marcotte mateo mcgraw menlo metabolic methods michael microarray mining mitchell mohammed more morgan muggleton multiple munakata murzin mycobacterium natl nature need nematode notoriously nucl nucleic occurred only optimization organisms other ouali ourselves over oxford paralogous paralogs park pathway pattern pearson pellegrine performance perspective phylogeny piatetsky platform possibilities possible powerful predict predicted predicting prediction predictions pregibon presented press probability proc proceedings produce profiles programmes programming programs projects protein proteins provide provost question quinlan raises random randomly reading references related resemble resource role rule ruled rules same sanger scale scene schulze science scop search searching secondary seems sequence sequences sequencing several shapiro showing shtm similar simpler single srinivasan steffen stolorez structural structure structures studies substructures such superfamily supplement support swissprot tatusov taxonomy taylor techniques teichmann templates test testing than thank that their these they this thompson together toivonen tools transfer transferred trembl trends tuberculosis under undetectable unidentified university unknown useful using utility vector visualization wales ways where wide wiley will with workers would yeates york young
http://doi.acm.org/10.1145/347090.347116	18	The IGrid Index: Reversing the Dimensionality Curse For Similarity Indexing in High Dimensional Space	addison aggarwal algorithms american analysis attributes berchtold beyer cactusclustering categorical conference data databases deerwester design dimensional dimensions distributions dynamic external faloutsos fractals ganti gehrke gionis goldstein graw guttman hashing high hilbert hinneburg icde icdt image improved index indexing indyk information introduction jagadish jain jects journal kamel katayama keim kelley kriegel latent madison mannila mcgill meaningful modern motwani multidimensional nearest neighbor neighbors pages performance probes proceedings queries query ramakrishnan references report retrieval ronkainen roussopoulos salton samet satoh science search searching sellis semantic shaft sigkdd sigmod similarity society spaces spatial spie storage structure structures summaries technical tree trees university unstable using video vincent vldb wesley what when white wisconsin with york
http://doi.acm.org/10.1145/347090.347150	36	Mining Asynchronous Periodic Patterns in Time Series Data	after algorithm association asynchronous average axis based chosen ciency cient combinations comparing conclusion cyclic data database demonstrate discovered discovery distance dong each ects elapse even figure given icde interesting maha mining most note overall ozden partial pattern patterns periodic possible potential proc process pruning ramaswamy reasonable references remaining repetition report research response rules scale segments series shows silberschatz since single stage task tested that then through time trivial valid validated validating validation vldb wang with yang
http://doi.acm.org/10.1145/347090.347192	71	Discovering Similar Patterns in Time Series	aaai able above acknowledgments added advances agrawal agustin akddm algorithms alonso analysis analysisthe analyzing anand appear applicable application applications applied approach artificial assessment association atlantic available avances balance barreiro based bases basis beach beckman been benicassim berndt best better blind both brachman california canada cara carlos centered centre cesar ceura characterization characterizing chavarr chile cicyt city clifford cnicas comments complementary computer computing conclusion conclusions conduct conf conference conocimiento considering construcci cope could curso curves data database databases degree dependency dependent design developing development directly discover discovered discovering discovery dise domain dong dynamometry efficient eleventh elicited eliciting engineering engineers enough entered entering episodes estudio evaluated evaluation every example experience expert experto expertos experts extracting extrapolated faced facultad faloutsos fast fayyad fernando finding fodo foundations fourth framework fraser frequent frica from fuertes function functions funded gained garc general generalise gleeson guide gupta however html http human iastate identifying ieee illescas implementation implications impossible incremental industrial inform information ingenier initially injuries intelligence intelligent international interpretaci interpretation into isocin isokinetic juristo kannus knowledge kriegel large later like lnai madrid mainly mannila manolopoulos marb mart master matching meant meantime mechanism medical medicine menlo mercer method methodological milwaukee mining models montes montreal more morphology muscle muscular national newport noteworthy numerical objective operation order organisation organisations orlando other para parameters park partial partly patterns pazos performance performed periodic physician physiotherapy piatetsky planned points polikar povinelli prediction preparation present press problem proc proceedings process processing produced project prototyping provided public purpose question ranganathan rectangles references refinement regard rehabilitaci rehabilitation report research robust roca rpolikar rules same santamar santiago scar schneider school science search seeger selection september sequence sequences sequential series sets seville shapiro sigmod similarity simon simposium sistema sistemas smyth society software spain spanish sports springer stages strength strikant subject submitted subsequence suited suppl swami system systemics systems taipei taiwan technical techniques temporal testing tests than thank thanks that their there therefore thesis they third this three tica ticas ticos time times toivonen total towards tree tutorial ultimate unable unifying university useful using uthursamy utility valente validated validating verifying verkamo verlag very volume wavelet wavelets were which with work would wttutorial zanoletty
http://doi.acm.org/10.1145/347090.347186	67	Evolutionary Algorithms in Data Mining: Multi-Objective Performance Modeling for Direct Marketing	aaai accurate addison algorithms altman analysis annual application applications approaches associates banking based best bhattacharyya bhattachryya business champaign churn classification comparing comparison computation computing concept conference constants craft data database david deception decile decision dejong depth differences different direct discovery discussion dissertation dominated driven edition effect eisenbeis elitism evaluated evett evolution evolutionary exploratory faster fayyad fernandez fifth figure file finance first fleming fonseca formulation forrest fourth functions gaeasiness gaimprovement generalization genetic gordon gpimprovement greenwich grefenstette guidelines hanson hilliard illinois implement improvement improves informs international introduction irwin journal kaufmann knowledge koza learning liepins lift lifts logistic london louis machine madison mahfoud marketing mass massand maximizing means methods michalewicz mining mitchell modeling models more morgan multi multiple mutation networks neural niching number numeric numreic numsolns objective optimality optimization optimizing over overview palmer pareto payoffs penalty performance piatetsky popsize population prediction press proceedings prodlifts product profit programming programs rawlins reading references regression response richardson rivett schaffer search second shapiro shepard simoudis sinkey sizes solutions some spears springer strategy structures summer table techniques test their third training tukey university urbana using value values vector verlag wesley whitley wiley wisconsin with without york
http://doi.acm.org/10.1145/347090.347101	9	Generating Non-Redundant Association Rules	aaai advances agrawal algorithm algorithms analysis association based bases basket bastide bayardo brin chess cient ciently closed computer concept conf confidence connect counting data database databases december dept discovered discovering discovery dynamic editors engineering fast fayyad figure formal formation foundations framework frequent from ganter generating godin grouping hatonen hsiao ieee implication incremental information institute interesting intl issues itemset itemsets june klemettinen knowledge lakhal large lattices learning long machine management mannila market mathematical menlo minimum mining missaoui mlnet most motwani mushroom navathe number october ogihara omiecinski pages park parthasarathy pasquier patterns polytechnic press pruning pumsb redundant references rensselaer report research ronkainen rule rules savasere science sigkdd sigmod springer srikant star statistics stumme synthetic systems taouil technical theoretical theory toivonen traditional tsur ullman using verkamo verlag vldb wille wkshp workshop zaki
http://doi.acm.org/10.1145/347090.347157	42	Application of Neural Networks to Biological Data Mining: A Case Study in Protein Sequence Classification	acids acknowledgments after algorithms alignment altschul analysis application applications applied approach barker based bayesian better bioinformatics biology biomolecular biosciences biosequences blast brazma cance cantly cation chirn classi classifying combinatorial combining compare complement computation computer conclusion conference contributions data database development discovering discovery discrimination domain done each elsevier erent evaluating evidence experimental extracting faster features following four fourth framework frequency frequently from functional gapped garavelli generation genome global gram haft have hidden hughey hunt include individually informatics input intel international jonassen karchin learning ledley ligent lipman local localization mackay madden main makarova management markov marr marzec maximum mclarty measures method mewes miller models molecular motifs namely ndings network networks neural novel nucleic occurring oligopeptide once only orcutt other oxford pages paper pattern patterns performance pfei phase preliminary presented press proceedings programs proposed protein references research results scha science scienti search sequence sequences shapiro shasha sigmod signi similarity sites solovyev some srinivasarao studied studies subfamilies superfamilies systems take techniques than that them they this three time tool tools trained training tsugita ukkonen university used using vilo wang weighting which with work yields york zhang
http://doi.acm.org/10.1145/347090.347124	24	Towards an Effective Cooperation of the User and the Computer for Classification	academic agrawal also ames angoss ankerst answertree approach attributes avignon based bayes beach belmont berchtold boosted breiman business center circle city classification classifier classifiers computer conf constraint construction coppersmith data database datasets decision diagrams diego discovery domingos edbt ellis elsen ester exploration exploring extending fast france francisco friedman halle hill hong horwood hosking html http ieee independence informatik interactive international interpretable intl introduction jagadish journal kane keim kluwer knowledge kohavi kriegel lakshmanan large learning liacc machine madigan mcgraw mehta michie mining mitchel multidimensional naive nasa neural newport nominal occam olshen partitioning proc publishers publishing razor references reggression research richardson ridgeway rissanen role ross scalable segments session sets sliq sommerfield spiegelhalter spss statistical statlog stone table targeting taylor technique techniques technology topic tree trees tutorial users version visual visualization visually wadsworth with york
http://doi.acm.org/10.1145/347090.347174	59	Predictive Modeling in Automotive Direct Marketing: Tools, Experiences and Open Issues	ability addressing aims algorithms allowing although application applications assessment assurance automate automobilproduzenten bartlmae because benefits berry bhattacharyya both business campaign case catlett changed chichester choosing chose classification clementine combining communication conclusions conference consider construction crisp cross curse curve customer data database diploma direct discovery documentation dresden economies effective einbindung eines erfolgsmessung estimating excellent experience experiences expert experts factory fawcett flexibility flexible formulierung framework future genetic gersten guide hand have having helps heterogeneous hipp home however html http indicators individual industry international knowledge kubat learned learning lessons lewis library lift ling linoff living machine mainly management marketing marketingaktionen masand matwin meant mining model modeling models must necessary organizational people performance piatetsky practical predictive problems proceedings process profile provost prozess prozesses quality quick quite realize reduce reference references relationship requires response reusing rules sales sampling scale scope scripting second sets shapiro skilled skills software solutions speeds standard standardized steuerung stream streams structures support supports systems targeted techniques textual therefore thesis thus tool tools towards training transfer unbalanced uncertainty university unsupervised used user users using various well when which while will wirth york
http://doi.acm.org/10.1145/347090.347188	69	Data Mining Techniques for Optimizing Inventories for Electronic Commerce	application applications artificial august bhat biswas bjorn blast brahma bulsari chemical classification cognition computers conference content control distributed dynamic eann engineer engineering expert exploration furnace fuzzy henrik ieee international iron ironmaking knoblock mcavoy mcclelland metal microstructure mitra modeling multilayer nallamali nets networks neural october operations osamu parallel perceptron prediction press principles probe process processing publications real references research rumelhart sawada saxen september sets silicon singh sridhar steel systems techniques temperatures timeseries toshiro transactions ushijima using world yuichi
http://doi.acm.org/10.1145/347090.347183	65	Identifying Prospective Customers	absence access agent agents agrawal algorithm allows also anderson annuity application applied applying architecture area avignon based been being belmont birch bombay breiman browser buyer canada center chile chou classification classifier clicks client clustering clusters company competing compiles computer conclusion conference conjunction consists created creates creation cross customer customers data database databases delivers density depicts deployed described description detailed devised dimitrios discovering discovery download during dynamically each easy edbt edna effective efficient electronic ensure ester example existing experimented exploits extending families fast fifth figure first force france friedman from gama general geographic grosman gunopulos hanspeter heights high households identifying implemented independent india individual industry information institute insurance interest jiawei john jorg jorma kamesam kauffman kaufman keeps knowledge kriegel kulikowski large leads learn learning level leverages life list livny machine maintains management manish manner manual martin mateo mehta method methodologies methodology methods mining miron modified montreal more morgan mouse noise note observations october olshen operation optimized oregon page paper parallel part parts pasumarti paul piloted population portland preferences preferred proc process product profile program programs prospect prospecting prospective prospects qualified quinlan raghu rakesh ramakrishnan raymond recent refer regression research results rissanen ross sales same sample sander santiago scalable scores scoring second segment segmentation selling separately september server sever several shafer sigmod skills sliq solution some spatial specify sprint starting stone study subselect successfully such support systems technique techniques technology term that their then this through tian track trees type uses using version very view vldb wadsworth watson weiss were which wishes with worldwide xiaowei yellin yorktown zhang
http://doi.acm.org/10.1145/347090.347180	63	Exploration Mining in Diabetic Patients Databases: Findings and Conclusions	aaai agrawal analysis analyze applications asia association associations august automated based beach beijing between beyond brin causal causation chen china cikm classification cleansing colorful computer concise conference constraints data database databases department dexa diego discovered discovery doctors engineering exception exceptions expert fifth finding florence fourth from general generated glymour hernandez ieee imielinski impressions inclusion integrating intelligible interesting international italy item items kaufmann klemetinen knowledge known large learned learning level ling machine makes mannila manu merge mining morgan motwani multi newport number organization pacific pages pakdd patterns pazzani plausible post predication problem proceedings program pruning purge quinlan references report results ronkainen rough rule rules scalable scheines science search sets shankle sigkdd sigmod silberschatz silverstein sixth spirtes springer srikant stanford stolfo structures summarization summarizing swami systems table technical techniques third toivonen transactions tsumoto tuzhilin ullman university using verkamo verlag warehousing what with year york
http://doi.acm.org/10.1145/347090.347110	15	Active Learning using Adaptive Resampling	accuracy active adaptive additive advances advertisements agents algorithm algorithms amounts angluin annals annual applications approaches apte arcing arti atlas august automated autonomous bagging bartlett based bauer benchmarks berry blake boosting breiman california cantly categorization cation catlett cial cient cing classi cochran cohn committee committees comparison comparitive computational computer concept conference connectionist constructing control customer damerau data databases dealing decision dept development dietterich direct discovery dmsk domains ectiveness eleventh empirical employing ensembles examples experimental experiments explanation feature fifteenth fifth fourteenth francis freund friedman from gale generalization ghahramani goetz growing hampp hastie have heterogeneous html http icml ieee improved indicate indurkhya information informative instances intel international internet irvine jensen john johnson jordan journal july kaufmann keogh know kohavi kulikowski kushmerick labeled labeling ladner learn learning ledge lewis liere ligence ligent lino logistic machine mamitsuka many margin marketing maximizing mccallum merz method methods miner mining mixture mlearn mlrespository model modeling models morgan multiple national needed networks neural nigam oates oles opper pages pedersen performance pool prediction presented problem proceedings processing progressive provost queries query random randomization reducing references regression remove report repository resampling research retrieval reuters rules sacri sales sampling schapire science selecting selection selective sequential seung seventeenth shamir sifting sigkdd signi sigr size software sompolinsky sons source stanford statistical statistics strategies study subset successful supervised support systems tadepalli taylor technical techniques text that their theory third this three tibshirani tishby training transactions trees uncertainty university unlabeled using variants various vast view voting weiss when wiley with without workshop yang
http://doi.acm.org/10.1145/347090.347196	74	Discovery of Multi-level Rules and Exceptions from a Distributed Database	aaai access accessing addison addsia advances agents aggregate aggregates aggregation agrawal albrecht algorithm alone also american analysis analytical anova applications applied area arning aronis association attempt attribute attributes authors automated been behavior behaviour bell between beyond biometrika bosworth bryk buchanan build cardiff care carried central chan chaudhuri cheung classification closely collective combination combine computing conducted conference conjunctive considered consisted consumer consumers contain cooper correlations could cross cube cubes data database databases dayal described detection deviation deviations differences dimension dimensions discovery discoverydriven distributed distributing dosis down drill each ecological edbt efficiency efficient either enable engineering european exceptions exploration exploring fast fayyad flairs form frequent froeschl from gathering generalised generalizing goldstein graefe gray grimson grossman group guided halstead have hershberger heterogeneous hewer hierarchical hierarchy highlighting hillol icde ideas increase individuals information integration interest interesting international into introducing involves irwin issues italy itemset iterative java johnson journal karali kargupta knowledge kolluri kreft kurki lamb large layman leading learning least leeuw lehrner less levels line linear lncs london look main mcclean measure measures megiddo meta metadata method millenium mining mixed model modeling models multilevel multiple murtagh navigate neter normal ntts olap operator options order oregon organising over overview paper parallel park part pdis personal perspective philip pirahesh pods portland pragash prague press primary principles proc proceeding proceedings processing prodromidis product products profiles project provost purchase purchasing raghavan rather raudenbush record references related relation relational research review robinson romaniuk royal rule rules sadreddini sage sarawagi scaling scotney september series shoshani sigmod similarities site skinner smart society sociological some sorrento sources springer squares statistical statistics stolfo sufficient suitable suonio supervised survey symposium systems task technology terms than there third this through tool total toward towards tselepis type used user uses using variation views wales warehouses warehousing wesley which wokingham work workshop world york
http://doi.acm.org/10.1145/347090.347176	60	X 8 £    ¥ A $  # 1 !  ¨  8 £    ¥ A $  8 ¨ § …  E  ¥£ ¥ 09)))9#ƒs  ©2F9B–09)))9#42h©c¢&¦"s `B9B4h¦¶s 92¢¤©¤7h)2¤&©) )¤YccB¦2h¦)&2¤9B¢&9£A A ¨  ¨ 8 A   # 1 g 8 £ £ 6 ¨  ¨ !      G £  £  ¨ 8£  ¥  P £ 3  ¥     !   §  ! £ ¥ ¥ A     6   ¡    ¡   8   ¥ 8 £  …   § ¨ § ¥£ ¡ ¤¤9¤©')%¦7R BRˆ& 0ˆ9&2h)7h©)¤(B94¦0¢  X  ¨ 8  ¥£ ¡  £ !  ¨3 •  £  $  ª 3  ¥ 6 ¡ £ ! B2% ‰¦¤C@& 57CB¦%&”Q'R9¦) `  8A ¨  ¡  A  E E  ¡ ¥   §  !  ¨  8 £    ¥ A $   # 1     £ Bh¦BF94A¢•©R)  t9B4¤©)))9#es 92F¤ „"! 3  s  A ¨ # 1  ¡  8 £  # ¥ ¨  6  3 !  ¡   6 ! £ § ¥ £` s A ¨£   6 6  BC¦£B92R9F©)¤2%R45"9&Rx& ¦052¦A¦$ RRh&$ 5B&¦&h¨ 0Ig%)2 0¢r¦&&"¢&¥  ))©#ˆ& 2&)¦"9B’&¦0(2¨ A ¨ $£  $  § ¨ ¥  ¥  §  § µ  £  $  ª X   ¥ A $ !   P  $ ¥£ ! 3  ¥ A § 6 `2&F9B(&¦)¦h))C¦y´9¦)Bh¦BF9)))©# A 79’BˆB¦29… a  !  ¨ ¥ $£  ¥£  ¨  ¥ ¡ £ E 6 ¡ £   8A ¨ 8 £    ¥ $  ¡  3   £ P ¨ ¡   ¡  ¥     ¥ £ ‹  £  $  ª X ¡ §  8  £  ¨ £ … ¨ £ ¥  $£   P 8 ©c&)2¨ )9#AA@¦&&"e–0¨ BC)¦ B9§0ƒxR&&¦ hp9£ `  £ £  ¨ § 3  6 A …  § ¨   6 ¡ £   8A ¨ 8 £    ¥ A $ V U S ³   # ¤B¦¦ ©´&¦0 0Rr)´©¦)2¦F©)))9#x‰DB¤s 921  ¡   $ # !   ¨ $    E  ¡ ¥ £ ¨A § a  •  £  $  ª X 8 £    ¥ A $   ©c&©"& eB%ƒ9Bœ9@9B¦¤2&Fw¦&&"x09)))9#R53  ¥ #  E f ¨  ¨ ! ¡ 8 #  ¡  d $ A $ b  ¡  3   #  ¨   ¡  ¥ £ ¨A § a  q  £ )©¢¢(2)h0C© 0¤)¦£c©–' ¤29‰9‰9B¦¤2&(cB¦ `%”ž&¦"¦B9Br2¦rs 92F©F©)))9#’‰h& B(9C@)¢E $  ª X ¥£ ¥ sA ¨  ¨ 8 A   # 1 !  ¨ 8 £    ¥ A $ 3  ¥ ¨  ¨  ¡  £ d    £  § ¥ s   # ¥ ²  £  $  ª X ¥ E  A 3 ¥ ¨ !   $  § £ E   § ¨ § ¥£ ¡ B¦)¤'"&hP 0re¦&&"R&I¦ABY'2C&&&" ¤gAA¢(“B9'¦0¢ 	adebooks agencies agency airfare airline airlines american amtrac amtrack amtrak antique anything backgrounds baseline bibliofind bookfinder books botany cards carribean city clickthrough continental creatacard delta discussion eagle eiweum emulator etsxsy fairs fhberp free full gameboy greatingcards greyhound groups hotel hotels hybrid insurance lariam mail nintendo northwest plane pnon pokemon postnet print rare rate references replace reservations roms sabre schedule schedules seminar southwest statistics suggestion swan talk tickets train trains travel travelosity united used xwus
http://doi.acm.org/10.1145/347090.347129	28	Visualization and The Process of Modeling: A Cognitive-theoretic View	aaai about academic acquisition addison advanced alabastro alan allen amsterdam analysis anderson anne arlington article assistant associates association attributes baddeley based basic beckmann belmont benbasat beverly books business california cambridge card carnegie chapman charlotte cheshire cleveland cliffs cognition cognitive colin collected communication communications company composite computer computers computing conference connecticut cons corin creative creativity daniel data david december decision defending department designing diagrammatic discoveries discovery display distinguishing division donald dozen dynamic earnshaw editor editors education edward effort elements elsevier engineering englewood envisioning erlbaum evaluating ewoldsen expert experts explanations exploratory fall finke formalism formulation forum francisco franck from gardner gathercole gerd gifford gina glenn graphics graphing graphs greg gurr hall harvard herbert heuristics hillsdale holland hove howard human humanformalism icis ieee imagery impact incentives information innovative insights institute interacting interaction interfaces international intonspeterson inventions iris isomorphism izak january jean jock john jones journal kaufmann keith kurt lack language languages large laurie lawrence learning limits literature logie london machine mackinlay make management manufacturing margaret mark marriot marylyn massey mathematical mathematics mcgill mellon memory menlo meyer michael mind model modeler modelers modeling monterey morgan naval navigation nested netherlands newell nicholas norman north norton office operations outs overcoming park parker perception perspective peter pinker pittsburgh polytechnic powell prentice press problem proceedings process pros psychology publishers publishing quantitative reading readings reasoning references reisbert rensselaer report representations research rita robert role ronald roskos routledge savage schoenfeld science sciences selection shneiderman simon sketches skill smart software solving spreadsheets springer statistics stenning stephen steven strategy structures stuart students studies study submitted susan swanston symposium systems tables teachers teaching technical technology tegarden that theories theory thesis things think thomas through today todd transactions troy tufte tukey unified university using vanlehn verlag versus vessey vince vision visual visualization visualizing volume wade wadsworth waisel wallace ware weighing wesley what when willemain william with working works york
http://doi.acm.org/10.1145/347090.347184	66	Targeting the Right Students Using Data Mining	addressing after aggregating agrawal algorithms analysis artificial association attributes audit barrier basket baskiri bayardo bayes benefits best better between bins boat break brin brunk build caep campaign card case categorical chan chicago class classification classifier classifiers clearly code combining comparison complete configuration constrained constraintbased construction continuous correcting cost costs counting credit cross curse customer data database databases decision dense detection dietterich different dimensional direct discovering discovery discretization distributions divide does dong dynamic each effective emerging enrollment entropy equally error estimating explain exploratory extending fast fawcett fawcettt fayyad feng fraud from fukuda ganti gehrke gunopulos heights html http hughes hume icde icml ijcai imbalanced imielinski implication imprecise integrating intelligence inter interesting interval into intrusion irani irwin items itemset itemsets john journal kaufmann knoweldege kohavi kubat lakshmanan large learning level library lift ling list local long machine manley mannila march market marketer marketing massand matwin mehta meretkis merz method methods minimum mining misclassification mlearn mlrepository modelling models morgan morimoto morishita most motwani multi multiclass multiple murphy numeric optimisation optimistic optimized other others output parallel patterns pavlov pazzani performance performs pfleger piatetsky power prediction problems produced professional profile program provost pruning quinlan ramakrishnan ranked ranking rankings rastogi reducing references report repository research rule rules sampling sanjeev save scalable scaleable scheme science scoring secondgeneration selection sets shafer shapiro shim shows sigmod smyth solutions solving space sprint srikant stolfo strategies students study superior supports swami system systems table tapping target techniques than that toivonen tokuyama tong tools towards training transaction transactions tree tsur ullman under uniform university user using valued various visualization vldb weak with wong wuthrich yorktown your zhang zytkow
http://doi.acm.org/10.1145/347090.347114	17	Depth First Generation of Long Patterns	aaai access agarwal aggarwal agrawal algorithm algorithms appear association attributes basket baskets bayardo between beyond bioinformatics biological brin cache candidate categorical cient ciently cikm combinatorial computing conference constrained constraints correlations counting data databases depth deshpande dewitt dimensional discovered discovering discovery distributed dunkel dynamic edbt enumeration fast figure finding first floratos framework frequent from fukuda generalized generalizing generation gunopulos hidber icde icdt imielinski implication interactive interesting international items itemset itemsets jection journal july kedem klementtinen know knowledge lakshmanan large ledge level long lowest mannila market maximum mining morimoto morishita most motwani navathe nding note numeric ogihara omiecinski online optimization optimized organization pages pang paral parthasarathy pattern patterns pincer pods prasad principles proceedings quantitative queries randomized rastogi reasoning references relational report representation research rigoutsos ronkainen rule rules rymon saluja savasere scheme search sentences sequences sets shim sigkdd sigmod silverstein soparkar speci srikant support swami systematic tables that through toivonen tokuyama tree tsur ullman using variable verkamo very visualization vldb with without workshop zaki