1. Abalone: Predict the age of abalone from physical measurements 2. Abscisic Acid Signaling Network: The objective is to determine the set of boolean rules that describe the interactions of the nodes within this plant signaling network. The dataset includes 300 separate boolean pseudodynamic simulations using an asynchronous update scheme. 3. Acute Inflammations: The data was created by a medical expert as a data set to test the expert system,
which will perform the presumptive diagnosis of two diseases of the urinary system.
4. Adult: Predict whether income exceeds $50K/yr based on census data. Also known as "Census Income" dataset. 5. Annealing: Steel annealing data 6. Anonymous Microsoft Web Data: Log of anonymous users of www.microsoft.com; predict areas of the web site a user visited based on data on other areas the user visited. 7. Arcene: ARCENE's task is to distinguish cancer versus normal patterns from mass-spectrometric data. This is a two-class classification problem with continuous input variables. This dataset is one of 5 datasets of the NIPS 2003 feature selection challenge. 8. Arrhythmia: Distinguish between the presence and absence of cardiac arrhythmia and classify it in one of the 16 groups. 9. Artificial Characters: Dataset artificially generated by using first order theory which describes structure of ten capital letters of English alphabet 10. Audiology (Original): Nominal audiology dataset from Baylor 11. Audiology (Standardized): Standardized version of the original audiology database 12. Australian Sign Language signs: This data consists of sample of Auslan (Australian Sign Language) signs. Examples of 95 signs were collected from five signers with a total of 6650 sign samples. 13. Australian Sign Language signs (High Quality): This data consists of sample of Auslan (Australian Sign Language) signs. 27 examples of each of 95 Auslan signs were captured from a native signer using high-quality position trackers 14. Auto MPG: Revised from CMU StatLib library, data concerns city-cycle fuel consumption 15. Automobile: From 1985 Ward's Automotive Yearbook 16. Bach Chorales: Time-series data based on chorales; challenge is to learn generative grammar; data in Lisp 17. Badges: Badges labeled with a "+" or "-" as a function of a person's name 18. Bag of Words: This data set contains five text collections in the form of bags-of-words. 19. Balance Scale: Balance scale weight & distance database 20. Balloons: Data previously used in cognitive psychology experiment; 4 data sets represent different conditions of an experiment 21. Blood Transfusion Service Center: Data taken from the Blood Transfusion Service Center in Hsin-Chu City in Taiwan -- this is a classification problem. 22. Breast Cancer: Breast Cancer Data (Restricted Access) 23. Breast Cancer Wisconsin (Diagnostic): Diagnostic Wisconsin Breast Cancer Database 24. Breast Cancer Wisconsin (Original): Original Wisconsin Breast Cancer Database 25. Breast Cancer Wisconsin (Prognostic): Prognostic Wisconsin Breast Cancer Database 26. CalIt2 Building People Counts: This data comes from the main door of the CalIt2 building at UCI. 27. Car Evaluation: Derived from simple hierarchical decision model, this database may be useful for testing constructive induction and structure discovery methods. 28. Census Income: Predict whether income exceeds $50K/yr based on census data. Also known as "Adult" dataset. 29. Census-Income (KDD): This data set contains weighted census data extracted from the 1994 and 1995 current population surveys conducted by the U.S. Census Bureau. 30. Challenger USA Space Shuttle O-Ring: Task: predict the number of O-rings that experience thermal distress on a flight at 31 degrees F given data on the previous 23 shuttle flights 31. Character Trajectories: Multiple, labelled samples of pen tip trajectories recorded whilst writing individual characters. All samples are from the same writer, for the purposes of primitive extraction. Only characters with a single pen-down segment were considered. 32. Chess (Domain Theories): 6 different domain theories for generating legal moves of chess 33. Chess (King-Rook vs. King): Chess Endgame Database for White King and Rook against Black King (KRK). 34. Chess (King-Rook vs. King-Knight): Knight Pin Chess End-Game Database Creator 35. Chess (King-Rook vs. King-Pawn): King+Rook versus King+Pawn on a7 (usually abbreviated KRKPA7). 36. Cloud: Little Documentation 37. CMU Face Images: This data consists of 640 black and white face images of people taken with varying pose (straight, left, right, up), expression (neutral, happy, sad, angry), eyes (wearing sunglasses or not), and size 38. Coil 1999 Competition Data: This data set is from the 1999 Computational Intelligence and Learning (COIL) competition. The data contains measurements of river chemical concentrations and algae densities. 39. Communities and Crime: Communities within the United States. The data combines socio-economic data from the 1990 US Census, law enforcement data from the 1990 US LEMAS survey, and crime data from the 1995 FBI UCR. 40. Computer Hardware: Relative CPU Performance Data, described in terms of its cycle time, memory size, etc. 41. Concrete Compressive Strength: Concrete is the most important material in civil engineering. The concrete compressive strength is a highly nonlinear function of age and ingredients. 42. Concrete Slump Test: Concrete is a highly complex material. The slump flow of concrete is not only determined by the water content, but that is also influenced by other concrete ingredients. 43. Congressional Voting Records: 1984 United Stated Congressional Voting Records; Classify as Republican or Democrat 44. Connect-4: Contains connect-4 positions 45. Connectionist Bench (Nettalk Corpus): The file "nettalk.data" contains a list of 20,008 English words, along with a phonetic transcription for each word. The task is to train a network to produce the proper phonemes 46. Connectionist Bench (Sonar, Mines vs. Rocks): The task is to train a network to discriminate between sonar signals bounced off a metal cylinder and those bounced off a roughly cylindrical rock. 47. Connectionist Bench (Vowel Recognition - Deterding Data): Speaker independent recognition of the eleven steady state vowels of British English using a specified training set of lpc derived log area ratios. 48. Contraceptive Method Choice: Dataset is a subset of the 1987 National Indonesia Contraceptive Prevalence Survey. 49. Corel Image Features: This dataset contains image features extracted from a Corel image collection. Four sets of features are available based on the color histogram, color histogram layout, color moments, and co-occurence 50. Covertype: Forest CoverType dataset 51. Credit Approval: This data concerns credit card applications; good mix of attributes 52. Cylinder Bands: Used in decision tree induction for mitigating process delays known as "cylinder bands" in rotogravure printing 53. Dermatology: Aim for this dataset is to determine the type of Eryhemato-Squamous Disease. 54. Dexter: DEXTER is a text classification problem in a bag-of-word representation. This is a two-class classification problem with sparse continuous input variables. This dataset is one of five datasets of the NIPS 2003 feature selection challenge.
55. DGP2 - The Second Data Generation Program: Generates application domains based on specific parameters, number of features, and proportion of positive to negative examples 56. Diabetes: This diabetes dataset is from AIM '94 57. Document Understanding: Five concepts, expressed as predicates, to be learned 58. Dodgers Loop Sensor: Loop sensor data was collected for the Glendale on ramp for the 101 North freeway in Los Angeles 59. Dorothea: DOROTHEA is a drug discovery dataset. Chemical compounds represented by structural molecular features must be classified as active (binding to thrombin) or inactive. This is one of 5 datasets of the NIPS 2003 feature selection challenge. 60. E. Coli Genes: Data giving characteristics of each ORF (potential gene) in the E. coli genome. Sequence, homology (similarity to other genes) and structural information, and function (if known) are provided. 61. EBL Domain Theories: Assorted small-scale domain theories 62. Echocardiogram: Data for classifying if patients will survive for at least one year after a heart attack 63. Ecoli: This data contains protein localization sites 64. Economic Sanctions: Domain Theory on Economic Sanctions; Undocumented 65. EEG Database: This data arises from a large study to examine EEG correlates of genetic predisposition to alcoholism. It contains measurements from 64 electrodes placed on the scalp sampled at 256 Hz 66. El Nino: The data set contains oceanographic and surface meteorological readings taken from a series of buoys positioned throughout the equatorial Pacific. 67. Entree Chicago Recommendation Data: This data contains a record of user interactions with the Entree Chicago restaurant recommendation system. 68. Flags: From Collins Gem Guide to Flags, 1986 69. Forest Fires: This is a difficult regression task, where the aim is to predict the burned area of forest fires, in the northeast region of Portugal, by using meteorological and other data (see details at: http://www.dsi.uminho.pt/~pcortez/forestfires). 70. Function Finding: Cases collected mostly from investigations in physical science; intention is to evaluate function-finding algorithms 71. Gisette: GISETTE is a handwritten digit recognition problem. The problem is to separate the highly confusible digits '4' and '9'. This dataset is one of five datasets of the NIPS 2003 feature selection challenge.
72. Glass Identification: From USA Forensic Science Service; 6 types of glass; defined in terms of their oxide content (i.e. Na, Fe, K, etc) 73. Haberman's Survival: Dataset contains cases from study conducted on the survival of patients who had undergone surgery for breast cancer 74. Hayes-Roth: Topic: human subjects study 75. Heart Disease: 4 databases: Cleveland, Hungary, Switzerland, and the VA Long Beach 76. Hepatitis: From G.Gong: CMU; Mostly Boolean or numeric-valued attribute types; Includes cost data (donated by Peter Turney) 77. Hill-Valley: Each record represents 100 points on a two-dimensional graph. When plotted in order (from 1 through 100) as the Y co-ordinate, the points will create either a Hill (a “bump” in the terrain) or a Valley (a “dip” in the terrain). 78. Horse Colic: Well documented attributes; 368 instances with 28 attributes (continuous, discrete, and nominal); 30% missing values 79. Housing: Taken from StatLib library 80. ICU: Data set prepared for the use of participants for the 1994 AAAI Spring Symposium on Artificial Intelligence in Medicine. 81. Image Segmentation: Image data described by high-level numeric-valued attributes, 7 classes 82. Insurance Company Benchmark (COIL 2000): This data set used in the CoIL 2000 Challenge contains information on customers of an insurance company. The data consists of 86 variables and includes product usage data and socio-demographic data 83. Internet Advertisements: This dataset represents a set of possible advertisements on Internet pages. 84. Internet Usage Data: This data contains general demographic information on internet users in 1997. 85. Ionosphere: Classification of radar returns from the ionosphere 86. IPUMS Census Database: This data set contains unweighted PUMS census data from the Los Angeles and Long Beach areas for the years 1970, 1980, and 1990. 87. Iris: Famous database; from Fisher, 1936 88. ISOLET: Goal: Predict which letter-name was spoken--a simple classification task. 89. Japanese Credit Screening: Includes domain theory (generated by talking to Japanese domain experts); data in Lisp 90. Japanese Vowels: This dataset records 640 time series of 12 LPC cepstrum coefficients taken from nine male speakers. 91. KDD Cup 1998 Data: This is the data set used for The Second International Knowledge Discovery and Data Mining Tools Competition, which was held in conjunction with KDD-98 92. KDD Cup 1999 Data: This is the data set used for The Third International Knowledge Discovery and Data Mining Tools Competition, which was held in conjunction with KDD-99 93. Kinship: Relational dataset 94. Labor Relations: From Collective Bargaining Review 95. LED Display Domain: From Classification and Regression Trees book; We provide here 2 C programs for generating sample databases 96. Lenses: Database for fitting contact lenses 97. Letter Recognition: Database of character image features; try to identify the letter 98. Libras Movement: The data set contains 15 classes of 24 instances each. Each class references to a hand movement type in LIBRAS (Portuguese
name 'LÍngua BRAsileira de Sinais', oficial brazilian signal language). 99. Liver Disorders: BUPA Medical Research Ltd. database donated by Richard S. Forsyth 100. Logic Theorist: All code for Logic Theorist 101. Low Resolution Spectrometer: From IRAS data -- NASA Ames Research Center 102. Lung Cancer: Lung cancer data; no attribute definitions 103. Lymphography: This lymphography domain was obtained from the University Medical Centre, Institute of Oncology, Ljubljana, Yugoslavia. (Restricted access) 104. M. Tuberculosis Genes: Data giving characteristics of each ORF (potential gene) in the M. tuberculosis bacterium. Sequence, homology (similarity to other genes) and structural information, and function (if known) are provided 105. Madelon: MADELON is an artificial dataset, which was part of the NIPS 2003 feature selection challenge. This is a two-class classification problem with continuous input variables. The difficulty is that the problem is multivariate and highly non-linear. 106. MAGIC Gamma Telescope: Data are MC generated to simulate registration of high energy gamma particles in an atmospheric Cherenkov telescope 107. Mammographic Mass: Discrimination of benign and malignant mammographic masses based on BI-RADS attributes and the patient's age. 108. Mechanical Analysis: Fault diagnosis problem of electromechanical devices; also PUMPS DATA SET is newer version with domain theory and results 109. Meta-data: Meta-Data was used in order to give advice about which classification method is appropriate for a particular dataset (taken from results of Statlog project). 110. Mobile Robots: Learning concepts from sensor data of a mobile robot; set of data sets 111. Molecular Biology (Promoter Gene Sequences): E. Coli promoter gene sequences (DNA) with partial domain theory 112. Molecular Biology (Protein Secondary Structure): From CMU connectionist bench repository; Classifies secondary structure of certain globular proteins 113. Molecular Biology (Splice-junction Gene Sequences): Primate splice-junction gene sequences (DNA) with associated imperfect domain theory 114. MONK's Problems: A set of three artificial domains over the same attribute space; Used to test a wide range of induction algorithms 115. Moral Reasoner: Horn-clause model that qualitatively simulates moral reasoning; Theory includes negated literals 116. Movie: This data set contains a list of over 10000 films including many older, odd, and cult films. There is information on actors, casts, directors, producers, studios, etc. 117. MSNBC.com Anonymous Web Data: This data describes the page visits of users who visited msnbc.com on September 28, 1999. Visits are recorded at the level of URL category (see description) and are recorded in time order. 118. Multiple Features: This dataset consists of features of handwritten numerals (`0'--`9') extracted from a collection of Dutch utility maps 119. Mushroom: From Audobon Society Field Guide; mushrooms described in terms of physical characteristics; classification: poisonous or edible 120. Musk (Version 1): The goal is to learn to predict whether new molecules will be musks or non-musks 121. Musk (Version 2): The goal is to learn to predict whether new molecules will be musks or non-musks 122. Netflix Prize: This is the official data set used in the Netflix Prize competition. The data consists of about 100 million movie ratings, and the goal is to predict missing entries in the movie-user rating matrix. 123. NSF Research Award Abstracts 1990-2003: This data set consists of (a) 129,000 abstracts describing NSF awards for basic research, (b) bag-of-word data files extracted from the abstracts, (c) a list of words used for indexing the bag-of-word 124. Nursery: Nursery Database was derived from a hierarchical decision model originally developed to rank applications for nursery schools. 125. Optical Recognition of Handwritten Digits: Two versions of this database available; see folder 126. Othello Domain Theory: Used in research to generate features for an inductive learning system 127. Ozone Level Detection: Two ground ozone level data sets are included in this collection. One is the eight hour peak set (eighthr.data), the other is the one hour peak set (onehr.data). Those data were collected from 1998 to 2004 at the Houston, Galveston and Brazoria area. 128. Page Blocks Classification: The problem consists of classifying all the blocks of the page layout of a document that has been detected by a segmentation process. 129. Parkinsons: Oxford Parkinson's Disease Detection Dataset 130. Pen-Based Recognition of Handwritten Digits: Digit database of 250 samples from 44 writers 131. Pima Indians Diabetes: From National Institute of Diabetes and Digestive and Kidney Diseases; Includes cost data (donated by Peter Turney) 132. Pioneer-1 Mobile Robot Data: This dataset contains time series sensor readings of the Pioneer-1 mobile robot. The data is broken into "experiences" in which the robot takes action for some period of time and experiences a control 133. Pittsburgh Bridges: Bridges database that has original and numeric-discretized datasets 134. Plants: Data has been extracted from the USDA plants database. It contains all plants (species and genera) in the database and the states of USA and Canada where they occur. 135. Poker Hand: Purpose is to predict poker hands 136. Post-Operative Patient: Dataset of patient features 137. Primary Tumor: From Ljubljana Oncology Institute 138. Prodigy: Assorted domains like blocksworld, eightpuzzle, and schedworld. 139. Protein Data: Undocumented 140. Pseudo Periodic Synthetic Time Series: This data set is designed for testing indexing schemes in time series databases. The data appears highly periodic, but never exactly repeats itself. 141. Quadruped Mammals: The file animals.c is a data generator of structured instances representing quadruped animals 142. Qualitative Structure Activity Relationships: Two sets of datasets are given: pyrimidines and triazines 143. Reuters Transcribed Subset: This dataset is created by reading out 200 files from the 10 largest Reuters
classes and using an Automatic Speech Recognition system to create
corresponding transcriptions. 144. Reuters-21578 Text Categorization Collection: This is a collection of documents that appeared on Reuters newswire in 1987. The documents were assembled and indexed with categories. 145. Robot Execution Failures: This dataset contains force and torque measurements on a robot after failure detection. Each failure is characterized by 15 force/torque samples collected at regular time intervals 146. SECOM: Data from a semi-conductor manufacturing process 147. Semeion Handwritten Digit: 1593 handwritten digits from around 80 persons were scanned, stretched in a rectangular box 16x16 in a gray scale of 256 values. 148. Servo: Data was from a simulation of a servo system 149. Shuttle Landing Control: Tiny database; all nominal values 150. Solar Flare: Each class attribute counts the number of solar flares of a certain class that occur in a 24 hour period 151. Soybean (Large): Michalski's famous soybean disease database 152. Soybean (Small): Michalski's famous soybean disease database 153. Spambase: Classifying Email as Spam or Non-Spam 154. SPECT Heart: Data on cardiac Single Proton Emission Computed Tomography (SPECT) images. Each patient classified into two categories: normal and abnormal. 155. SPECTF Heart: Data on cardiac Single Proton Emission Computed Tomography (SPECT) images. Each patient classified into two categories: normal and abnormal. 156. Sponge: Data on sponges; Attributes in spanish 157. Statlog (Australian Credit Approval): This file concerns credit card applications. This database exists elsewhere in the repository (Credit Screening Database) in a slightly different form 158. Statlog (German Credit Data): This dataset classifies people described by a set of attributes as good or bad credit risks. Comes in two formats (one all numeric). Also comes with a cost matrix 159. Statlog (Heart): This dataset is a heart disease database similar to a database already present in the repository (Heart Disease databases) but in a slightly different form 160. Statlog (Image Segmentation): This dataset is an image segmentation database similar to a database already present in the repository (Image segmentation database) but in a slightly different form. 161. Statlog (Landsat Satellite): Multi-spectral values of pixels in 3x3 neighbourhoods in a satellite image, and the classification associated with the central pixel in each neighbourhood 162. Statlog (Shuttle): The shuttle dataset contains 9 attributes all of which are numerical. Approximately 80% of the data belongs to class 1 163. Statlog (Vehicle Silhouettes): 3D objects within a 2D image by application of an ensemble of shape feature extractors to the 2D silhouettes of the objects. 164. Statlog Project: Various Databases: Vehicle silhouttes, Landsat Sattelite, Shuttle, Australian Credit Approval, Heart Disease, Image Segmentation, German Credit 165. Student Loan Relational: Student Loan Relational Domain 166. Synthetic Control Chart Time Series: This data consists of synthetically generated control charts. 167. Syskill and Webert Web Page Ratings: This database contains HTML source of web pages plus the ratings of a single user on these web pages. Web pages are on four seperate subjects (Bands- recording artists; Goats; Sheep; and BioMedical) 168. Teaching Assistant Evaluation: The data consist of evaluations of teaching performance; scores are "low", "medium", or "high" 169. Thyroid Disease: 10 separate databases from Garavan Institute 170. Tic-Tac-Toe Endgame: Binary classification task on possible configurations of tic-tac-toe game 171. Trains: 2 data formats (structured, one-instance-per-line) 172. Twenty Newsgroups: This data set consists of 20000 messages taken from 20 newsgroups. 173. UJI Pen Characters: Data consists of written characters in a UNIPEN-like format 174. UJI Pen Characters (Version 2): A pen-based database with more than 11k isolated handwritten characters 175. Undocumented: Various datasets without documentation (feel free to explore!) 176. University: Data in original (LISP-readable) form 177. UNIX User Data: This file contains 9 sets of sanitized user data drawn from the command histories of 8 UNIX computer users at Purdue over the course of up to 2 years. 178. URL Reputation: Anonymized 120-day subset of the ICML-09 URL data containing 2.4 million examples and 3.2 million features. 179. US Census Data (1990): The USCensus1990raw data set contains a one percent sample of the Public Use Microdata Samples (PUMS) person records drawn from the full 1990 census sample. 180. Volcanoes on Venus - JARtool experiment: The JARtool project was a pioneering effort to develop an automatic system for cataloging small volcanoes in the large set of Venus images returned by the Magellan spacecraft. 181. Water Treatment Plant: Multiple classes predict plant state 182. Waveform Database Generator (Version 1): CART book's waveform domains 183. Waveform Database Generator (Version 2): CART book's waveform domains 184. Wine: Using chemical analysis determine the origin of wines 185. Wine Quality: Two datasets are included, related to red and white vinho verde wine samples, from the north of Portugal. The goal is to model wine quality based on physicochemical tests (see [Cortez et al., 2009], http://www3.dsi.uminho.pt/pcortez/wine/). 186. Yeast: Predicting the Cellular Localization Sites of Proteins 187. Zoo: Artificial, 7 classes of animals | 
