A Methodology for Direct and Indirect Discrimination Prevention in Data Mining

Size: px
Start display at page:

Download "A Methodology for Direct and Indirect Discrimination Prevention in Data Mining"

Transcription

1 A Methodology for Direct and Indirect Discrimination Prevention in Data Mining Sara Hajian and Josep Domingo-Ferrer IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2013 Presented by Polina Rozenshtein

2 Outline Problem addressed Direct and indirect discrimination Background, definitions and measures Approach proposed Discrimination Measurement Data Transformation Algorithms and running time Experimental results

3 Problem Discrimination: direct or indirect. Direct discrimination: decisions are made based on sensitive attributes. Indirect discrimination (redlining): decisions are made based on nonsensitive attributes which are strongly correlated with biased sensitive ones. Decision rules

4 Definitions Dataset collection of records Item - attribute with its value, e.g., Race = black item set - collection of items X: {Foreign worker = Yes; City = NYC} classification rule - X C {yes/no} {Foreign worker = Yes; City = NYC} Hire = no

5 Definitions support, supp(x) - fraction of records that contain X confidence, conf X C - how often C appears in records that contain X conf X C = supp(x,c) supp(x) frequent classification rule: supp X, C > s conf X C > c negated item set: X = {Foreign worker = Yes} X = {Foreign worker = No}

6 Classification rules DI s - predetermined discriminatory items DI s = {Foreign worker = Yes; Race = Black} X C - potentially discriminatory (PD) X = A, B with A DI s, B DI s {Foreign worker = Yes; City = NYC} Hire = No X C - potentially nondiscriminatory (PND) X = D, B with D DI s, B DI s {Zip = 10451; City = NYC} Hire = No

7 Direct Discrimination Measure extended lift (elift): elift A, B C = conf(a,b C) conf(b C) A DI S A, B C is α-protective, if and elift A, B C < α A, B C is α-discriminatory, if elift A, B C α

8 Indirect Discrimination Measure Theorem: Let r: D, B C is PND; γ = conf(r: D, B C) and δ = conf B C > 0 A DI s, conf r b1 : A, B D β 1, conf r b2 : D, B A β 2 > 0 f x = β 1 β 2 β 2 + x 1 elb x, y = f(x) y, if f x > 0 0, otherwise Then if elb γ, δ α, then PD r : A, B C is α-discriminatory

9 Indirect Discrimination or not A PND rule r: D, B C is a redlining rule, if it could yield αdiscriminatory rule r 0 : A, B C available knowledge rules r b1 : A, B D and r b2 : D, B A With A DI s {Zip = 10451; City = NYC} Hire = No. A PND rule r: D, B C is a nonredlining rule, if it cannot yield α-discriminatory rule r 0 : A, B C available rules r b1 : A, B D and r b2 : D, B A and A DI s {Experience = Low; City = NYC} Hire = No.

10 The Approach Discrimination measurement: Find PD and PND Direct discrimination: In PD find α-discriminatory by elif() Indirect discrimination: In PND find redlining by elb() + background knowledge Data transformation: Alter dataset and remove discriminatory biases Minimum impact on data and legitimate rules

11 Direct rules protection A ID S, Wish elif r : A, B C > α conf(a,b C) conf(b C) < α Decrease conf A, B C = supp(a,b,c) supp(a,b) Decrease conf(a, B C) by increasing supp(a, B)! A, B C A, B C supp A, B, C remains the same

12 Direct rules protection 2 Wish elif r : A, B C > α conf(a,b C) conf(b C) < α Increase conf B C = supp(b,c) supp(b) Increase supp B, C! A, B C A, B C supp B remains the same

13 Direct rules generalization PD: {Foreign worker = Yes; City = NYC} Hire = No. PND: {Experience = Low; City = NYC} Hire = No. If conf r: D, B C conf r : A, B C, and conf A, B D = 1 then PD rule r : A, B C is an instance of a PND rule r: D, B C

14 Direct rules generalization PD: {Foreign worker = Yes; City = NYC} Hire = No. PND: {Experience = Low; City = NYC} Hire = No. 1) If conf r: D, B C p conf r : A, B C, 2) and conf A, B D p then PD rule r : A, B C is an p-instance of a PND rule r: D, B C Change α-discriminatory to be p-instance of some PND rule r: D, B C

15 Direct rules generalization Condition 2 is satisfied, but Condition 1 is not: Wish conf r: D, B C p conf r : A, B C Decrease conf r : A, B C, preserve conf A, B D A, B, D C A, B, D C Condition 1 is satisfied, but Condition 2 is not: Wish conf A, B D p Increase conf A, B D, preserve conf r: D, B C p conf r : A, B C Impossible

16 Direct rules generalization Use generalization when possible to increase number of PND Use generalization when at least Condition 2 is satisfied After generalization is done, use methods for direct protection Try to perform minimum transformation

17 Indirect Rule Protection The same strategy as for Directed Rule Protection: Wish elb conf r: D, B C, conf B C > α conf r b1 :A,B D conf r b2 :D,B A conf r b2:d,b A +conf r:d,b C 1 conf(b C) < α Method 1: Decrease conf A, B D A, B, D C A, B, D C Method 2: Increase conf B C A, B, D C A, B, D C

18 Simultaneous direct and indirect discrimination prevention Method 1 Method 2 Direct Rule Protection A, B C A, B C A, B C A, B C Indirect Rule Protection A, B, D C A, B, D C A, B, D C A, B, D C Lemma 1. Method 1 for DRP cannot be used for simultaneous DRP and IRP Method 1 for DRP might undo the protection provided by Method 1 for IRP

19 Simultaneous direct and indirect discrimination prevention Method 1 Method 2 Direct Rule Protection A, B C A, B C A, B C A, B C Indirect Rule Protection A, B, D C A, B, D C A, B, D C A, B, D C Lemma 2. Method 2 for IRP is beneficial for Method 2 for DRP. Method 2 for DRP is at worst neutral for Method 2 for IRP. Method 2 for DRP and Method 2 for IRP both increase conf(b C).

20 Simultaneous direct and indirect discrimination prevention Transform PD to PND when possible Run Method 2 for IRP for PND and Method 2 for DRP for the rest PD.

21 Algorithms DB database FR frequent rules MR direct discriminative rules DI s discriminative item set

22 Computational Cost m - the number of records in DB k - number of rules in FR h - number of records in subset DB c n - the number of discriminatory rules in MR O(m) to get DB c O(kh) to get impact(db c ) for all db c DB c O(h log h ) for sorting O(dm) for modification O(n (m + kh + h log h + dm))

23 Experiments German credit data set and adult data set. Direct discrimination prevention degree (DDPD): percentage of α-discriminatory rules that are no longer αdiscriminatory Direct discrimination protection preservation (DDPP): percentage of α-protective rules that remain α- protective IDPD and IDPP the same for redlining rules

24 German credit data set Min support 5%, min confidence 10% frequent classification rules background knowledge rules 37 redlining rules, 42 indirect and 991 direct discriminations

25 Information loss Misses cost (MC): percentage of lost rules Ghost cost (GC): percentage of introduced rules

26 Conclusions Considers frequent classification rule mining Defines direct and indirect discrimination Propose measures of discrimination Propose methods to modify dataset to avoid discrimination Meaningful qualitative results

Detecting Anomalous and Exceptional Behaviour on Credit Data by means of Association Rules. M. Delgado, M.D. Ruiz, M.J. Martin-Bautista, D.

Detecting Anomalous and Exceptional Behaviour on Credit Data by means of Association Rules. M. Delgado, M.D. Ruiz, M.J. Martin-Bautista, D. Detecting Anomalous and Exceptional Behaviour on Credit Data by means of Association Rules M. Delgado, M.D. Ruiz, M.J. Martin-Bautista, D. Sánchez 18th September 2013 Detecting Anom and Exc Behaviour on

More information

Correlation Preserving Unsupervised Discretization. Outline

Correlation Preserving Unsupervised Discretization. Outline Correlation Preserving Unsupervised Discretization Jee Vang Outline Paper References What is discretization? Motivation Principal Component Analysis (PCA) Association Mining Correlation Preserving Discretization

More information

Assignment 7 (Sol.) Introduction to Data Analytics Prof. Nandan Sudarsanam & Prof. B. Ravindran

Assignment 7 (Sol.) Introduction to Data Analytics Prof. Nandan Sudarsanam & Prof. B. Ravindran Assignment 7 (Sol.) Introduction to Data Analytics Prof. Nandan Sudarsanam & Prof. B. Ravindran 1. Let X, Y be two itemsets, and let denote the support of itemset X. Then the confidence of the rule X Y,

More information

CS4445 Data Mining and Knowledge Discovery in Databases. B Term 2014 Solutions Exam 2 - December 15, 2014

CS4445 Data Mining and Knowledge Discovery in Databases. B Term 2014 Solutions Exam 2 - December 15, 2014 CS4445 Data Mining and Knowledge Discovery in Databases. B Term 2014 Solutions Exam 2 - December 15, 2014 Prof. Carolina Ruiz Department of Computer Science Worcester Polytechnic Institute NAME: Prof.

More information

Cse537 Ar*fficial Intelligence Short Review 1 for Midterm 2. Professor Anita Wasilewska Computer Science Department Stony Brook University

Cse537 Ar*fficial Intelligence Short Review 1 for Midterm 2. Professor Anita Wasilewska Computer Science Department Stony Brook University Cse537 Ar*fficial Intelligence Short Review 1 for Midterm 2 Professor Anita Wasilewska Computer Science Department Stony Brook University Data Mining Process Ques*ons: Describe and discuss all stages of

More information

Association Analysis. Part 1

Association Analysis. Part 1 Association Analysis Part 1 1 Market-basket analysis DATA: A large set of items: e.g., products sold in a supermarket A large set of baskets: e.g., each basket represents what a customer bought in one

More information

Effective Elimination of Redundant Association Rules

Effective Elimination of Redundant Association Rules Effective Elimination of Redundant Association Rules James Cheng Yiping Ke Wilfred Ng Department of Computer Science and Engineering The Hong Kong University of Science and Technology Clear Water Bay,

More information

FUZZY ASSOCIATION RULES: A TWO-SIDED APPROACH

FUZZY ASSOCIATION RULES: A TWO-SIDED APPROACH FUZZY ASSOCIATION RULES: A TWO-SIDED APPROACH M. De Cock C. Cornelis E. E. Kerre Dept. of Applied Mathematics and Computer Science Ghent University, Krijgslaan 281 (S9), B-9000 Gent, Belgium phone: +32

More information

CSE-4412(M) Midterm. There are five major questions, each worth 10 points, for a total of 50 points. Points for each sub-question are as indicated.

CSE-4412(M) Midterm. There are five major questions, each worth 10 points, for a total of 50 points. Points for each sub-question are as indicated. 22 February 2007 CSE-4412(M) Midterm p. 1 of 12 CSE-4412(M) Midterm Sur / Last Name: Given / First Name: Student ID: Instructor: Parke Godfrey Exam Duration: 75 minutes Term: Winter 2007 Answer the following

More information

Data Mining. Dr. Raed Ibraheem Hamed. University of Human Development, College of Science and Technology Department of Computer Science

Data Mining. Dr. Raed Ibraheem Hamed. University of Human Development, College of Science and Technology Department of Computer Science Data Mining Dr. Raed Ibraheem Hamed University of Human Development, College of Science and Technology Department of Computer Science 2016 2017 Road map The Apriori algorithm Step 1: Mining all frequent

More information

Data Mining and Knowledge Discovery. Petra Kralj Novak. 2011/11/29

Data Mining and Knowledge Discovery. Petra Kralj Novak. 2011/11/29 Data Mining and Knowledge Discovery Petra Kralj Novak Petra.Kralj.Novak@ijs.si 2011/11/29 1 Practice plan 2011/11/08: Predictive data mining 1 Decision trees Evaluating classifiers 1: separate test set,

More information

Privacy-preserving Data Mining

Privacy-preserving Data Mining Privacy-preserving Data Mining What is [data] privacy? Privacy and Data Mining Privacy-preserving Data mining: main approaches Anonymization Obfuscation Cryptographic hiding Challenges Definition of privacy

More information

1 Frequent Pattern Mining

1 Frequent Pattern Mining Decision Support Systems MEIC - Alameda 2010/2011 Homework #5 Due date: 31.Oct.2011 1 Frequent Pattern Mining 1. The Apriori algorithm uses prior knowledge about subset support properties. In particular,

More information

Data Analytics Beyond OLAP. Prof. Yanlei Diao

Data Analytics Beyond OLAP. Prof. Yanlei Diao Data Analytics Beyond OLAP Prof. Yanlei Diao OPERATIONAL DBs DB 1 DB 2 DB 3 EXTRACT TRANSFORM LOAD (ETL) METADATA STORE DATA WAREHOUSE SUPPORTS OLAP DATA MINING INTERACTIVE DATA EXPLORATION Overview of

More information

arxiv: v1 [cs.db] 26 Oct 2016

arxiv: v1 [cs.db] 26 Oct 2016 Measuring airness in Ranked Outputs Ke Yang Drexel University ky323@drexel.edu Julia Stoyanovich Drexel University stoyanovich@drexel.edu arxiv:1610.08559v1 [cs.db] 26 Oct 2016 ABSTRACT Ranking and scoring

More information

732A61/TDDD41 Data Mining - Clustering and Association Analysis

732A61/TDDD41 Data Mining - Clustering and Association Analysis 732A61/TDDD41 Data Mining - Clustering and Association Analysis Lecture 6: Association Analysis I Jose M. Peña IDA, Linköping University, Sweden 1/14 Outline Content Association Rules Frequent Itemsets

More information

D B M G Data Base and Data Mining Group of Politecnico di Torino

D B M G Data Base and Data Mining Group of Politecnico di Torino Data Base and Data Mining Group of Politecnico di Torino Politecnico di Torino Association rules Objective extraction of frequent correlations or pattern from a transactional database Tickets at a supermarket

More information

Association Rules. Fundamentals

Association Rules. Fundamentals Politecnico di Torino Politecnico di Torino 1 Association rules Objective extraction of frequent correlations or pattern from a transactional database Tickets at a supermarket counter Association rule

More information

Data Mining of Medical Data: Opportunities and Challenges

Data Mining of Medical Data: Opportunities and Challenges 1 Data Mining of Medical Data: Opportunities and Challenges Dan A. Simovici IALS Cecilienhof Potsdam Brandemburg, Germany UMB 2 Data Mining Processes Mining Tabular Data AR and Nosocomial Infections Association

More information

D B M G. Association Rules. Fundamentals. Fundamentals. Elena Baralis, Silvia Chiusano. Politecnico di Torino 1. Definitions.

D B M G. Association Rules. Fundamentals. Fundamentals. Elena Baralis, Silvia Chiusano. Politecnico di Torino 1. Definitions. Definitions Data Base and Data Mining Group of Politecnico di Torino Politecnico di Torino Itemset is a set including one or more items Example: {Beer, Diapers} k-itemset is an itemset that contains k

More information

D B M G. Association Rules. Fundamentals. Fundamentals. Association rules. Association rule mining. Definitions. Rule quality metrics: example

D B M G. Association Rules. Fundamentals. Fundamentals. Association rules. Association rule mining. Definitions. Rule quality metrics: example Association rules Data Base and Data Mining Group of Politecnico di Torino Politecnico di Torino Objective extraction of frequent correlations or pattern from a transactional database Tickets at a supermarket

More information

Data Warehousing & Data Mining

Data Warehousing & Data Mining Data Warehousing & Data Mining Wolf-Tilo Balke Kinda El Maarry Institut für Informationssysteme Technische Universität Braunschweig http://www.ifis.cs.tu-bs.de 9. Business Intelligence 9. Business Intelligence

More information

Data Warehousing & Data Mining

Data Warehousing & Data Mining 9. Business Intelligence Data Warehousing & Data Mining Wolf-Tilo Balke Silviu Homoceanu Institut für Informationssysteme Technische Universität Braunschweig http://www.ifis.cs.tu-bs.de 9. Business Intelligence

More information

Privacy Preserving Frequent Itemset Mining. Workshop on Privacy, Security, and Data Mining ICDM - Maebashi City, Japan December 9, 2002

Privacy Preserving Frequent Itemset Mining. Workshop on Privacy, Security, and Data Mining ICDM - Maebashi City, Japan December 9, 2002 Privacy Preserving Frequent Itemset Mining Stanley R. M. Oliveira 1,2 Osmar R. Zaïane 2 1 oliveira@cs.ualberta.ca zaiane@cs.ualberta.ca Embrapa Information Technology Database Systems Laboratory Andre

More information

P, NP, NP-Complete, and NPhard

P, NP, NP-Complete, and NPhard P, NP, NP-Complete, and NPhard Problems Zhenjiang Li 21/09/2011 Outline Algorithm time complicity P and NP problems NP-Complete and NP-Hard problems Algorithm time complicity Outline What is this course

More information

Parts 3-6 are EXAMPLES for cse634

Parts 3-6 are EXAMPLES for cse634 1 Parts 3-6 are EXAMPLES for cse634 FINAL TEST CSE 352 ARTIFICIAL INTELLIGENCE Fall 2008 There are 6 pages in this exam. Please make sure you have all of them INTRODUCTION Philosophical AI Questions Q1.

More information

Data Mining Part 4. Prediction

Data Mining Part 4. Prediction Data Mining Part 4. Prediction 4.3. Fall 2009 Instructor: Dr. Masoud Yaghini Outline Introduction Bayes Theorem Naïve References Introduction Bayesian classifiers A statistical classifiers Introduction

More information

10/19/2017 MIST.6060 Business Intelligence and Data Mining 1. Association Rules

10/19/2017 MIST.6060 Business Intelligence and Data Mining 1. Association Rules 10/19/2017 MIST6060 Business Intelligence and Data Mining 1 Examples of Association Rules Association Rules Sixty percent of customers who buy sheets and pillowcases order a comforter next, followed by

More information

Association Analysis. Part 2

Association Analysis. Part 2 Association Analysis Part 2 1 Limitations of the Support/Confidence framework 1 Redundancy: many of the returned patterns may refer to the same piece of information 2 Difficult control of output size:

More information

Lecture 2. Judging the Performance of Classifiers. Nitin R. Patel

Lecture 2. Judging the Performance of Classifiers. Nitin R. Patel Lecture 2 Judging the Performance of Classifiers Nitin R. Patel 1 In this note we will examine the question of how to udge the usefulness of a classifier and how to compare different classifiers. Not only

More information

CHAPTER 7 FUNCTIONS. Alessandro Artale UniBZ - artale/

CHAPTER 7 FUNCTIONS. Alessandro Artale UniBZ -   artale/ CHAPTER 7 FUNCTIONS Alessandro Artale UniBZ - http://www.inf.unibz.it/ artale/ SECTION 7.1 Functions Defined on General Sets Copyright Cengage Learning. All rights reserved. Functions Defined on General

More information

arxiv: v1 [cs.lg] 22 Nov 2016

arxiv: v1 [cs.lg] 22 Nov 2016 A Causal Framework for Discovering and Removing Direct and Indirect Discrimination Lu Zhang, Yongkai Wu, and Xintao Wu University of Arkansas {lz006,yw009,xintaowu}@uark.edu arxiv:1611.07509v1 [cs.lg]

More information

Data preprocessing. DataBase and Data Mining Group 1. Data set types. Tabular Data. Document Data. Transaction Data. Ordered Data

Data preprocessing. DataBase and Data Mining Group 1. Data set types. Tabular Data. Document Data. Transaction Data. Ordered Data Elena Baralis and Tania Cerquitelli Politecnico di Torino Data set types Record Tables Document Data Transaction Data Graph World Wide Web Molecular Structures Ordered Spatial Data Temporal Data Sequential

More information

Review of Lecture 1. Across records. Within records. Classification, Clustering, Outlier detection. Associations

Review of Lecture 1. Across records. Within records. Classification, Clustering, Outlier detection. Associations Review of Lecture 1 This course is about finding novel actionable patterns in data. We can divide data mining algorithms (and the patterns they find) into five groups Across records Classification, Clustering,

More information

Data Mining: Data. Lecture Notes for Chapter 2. Introduction to Data Mining

Data Mining: Data. Lecture Notes for Chapter 2. Introduction to Data Mining Data Mining: Data Lecture Notes for Chapter 2 Introduction to Data Mining by Tan, Steinbach, Kumar 1 Types of data sets Record Tables Document Data Transaction Data Graph World Wide Web Molecular Structures

More information

Algorithms for Classification: The Basic Methods

Algorithms for Classification: The Basic Methods Algorithms for Classification: The Basic Methods Outline Simplicity first: 1R Naïve Bayes 2 Classification Task: Given a set of pre-classified examples, build a model or classifier to classify new cases.

More information

Testing for Discrimination

Testing for Discrimination Testing for Discrimination Spring 2010 Alicia Rosburg (ISU) Testing for Discrimination Spring 2010 1 / 40 Relevant Readings BFW Appendix 7A (pgs 250-255) Alicia Rosburg (ISU) Testing for Discrimination

More information

Data Mining: Concepts and Techniques. (3 rd ed.) Chapter 6

Data Mining: Concepts and Techniques. (3 rd ed.) Chapter 6 Data Mining: Concepts and Techniques (3 rd ed.) Chapter 6 Jiawei Han, Micheline Kamber, and Jian Pei University of Illinois at Urbana-Champaign & Simon Fraser University 2013 Han, Kamber & Pei. All rights

More information

ECLT 5810 Data Preprocessing. Prof. Wai Lam

ECLT 5810 Data Preprocessing. Prof. Wai Lam ECLT 5810 Data Preprocessing Prof. Wai Lam Why Data Preprocessing? Data in the real world is imperfect incomplete: lacking attribute values, lacking certain attributes of interest, or containing only aggregate

More information

EECS 349:Machine Learning Bryan Pardo

EECS 349:Machine Learning Bryan Pardo EECS 349:Machine Learning Bryan Pardo Topic 2: Decision Trees (Includes content provided by: Russel & Norvig, D. Downie, P. Domingos) 1 General Learning Task There is a set of possible examples Each example

More information

Rough Set Model Selection for Practical Decision Making

Rough Set Model Selection for Practical Decision Making Rough Set Model Selection for Practical Decision Making Joseph P. Herbert JingTao Yao Department of Computer Science University of Regina Regina, Saskatchewan, Canada, S4S 0A2 {herbertj, jtyao}@cs.uregina.ca

More information

Unit 1A: Computational Complexity

Unit 1A: Computational Complexity Unit 1A: Computational Complexity Course contents: Computational complexity NP-completeness Algorithmic Paradigms Readings Chapters 3, 4, and 5 Unit 1A 1 O: Upper Bounding Function Def: f(n)= O(g(n)) if

More information

15 Introduction to Data Mining

15 Introduction to Data Mining 15 Introduction to Data Mining 15.1 Introduction to principle methods 15.2 Mining association rule see also: A. Kemper, Chap. 17.4, Kifer et al.: chap 17.7 ff 15.1 Introduction "Discovery of useful, possibly

More information

Lars Schmidt-Thieme, Information Systems and Machine Learning Lab (ISMLL), University of Hildesheim, Germany

Lars Schmidt-Thieme, Information Systems and Machine Learning Lab (ISMLL), University of Hildesheim, Germany Syllabus Fri. 21.10. (1) 0. Introduction A. Supervised Learning: Linear Models & Fundamentals Fri. 27.10. (2) A.1 Linear Regression Fri. 3.11. (3) A.2 Linear Classification Fri. 10.11. (4) A.3 Regularization

More information

COMP9444: Neural Networks. Vapnik Chervonenkis Dimension, PAC Learning and Structural Risk Minimization

COMP9444: Neural Networks. Vapnik Chervonenkis Dimension, PAC Learning and Structural Risk Minimization : Neural Networks Vapnik Chervonenkis Dimension, PAC Learning and Structural Risk Minimization 11s2 VC-dimension and PAC-learning 1 How good a classifier does a learner produce? Training error is the precentage

More information

Statistical Privacy For Privacy Preserving Information Sharing

Statistical Privacy For Privacy Preserving Information Sharing Statistical Privacy For Privacy Preserving Information Sharing Johannes Gehrke Cornell University http://www.cs.cornell.edu/johannes Joint work with: Alexandre Evfimievski, Ramakrishnan Srikant, Rakesh

More information

1 [15 points] Frequent Itemsets Generation With Map-Reduce

1 [15 points] Frequent Itemsets Generation With Map-Reduce Data Mining Learning from Large Data Sets Final Exam Date: 15 August 2013 Time limit: 120 minutes Number of pages: 11 Maximum score: 100 points You can use the back of the pages if you run out of space.

More information

STAT Section 2.1: Basic Inference. Basic Definitions

STAT Section 2.1: Basic Inference. Basic Definitions STAT 518 --- Section 2.1: Basic Inference Basic Definitions Population: The collection of all the individuals of interest. This collection may be or even. Sample: A collection of elements of the population.

More information

Data Mining Project. C4.5 Algorithm. Saber Salah. Naji Sami Abduljalil Abdulhak

Data Mining Project. C4.5 Algorithm. Saber Salah. Naji Sami Abduljalil Abdulhak Data Mining Project C4.5 Algorithm Saber Salah Naji Sami Abduljalil Abdulhak Decembre 9, 2010 1.0 Introduction Before start talking about C4.5 algorithm let s see first what is machine learning? Human

More information

Università di Pisa A.A Data Mining II June 13th, < {A} {B,F} {E} {A,B} {A,C,D} {F} {B,E} {C,D} > t=0 t=1 t=2 t=3 t=4 t=5 t=6 t=7

Università di Pisa A.A Data Mining II June 13th, < {A} {B,F} {E} {A,B} {A,C,D} {F} {B,E} {C,D} > t=0 t=1 t=2 t=3 t=4 t=5 t=6 t=7 Università di Pisa A.A. 2016-2017 Data Mining II June 13th, 2017 Exercise 1 - Sequential patterns (6 points) a) (3 points) Given the following input sequence < {A} {B,F} {E} {A,B} {A,C,D} {F} {B,E} {C,D}

More information

The Beauty and Joy of Computing

The Beauty and Joy of Computing The Beauty and Joy of Computing Lecture #23 Limits of Computing UC Berkeley EECS Sr Lecturer SOE Dan You ll have the opportunity for extra credit on your project! After you submit it, you can make a 5min

More information

Meelis Kull Autumn Meelis Kull - Autumn MTAT Data Mining - Lecture 05

Meelis Kull Autumn Meelis Kull - Autumn MTAT Data Mining - Lecture 05 Meelis Kull meelis.kull@ut.ee Autumn 2017 1 Sample vs population Example task with red and black cards Statistical terminology Permutation test and hypergeometric test Histogram on a sample vs population

More information

Chapter 4.5 Association Rules. CSCI 347, Data Mining

Chapter 4.5 Association Rules. CSCI 347, Data Mining Chapter 4.5 Association Rules CSCI 347, Data Mining Mining Association Rules Can be highly computationally complex One method: Determine item sets Build rules from those item sets Vocabulary from before

More information

Algorithms and Complexity Theory. Chapter 8: Introduction to Complexity. Computer Science - Durban - September 2005

Algorithms and Complexity Theory. Chapter 8: Introduction to Complexity. Computer Science - Durban - September 2005 Algorithms and Complexity Theory Chapter 8: Introduction to Complexity Jules-R Tapamo Computer Science - Durban - September 2005 Contents 1 Introduction 2 1.1 Dynamic programming...................................

More information

Unsupervised Data Discretization of Mixed Data Types

Unsupervised Data Discretization of Mixed Data Types Unsupervised Data Discretization of Mixed Data Types Jee Vang Outline Introduction Background Objective Experimental Design Results Future Work 1 Introduction Many algorithms in data mining, machine learning,

More information

Approximate counting: count-min data structure. Problem definition

Approximate counting: count-min data structure. Problem definition Approximate counting: count-min data structure G. Cormode and S. Muthukrishhan: An improved data stream summary: the count-min sketch and its applications. Journal of Algorithms 55 (2005) 58-75. Problem

More information

Mining Class-Dependent Rules Using the Concept of Generalization/Specialization Hierarchies

Mining Class-Dependent Rules Using the Concept of Generalization/Specialization Hierarchies Mining Class-Dependent Rules Using the Concept of Generalization/Specialization Hierarchies Juliano Brito da Justa Neves 1 Marina Teresa Pires Vieira {juliano,marina}@dc.ufscar.br Computer Science Department

More information

Data Structures and Algorithms

Data Structures and Algorithms Data Structures and Algorithms Spring 2017-2018 Outline 1 Sorting Algorithms (contd.) Outline Sorting Algorithms (contd.) 1 Sorting Algorithms (contd.) Analysis of Quicksort Time to sort array of length

More information

A Clear View on Quality Measures for Fuzzy Association Rules

A Clear View on Quality Measures for Fuzzy Association Rules A Clear View on Quality Measures for Fuzzy Association Rules Martine De Cock, Chris Cornelis, and Etienne E. Kerre Fuzziness and Uncertainty Modelling Research Unit Department of Applied Mathematics and

More information

Standardising the Lift of an Association Rule

Standardising the Lift of an Association Rule Standardising the Lift of an Association Rule P.D. McNicholas a,1,, T.B. Murphy a,1, M. O Regan a a Department of Statistics, Trinity College Dublin, Ireland. Abstract The lift of an association rule is

More information

Why Spatial Data Mining?

Why Spatial Data Mining? Intelligent Data Analysis for Spatial Data Mining Applications Wei Ding Knowledge Discovery Lab Department of Computer Science University of Massachusetts Boston Why Spatial Data Mining? Spatial Data mining

More information

Data classification (II)

Data classification (II) Lecture 4: Data classification (II) Data Mining - Lecture 4 (2016) 1 Outline Decision trees Choice of the splitting attribute ID3 C4.5 Classification rules Covering algorithms Naïve Bayes Classification

More information

CSE 5243 INTRO. TO DATA MINING

CSE 5243 INTRO. TO DATA MINING CSE 5243 INTRO. TO DATA MINING Data & Data Preprocessing & Classification (Basic Concepts) Huan Sun, CSE@The Ohio State University Slides adapted from UIUC CS412, Fall 2017, by Prof. Jiawei Han Chapter

More information

Decision trees for stream data mining new results

Decision trees for stream data mining new results Decision trees for stream data mining new results Leszek Rutkowski leszek.rutkowski@iisi.pcz.pl Lena Pietruczuk lena.pietruczuk@iisi.pcz.pl Maciej Jaworski maciej.jaworski@iisi.pcz.pl Piotr Duda piotr.duda@iisi.pcz.pl

More information

Data Mining and Matrices

Data Mining and Matrices Data Mining and Matrices 08 Boolean Matrix Factorization Rainer Gemulla, Pauli Miettinen June 13, 2013 Outline 1 Warm-Up 2 What is BMF 3 BMF vs. other three-letter abbreviations 4 Binary matrices, tiles,

More information

CS5112: Algorithms and Data Structures for Applications

CS5112: Algorithms and Data Structures for Applications CS5112: Algorithms and Data Structures for Applications Lecture 19: Association rules Ramin Zabih Some content from: Wikipedia/Google image search; Harrington; J. Leskovec, A. Rajaraman, J. Ullman: Mining

More information

Machine Learning (CS 567) Lecture 2

Machine Learning (CS 567) Lecture 2 Machine Learning (CS 567) Lecture 2 Time: T-Th 5:00pm - 6:20pm Location: GFS118 Instructor: Sofus A. Macskassy (macskass@usc.edu) Office: SAL 216 Office hours: by appointment Teaching assistant: Cheol

More information

CS4445 B10 Homework 4 Part I Solution

CS4445 B10 Homework 4 Part I Solution CS4445 B10 Homework 4 Part I Solution Yutao Wang Consider the zoo.arff dataset converted to arff from the Zoo Data Set available at Univ. of California Irvine KDD Data Repository. 1. Load this dataset

More information

Cse352 AI Homework 2 Solutions

Cse352 AI Homework 2 Solutions 1 Cse352 AI Homework 2 Solutions PART ONE Classification: Characteristic and Discriminant Rules Here are some DEFINITIONS from the Lecture Notes that YOU NEED for your Homework Definition 1 Given a classification

More information

A Tiered Screen Protocol for the Discovery of Structurally Diverse HIV Integrase Inhibitors

A Tiered Screen Protocol for the Discovery of Structurally Diverse HIV Integrase Inhibitors A Tiered Screen Protocol for the Discovery of Structurally Diverse HIV Integrase Inhibitors Rajarshi Guha, Debojyoti Dutta, Ting Chen and David J. Wild School of Informatics Indiana University and Dept.

More information

Multiprocessor Scheduling I: Partitioned Scheduling. LS 12, TU Dortmund

Multiprocessor Scheduling I: Partitioned Scheduling. LS 12, TU Dortmund Multiprocessor Scheduling I: Partitioned Scheduling Prof. Dr. Jian-Jia Chen LS 12, TU Dortmund 22/23, June, 2015 Prof. Dr. Jian-Jia Chen (LS 12, TU Dortmund) 1 / 47 Outline Introduction to Multiprocessor

More information

Data Warehousing. Wolf-Tilo Balke Silviu Homoceanu Institut für Informationssysteme Technische Universität Braunschweig

Data Warehousing. Wolf-Tilo Balke Silviu Homoceanu Institut für Informationssysteme Technische Universität Braunschweig Data Warehousing & Data Mining Wolf-Tilo Balke Silviu Homoceanu Institut für Informationssysteme Technische Universität Braunschweig http://www.ifis.cs.tu-bs.de Summary How to build a DW The DW Project:

More information

Machine Learning: Pattern Mining

Machine Learning: Pattern Mining Machine Learning: Pattern Mining Information Systems and Machine Learning Lab (ISMLL) University of Hildesheim Wintersemester 2007 / 2008 Pattern Mining Overview Itemsets Task Naive Algorithm Apriori Algorithm

More information

Chapter 6. Frequent Pattern Mining: Concepts and Apriori. Meng Jiang CSE 40647/60647 Data Science Fall 2017 Introduction to Data Mining

Chapter 6. Frequent Pattern Mining: Concepts and Apriori. Meng Jiang CSE 40647/60647 Data Science Fall 2017 Introduction to Data Mining Chapter 6. Frequent Pattern Mining: Concepts and Apriori Meng Jiang CSE 40647/60647 Data Science Fall 2017 Introduction to Data Mining Pattern Discovery: Definition What are patterns? Patterns: A set of

More information

Decision Tree Learning Mitchell, Chapter 3. CptS 570 Machine Learning School of EECS Washington State University

Decision Tree Learning Mitchell, Chapter 3. CptS 570 Machine Learning School of EECS Washington State University Decision Tree Learning Mitchell, Chapter 3 CptS 570 Machine Learning School of EECS Washington State University Outline Decision tree representation ID3 learning algorithm Entropy and information gain

More information

Summary. 8.1 BI Overview. 8. Business Intelligence. 8.1 BI Overview. 8.1 BI Overview 12/17/ Business Intelligence

Summary. 8.1 BI Overview. 8. Business Intelligence. 8.1 BI Overview. 8.1 BI Overview 12/17/ Business Intelligence Summary Data Warehousing & Data Mining Wolf-Tilo Balke Silviu Homoceanu Institut für Informationssysteme Technische Universität Braunschweig http://www.ifis.cs.tu-bs.de How to build a DW The DW Project:

More information

Variables, distributions, and samples (cont.) Phil 12: Logic and Decision Making Fall 2010 UC San Diego 10/18/2010

Variables, distributions, and samples (cont.) Phil 12: Logic and Decision Making Fall 2010 UC San Diego 10/18/2010 Variables, distributions, and samples (cont.) Phil 12: Logic and Decision Making Fall 2010 UC San Diego 10/18/2010 Review Recording observations - Must extract that which is to be analyzed: coding systems,

More information

Data Mining. Chapter 1. What s it all about?

Data Mining. Chapter 1. What s it all about? Data Mining Chapter 1. What s it all about? 1 DM & ML Ubiquitous computing environment Excessive amount of data (data flooding) Gap between the generation of data and their understanding Looking for structural

More information

Machine Learning & Data Mining

Machine Learning & Data Mining Group M L D Machine Learning M & Data Mining Chapter 7 Decision Trees Xin-Shun Xu @ SDU School of Computer Science and Technology, Shandong University Top 10 Algorithm in DM #1: C4.5 #2: K-Means #3: SVM

More information

MN 400: Research Methods. CHAPTER 7 Sample Design

MN 400: Research Methods. CHAPTER 7 Sample Design MN 400: Research Methods CHAPTER 7 Sample Design 1 Some fundamental terminology Population the entire group of objects about which information is wanted Unit, object any individual member of the population

More information

The Beauty and Joy of Computing

The Beauty and Joy of Computing The Beauty and Joy of Computing Lecture #23 Limits of Computing UC Berkeley EECS Sr Lecturer SOE Dan Researchers at CMU have built a system which searches the Web for images constantly and tries to decide

More information

Report on Differential Privacy

Report on Differential Privacy Report on Differential Privacy Lembit Valgma Supervised by Vesal Vojdani December 19, 2017 1 Introduction Over the past decade the collection and analysis of personal data has increased a lot. This has

More information

Real-Time Course. Transaction based temporal model for Real-time databases

Real-Time Course. Transaction based temporal model for Real-time databases Real-Time Course Transaction based temporal model for Real-time databases 1 Real-time data Data used in classical administration system bank account -> represent status of constant real-world Data used

More information

CSE 5243 INTRO. TO DATA MINING

CSE 5243 INTRO. TO DATA MINING CSE 5243 INTRO. TO DATA MINING Mining Frequent Patterns and Associations: Basic Concepts (Chapter 6) Huan Sun, CSE@The Ohio State University Slides adapted from Prof. Jiawei Han @UIUC, Prof. Srinivasan

More information

Midterm: CS 6375 Spring 2015 Solutions

Midterm: CS 6375 Spring 2015 Solutions Midterm: CS 6375 Spring 2015 Solutions The exam is closed book. You are allowed a one-page cheat sheet. Answer the questions in the spaces provided on the question sheets. If you run out of room for an

More information

Mining Molecular Fragments: Finding Relevant Substructures of Molecules

Mining Molecular Fragments: Finding Relevant Substructures of Molecules Mining Molecular Fragments: Finding Relevant Substructures of Molecules Christian Borgelt, Michael R. Berthold Proc. IEEE International Conference on Data Mining, 2002. ICDM 2002. Lecturers: Carlo Cagli

More information

Adaptive Learning and Mining for Data Streams and Frequent Patterns

Adaptive Learning and Mining for Data Streams and Frequent Patterns Adaptive Learning and Mining for Data Streams and Frequent Patterns Albert Bifet Laboratory for Relational Algorithmics, Complexity and Learning LARCA Departament de Llenguatges i Sistemes Informàtics

More information

Possibilities of third parties in real estate management in the light of the INSPIRE Directive

Possibilities of third parties in real estate management in the light of the INSPIRE Directive Possibilities of third parties in real estate management in the light of the INSPIRE Directive Faculty of Mining Surveying and Environmental Engineering Department of Geomatics Barcelona, Spain, 29 September

More information

Supervised Learning! Algorithm Implementations! Inferring Rudimentary Rules and Decision Trees!

Supervised Learning! Algorithm Implementations! Inferring Rudimentary Rules and Decision Trees! Supervised Learning! Algorithm Implementations! Inferring Rudimentary Rules and Decision Trees! Summary! Input Knowledge representation! Preparing data for learning! Input: Concept, Instances, Attributes"

More information

CS145: INTRODUCTION TO DATA MINING

CS145: INTRODUCTION TO DATA MINING CS145: INTRODUCTION TO DATA MINING 4: Vector Data: Decision Tree Instructor: Yizhou Sun yzsun@cs.ucla.edu October 10, 2017 Methods to Learn Vector Data Set Data Sequence Data Text Data Classification Clustering

More information

Qualifying Exam in Machine Learning

Qualifying Exam in Machine Learning Qualifying Exam in Machine Learning October 20, 2009 Instructions: Answer two out of the three questions in Part 1. In addition, answer two out of three questions in two additional parts (choose two parts

More information

Key words. free Boolean algebra, measure, Bonferroni-type inquality, exclusion-inclusion, missing

Key words. free Boolean algebra, measure, Bonferroni-type inquality, exclusion-inclusion, missing AN INCLUSION-EXCLUSION RESULT FOR BOOLEAN POLYNOMIALS AND ITS APPLICATIONS IN DATA MINING SZYMON JAROSZEWICZ, DAN A. SIMOVICI, AND IVO ROSENBERG Abstract. We characterize measures on free Boolean algebras

More information

Distributed Consensus

Distributed Consensus Distributed Consensus Reaching agreement is a fundamental problem in distributed computing. Some examples are Leader election / Mutual Exclusion Commit or Abort in distributed transactions Reaching agreement

More information

Mining Positive and Negative Fuzzy Association Rules

Mining Positive and Negative Fuzzy Association Rules Mining Positive and Negative Fuzzy Association Rules Peng Yan 1, Guoqing Chen 1, Chris Cornelis 2, Martine De Cock 2, and Etienne Kerre 2 1 School of Economics and Management, Tsinghua University, Beijing

More information

THE IMPACT ON SCALING ON THE PAIR-WISE COMPARISON OF THE ANALYTIC HIERARCHY PROCESS

THE IMPACT ON SCALING ON THE PAIR-WISE COMPARISON OF THE ANALYTIC HIERARCHY PROCESS ISAHP 200, Berne, Switzerland, August 2-4, 200 THE IMPACT ON SCALING ON THE PAIR-WISE COMPARISON OF THE ANALYTIC HIERARCHY PROCESS Yuji Sato Department of Policy Science, Matsusaka University 846, Kubo,

More information

Anomaly Detection for the CERN Large Hadron Collider injection magnets

Anomaly Detection for the CERN Large Hadron Collider injection magnets Anomaly Detection for the CERN Large Hadron Collider injection magnets Armin Halilovic KU Leuven - Department of Computer Science In cooperation with CERN 2018-07-27 0 Outline 1 Context 2 Data 3 Preprocessing

More information

Mining Infrequent Patter ns

Mining Infrequent Patter ns Mining Infrequent Patter ns JOHAN BJARNLE (JOHBJ551) PETER ZHU (PETZH912) LINKÖPING UNIVERSITY, 2009 TNM033 DATA MINING Contents 1 Introduction... 2 2 Techniques... 3 2.1 Negative Patterns... 3 2.2 Negative

More information

Decision Trees. CS57300 Data Mining Fall Instructor: Bruno Ribeiro

Decision Trees. CS57300 Data Mining Fall Instructor: Bruno Ribeiro Decision Trees CS57300 Data Mining Fall 2016 Instructor: Bruno Ribeiro Goal } Classification without Models Well, partially without a model } Today: Decision Trees 2015 Bruno Ribeiro 2 3 Why Trees? } interpretable/intuitive,

More information

Be able to define the following terms and answer basic questions about them:

Be able to define the following terms and answer basic questions about them: CS440/ECE448 Section Q Fall 2017 Final Review Be able to define the following terms and answer basic questions about them: Probability o Random variables, axioms of probability o Joint, marginal, conditional

More information

Test and Evaluation of an Electronic Database Selection Expert System

Test and Evaluation of an Electronic Database Selection Expert System 282 Test and Evaluation of an Electronic Database Selection Expert System Introduction As the number of electronic bibliographic databases available continues to increase, library users are confronted

More information