Factor Models for Gender Prediction Based on E-commerce Data

Similar documents

Classifying Large Data Sets Using SVMs with Hierarchical Clusters. Presented by :Limou Wang

Introduction to Data Mining

Role of Social Networking in Marketing using Data Mining

International Journal of Computer Science Trends and Technology (IJCST) Volume 3 Issue 3, May-June 2015

MACHINE LEARNING IN HIGH ENERGY PHYSICS

Data Mining Techniques in CRM

A Basic Guide to Modeling Techniques for All Direct Marketing Challenges

Practical Applications of DATA MINING. Sang C Suh Texas A&M University Commerce JONES & BARTLETT LEARNING

1. Overall, how satisfied are you working for The Company? Extremely Dissatisfied. Very Dissatisfied. Somewhat Dissatisfied.

Data Mining. Dr. Saed Sayad. University of Toronto

Enrollment Data Undergraduate Programs by Race/ethnicity and Gender (Fall 2008) Summary Data Undergraduate Programs by Race/ethnicity

The Data Mining Process

MS1b Statistical Data Mining

Blood Type Probability O 0.42 A 0.43 B 0.11 AB 0.04

Part 2: Community Detection

Predict Influencers in the Social Network

Principles of Dat Da a t Mining Pham Tho Hoan hoanpt@hnue.edu.v hoanpt@hnue.edu. n

Data Mining is the process of knowledge discovery involving finding

Web 3.0 image search: a World First

EMPIRICAL RISK MINIMIZATION FOR CAR INSURANCE DATA

KPIs and Scorecards using OBIEE 11g Mark Rittman, Rittman Mead Consulting Collaborate 11, Orlando, Florida, April 2011

Data Mining Analytics for Business Intelligence and Decision Support

The Economist/YouGov Poll

Clustering. Data Mining. Abraham Otero. Data Mining. Agenda

WHAT IS A SITE MAP. Types of Site Maps. vertical. horizontal. A site map (or sitemap) is a

Protein Protein Interaction Networks

Performance Analysis of Naive Bayes and J48 Classification Algorithm for Data Classification

Clustering. Danilo Croce Web Mining & Retrieval a.a. 2015/201 16/03/2016

CSci 538 Articial Intelligence (Machine Learning and Data Analysis)

COPYRIGHTED MATERIAL. Contents. List of Figures. Acknowledgments

Class 10. Data Mining and Artificial Intelligence. Data Mining. We are in the 21 st century So where are the robots?

Analytics on Big Data

WebFOCUS RStat. RStat. Predict the Future and Make Effective Decisions Today. WebFOCUS RStat

Support Vector Machines with Clustering for Training with Very Large Datasets

BIG DATA What it is and how to use?

Active Learning SVM for Blogs recommendation

TURKISH ORACLE USER GROUP

Data Mining + Business Intelligence. Integration, Design and Implementation

Factorization Machines

Machine Learning Logistic Regression

Data Preprocessing. Week 2

CSCI567 Machine Learning (Fall 2014)

Predicting borrowers chance of defaulting on credit loans

Data Mining Part 5. Prediction

SPECIAL PERTURBATIONS UNCORRELATED TRACK PROCESSING

Neural Network Add-in

Data Mining: An Overview. David Madigan

Review of Modern Techniques of Qualitative Data Clustering

Data Warehousing und Data Mining

Enhanced Boosted Trees Technique for Customer Churn Prediction Model

Artificial Neural Networks and Support Vector Machines. CS 486/686: Introduction to Artificial Intelligence

ARTIFICIAL INTELLIGENCE (CSCU9YE) LECTURE 6: MACHINE LEARNING 2: UNSUPERVISED LEARNING (CLUSTERING)

The Predictive Data Mining Revolution in Scorecards:

Lavastorm Analytic Library Predictive and Statistical Analytics Node Pack FAQs

Finding Frequent Patterns Based On Quantitative Binary Attributes Using FP-Growth Algorithm

Bayesian Factorization Machines

Chapter 6. The stacking ensemble approach

Joseph Twagilimana, University of Louisville, Louisville, KY

Best Practices in Data Visualizations. Vihao Pham January 29, 2014

Best Practices in Data Visualizations. Vihao Pham 2014

An Introduction to Data Mining

Anomaly Detection and Predictive Maintenance

CSC 411: Lecture 07: Multiclass Classification

Question 2 Naïve Bayes (16 points)

Bing Liu. Web Data Mining. Exploring Hyperlinks, Contents, and Usage Data. With 177 Figures. ~ Spring~r

Automatic Network Protocol Analysis

Social Media Mining. Data Mining Essentials

Sanjeev Kumar. contribute

DATA MINING CLUSTER ANALYSIS: BASIC CONCEPTS

Classification of Bad Accounts in Credit Card Industry

A Survey on Pre-processing and Post-processing Techniques in Data Mining

DTREG. Predictive Modeling Software. Phillip H. Sherrod. Copyright All rights reserved.

Adaptive Anomaly Detection for Network Security

Online Ensembles for Financial Trading

CS 2750 Machine Learning. Lecture 1. Machine Learning. CS 2750 Machine Learning.

SOLiD System accuracy with the Exact Call Chemistry module

Public Information for ACBSP Accredited Programs at Florida State College at Jacksonville

EXTENDED CENTROID BASED CLUSTERING TECHNIQUE FOR ONLINE SHOPPING FRAUD DETECTION

Neural Networks Lesson 5 - Cluster Analysis

Heritage Provider Network Health Prize Round 3 Milestone: Team crescendo s Solution

Appendix K: Responses to Selected Survey Results by Gender

Qn: # Mark Score Total 100

KATE GLEASON COLLEGE OF ENGINEERING. John D. Hromi Center for Quality and Applied Statistics

5. Correlation. Open HeightWeight.sav. Take a moment to review the data file.

The Forgotten JMP Visualizations (Plus Some New Views in JMP 9) Sam Gardner, SAS Institute, Lafayette, IN, USA

Big Data and Marketing

A New Approach for Evaluation of Data Mining Techniques

ANALYTICS CENTER LEARNING PROGRAM

Multivariate Analysis of Variance. The general purpose of multivariate analysis of variance (MANOVA) is to determine

Transcription:

Factor Models for Gender Prediction Based on E-commerce Data Data Mining Competition PAKDD 2015, HoChiMinh City, Vietnam

Outline Hierarchical Basket Model Modeling Autocorrelation Sequential Block Voting Results & Implementation

Outline Hierarchical Basket Model Tree Encoding Factorization Machine Modeling Autocorrelation Sequential Block Voting Results & Implementation

Product Hierarchy u1, 2014-11-13, 2014-11-14, A01/B01/C01/D01/ u2, 2014-11-14, 2014-11-15, A02/B02/C02/D02/;A02/B02/C03/D03/; u3, 2014-11-14, 2014-11-16, A01/B01/C01/D02/;A01/B04/C05/D98/; A01 B01 B04 C01 C02 C05 D01 D02 D06 D22 D45 D98 D21 D89 D15

Path Encoding u3, 2014-11-14, 2014-11-16, A01/B01/C01/D02/;A01/B04/C05/D98/; A01 B01 B04 C01 C02 C05 D01 D02 D06 D22 D45 D98 D21 D89 D15 x i = {2, 0,, 1, 0, 0, 1, 0, 1,, 1, 0, } } {{ } } {{ } } {{ } A B D

Factorization Machine FM model of order d = 2 ŷ FM (x) := w 0 + w j x j + x j x j v j, v j j=1 j=1 j =j+1 w 0 R, w R p, V R p k are the model parameters k N is the size/ dimensionality of the latent space the model has one feature vector v i for each variable x i [Rendle, TIST 2012]

Factorization Machine FM model of order d = 2 ŷ FM (x) := w 0 + w j x j + x j x j v j, v j j=1 j=1 j =j+1 w 0 R, w R p, V R p k are the model parameters k N is the size/ dimensionality of the latent space the model has one feature vector v i for each variable x i [Rendle, TIST 2012]

Factorization Machine FM model of order d = 2 ŷ FM (x) := w 0 + w j x j + x j x j v j, v j j=1 j=1 j =j+1 w 0 R, w R p, V R p k are the model parameters k N is the size/ dimensionality of the latent space the model has one feature vector v i for each variable x i [Rendle, TIST 2012]

Factorization Machine FM model of order d = 2 ŷ FM (x) := w 0 + w j x j + x j x j v j, v j j=1 j=1 j =j+1 w 0 R, w R p, V R p k are the model parameters k N is the size/ dimensionality of the latent space the model has one feature vector v i for each variable x i [Rendle, TIST 2012]

Linear Part a FM model of order d = 2 ŷ FM (x) := w 0 + w j x j + j=1 x j x j v j, v j j=1 j =j+1 A02 x i = (0, 1,, 0, 0,, 1,, 0, 0,, 1,, 0) } {{ } } {{ } } {{ } A B D B11 D55 p(female x i ) p(female A02) + p(female B11) + p(female D55)

Linear Part a FM model of order d = 2 ŷ FM (x) := w 0 + w j x j + j=1 x j x j v j, v j j=1 j =j+1 A02 x i = (0, 1,, 0, 0,, 1,, 0, 0,, 1,, 0) } {{ } } {{ } } {{ } A B D B11 D55 p(female x i ) p(female A02) + p(female B11) + p(female D55)

Linear Part a FM model of order d = 2 ŷ FM (x) := w 0 + w j x j + j=1 x j x j v j, v j j=1 j =j+1 A02 x i = (0, 1,, 0, 0,, 1,, 0, 0,, 1,, 0) } {{ } } {{ } } {{ } A B D B11 D55 p(female x i ) p(female A02) + p(female B11) + p(female D55)

Pairwise Interactions a FM model of order d = 2 ŷ FM (x) := w 0 + A02 w j x j + j=1 B11 j=1 j =j+1 x j x j v j, v j x i = (0, 1,, 0, 0,, 1,, 0, 0,, 1,, 1,, 0) } {{ } } {{ } } {{ } A B D Example: V =, Summer } Swimming {{ } j=d55,, Summer D55 } Swimming {{ } j =D95 D95,, V R p k

Pairwise Interactions a FM model of order d = 2 ŷ FM (x) := w 0 + A02 w j x j + j=1 B11 j=1 j =j+1 x j x j v j, v j x i = (0, 1,, 0, 0,, 1,, 0, 0,, 1,, 1,, 0) } {{ } } {{ } } {{ } A B D Example: V =, Summer } Swimming {{ } j=d55,, Summer D55 } Swimming {{ } j =D95 D95,, V R p k

Pairwise Interactions a FM model of order d = 2 ŷ FM (x) := w 0 + A02 w j x j + j=1 B11 j=1 j =j+1 x j x j v j, v j x i = (0, 1,, 0, 0,, 1,, 0, 0,, 1,, 1,, 0) } {{ } } {{ } } {{ } A B D Example: V =, Summer } Swimming {{ } j=d55,, Summer D55 } Swimming {{ } j =D95 D95,, V R p k

Pairwise Interactions a FM model of order d = 2 ŷ FM (x) := w 0 + A02 w j x j + j=1 B11 j=1 j =j+1 x j x j v j, v j x i = (0, 1,, 0, 0,, 1,, 0, 0,, 1,, 1,, 0) } {{ } } {{ } } {{ } A B D Example: V =, Summer } Swimming {{ } j=d55,, Summer D55 } Swimming {{ } j =D95 D95,, V R p k

Outline Hierarchical Basket Model Modeling Autocorrelation Sequential Block Voting Results & Implementation

Factoring Joint Probabilities 100 Autocorrelation 095 090 085 080 20 15 10 5 0 5 10 15 20 Lag We can factorize the joint probability by conditioning on features that describe the related samples n p(y 0,, y n x 0,, x n ) := p(y i xi r, x i ) 0

Relational Features u3, 2014-11-13, 2014-11-14, A01/B01/C05/D11/ u4, 2014-11-14, 2014-11-16, A02/B01/C01/D02/;A05/B04/C05/D98/; u5, 2014-11-14, 2014-11-16, A05/B04/C05/D98/; u6, 2014-11-14, 2014-11-16, A04/B03/C06/D22/;A05/B14/C45/D68/; u7, 2014-11-14, 2014-11-16, A01/B01/C01/D03/;A01/B04/C05/D78/; A2 A4 A5 x a1 = [0, 1, 0, 1, 2, ] A1 A2 A4 A5 x a1:2 = [ 3, 1, 0, 1, 2, ] Combining different lags and categories we can describe the sample neighborhood with: x u5 = [x a1, x a1:2, x b1:3, x d1 ]

Relational Features u3, 2014-11-13, 2014-11-14, A01/B01/C05/D11/ u4, 2014-11-14, 2014-11-16, A02/B01/C01/D02/;A05/B04/C05/D98/; u5, 2014-11-14, 2014-11-16, A05/B04/C05/D98/; u6, 2014-11-14, 2014-11-16, A04/B03/C06/D22/;A05/B14/C45/D68/; u7, 2014-11-14, 2014-11-16, A01/B01/C01/D03/;A01/B04/C05/D78/; A2 A4 A5 x a1 = [0, 1, 0, 1, 2, ] A1 A2 A4 A5 x a1:2 = [ 3, 1, 0, 1, 2, ] Combining different lags and categories we can describe the sample neighborhood with: x u5 = [x a1, x a1:2, x b1:3, x d1 ]

Relational Features u3, 2014-11-13, 2014-11-14, A01/B01/C05/D11/ u4, 2014-11-14, 2014-11-16, A02/B01/C01/D02/;A05/B04/C05/D98/; u5, 2014-11-14, 2014-11-16, A05/B04/C05/D98/; u6, 2014-11-14, 2014-11-16, A04/B03/C06/D22/;A05/B14/C45/D68/; u7, 2014-11-14, 2014-11-16, A01/B01/C01/D03/;A01/B04/C05/D78/; A2 A4 A5 x a1 = [0, 1, 0, 1, 2, ] A1 A2 A4 A5 x a1:2 = [ 3, 1, 0, 1, 2, ] Combining different lags and categories we can describe the sample neighborhood with: x u5 = [x a1, x a1:2, x b1:3, x d1 ]

Outline Hierarchical Basket Model Modeling Autocorrelation Sequential Block Voting Results & Implementation

Identifying Sequential Blocks u1, 2014-11-13, 2014-11-14, A01/B01/C01/D01/ u2, 2014-11-14, 2014-11-15, A02/B02/C02/D02/;A02/B02/C03/D03/; u3, 2014-11-14, 2014-11-16, A02/B02/C02/D02/;A02/B02/C03/D04/; 1: blockid[:] 0 2: count 0 3: for i 1, n do 4: if endtime(i) endtime(i-1) then 5: count ++ 6: end if 7: blockid[i] count 8: end for

# wrong labels in block 8 7 6 5 4 3 2 1 0 0 20 40 60 80 100 120 140 160 block size

Block based Voting 1: if blocksize(i) 10 AND (median(i) 6 OR median(i) 9) then 2: if median(i) 9 then 3: predict female 4: else if median(i) 6 then 5: predict male 6: end if 7: else per sample threshold 8: if y i 82 then 9: predict female 10: else 11: predict male 12: end if 13: end if

Outline Hierarchical Basket Model Modeling Autocorrelation Sequential Block Voting Results & Implementation

Results & Implementation Score Place Final Result 084067348 7 Full Competition Source Code: https://githubcom/ibayer/pakdd2015_competition Factorization Machine Implementation: https://githubcom/ibayer/fastfm