Predictive analytics for cars.com
- 1. + Predictive Analytics for Cars.com Directed by Professor Martin Bariff Joyce Yang Ivy Shi, Chris Zhu
- 2. + Introduction Data Preparation Data Mining Methods Better Cars.com 2
- 6. + DATA PREPARATION KEY VARIABLES 6 a. Basic Information b. Ratings c. Indicators
- 7. + DATA PREPARATION CLEANING 7 Ready-to-Use Data Overall Rating Quality of Repair Shopping for Used
- 8. + DATA PREPARATION 8 Unbalanced Data Balanced Data BALANCING 68.45% 10.01% 2.11% 3.01% 16.43% 41.96% 30.21% 18.40% 3.88% 5.54% 27 ％
- 10. + METHODS 10 • K-Means Cluster Analysis • Decision Tree Predictive Analysis Text Mining
- 11. + CLUSTER ANALYSIS 11 K-MEANS K-Means is the most popular nonhierarchical clustering method. K-Means is based on geometric notions of similarity
- 12. + CLUSTER ANALYSIS K-MEANS 12 Model Accuracy Model Summary
- 14. + Customers who purchase used cars from a dealer rating high for the dealer recommending the dealer to others. 14 K-MEANS CLUSTER ANALYSIS
- 15. + PREDICTIVE ANALYSIS A tree-building algorithm Recursively splitting the data into smaller and smaller groups based on the fields that provides the maximum information gain Used C5.0 model in our research 15 INTRODUCTION OF DECISION TREE MODEL
- 16. + 16 Decision Tree with Balanced Data PREDICTIVE ANALYSIS DECISION TREE Evaluation Standard Overall accuracy: > 80% Favorability between training & testing samples: The results with the testing sample compare favorably to the training sample. 60% 40%
- 17. + 17 DECISION TREE PREDICTIVE ANALYSIS Rating - Customer Service
- 18. + PREDICTIVE ANALYSIS Extract key concepts from the text and create categories with these concepts by using linguistic and frequency techniques Explore more information and context included in the data Better compare the results with and without text data and see the difference 18 INTRODUCTION OF TEXT MINING MODEL
- 19. + PREDICTIVE ANALYSIS 19 Model with Only Numeric Data Model with Text & Numeric Data DECISION TREE MODEL WITH TEXT DATA
- 20. + 20 Interactive Workbench Categories and Concepts View PREDICTIVE ANALYSIS
- 21. buying/buying process 21 Trustful & Knowledgeable Relatively consistent pricing Extended warranty Nearest location < Service & Credibility
- 22. + 0 10 20 30 40 50 60 70 80 90 100 High Overall Rating % 22 Rating = 5 Rating = 1 PREDICTIVE ANALYSIS 0 10 20 30 40 50 60 70 80 90 100 Low Overall Rating % TEXT MINING
- 24. 24What we get from our analysis… Less influential dealer’s information Purchase behavior =>Higher overall rating Higher rating for buying process & customer service =>Higher Overall Rating Text Mining =>New Hint for Consumer behavior Overall Rating
- 25. + Stimulus – Influence Overall Rating Buying Process (experience) -Sales people -Service -Facility (Eg: Internet) -Family’s feeling Price sensitivity Finance issue 25 NEW HINT
- 26. + Additional Rating Review Additional Questions Personal Information Motivation New Review Sheet 26 STEP 1: Customers have more rights on review sheet
- 28. Are you satisfied with this purchase? Yes No Please tell us WHY (Mark all that apply) Quality of in-store service Quality of vehicle Price Financial Service (Insurance, cash deal, warranty cost, monthly payment) Location of dealer Sales People In-store facility In-store environment Can/Cannot get vehicle in quickly enough Service Department hours Alternative transportation not available (rental car, shuttle, etc.) Other______________ 28 Additional Questions
- 29. + Dealer Rating Dealer: Motivation 29 STEP 2: More visual hint for customers Dealer: Best Seller Extended Warranty Label
- 30. + Motivation Facilities: Services: More space for Dealer Description • Lounge with snacks and drink • Free Wi-Fi • Insurance • Deal/Gift • Extended Warranty • Maintenance • Free certification 30 STEP 3: New Dealers Resume 3 others viewing this vehicle right now 15 others bought vehicles from this dealer in the last month
- 31. + Motivation • Sub-rating list • Monthly Star Dealer (label in the search page) Monthly highest rating dealer Monthly recommended dealer Monthly best seller The most favorable dealer 31 STEP 4: Monthly rating list
- 32. + Better Cars.Com Combine Cars review sheet and Dealer review sheet Continue to review dealer? Yes No Dealers Review sheet……… Add schedule plug-in Online voicemail Add to Favorite Relevant vehicles to consider You Viewed Customer who view this also viewed Recommended base on your browsing history 32
- 33. + Thank You for Your Listening Predictive Analytics for Cars.com Directed by Professor Martin Bariff Questions???