Recommender Systems in E-Commerce
Download as PPT, PDF6 likes4,104 views
This document summarizes recommender systems used in e-commerce and their benefits. It outlines examples of recommender systems from companies like Amazon, CDNOW, and eBay. It then categorizes recommender systems based on their interface (browsing, top-N lists, etc.) and recommendation technology (item-to-item correlation, people-to-people correlation, etc.). Finally, it discusses how recommender systems can enhance e-commerce by helping customers find products, suggesting additional purchases, and creating customer loyalty.
Recommender Systems in E-Commerce
- 1. Recommender Systems in E-Commerce J. Ben Schafer, Joseph Konstan, John Riedl E-COMMERCR 99,Denver,Colorado 1999 ACM Presentation by 邱信淵
- 2. Outline Introduction Recommender System Examples Taxonomy of recommender systems E-Commerce Opportunities Conclusion
- 3. Introduction Old world of mass production Standardized products Homogeneous markets Long product life and development cycles Now Develop multiple products to meet the multiple needs of multiple customers
- 4. A Little Problem “ information overload!” Customers have to process the amount of information before to select what them want. One solution: recommender systems
- 5. Enhance E-commerce sales in 3 ways Browsers into Buyers Help customers find the products Cross-sell Suggestion additional products Loyalty Creating relationships
- 6. Recommender System Examples Amazon CDNOW eBay Levis Moviefinder.com Reel.com
- 7. Recommender System Examples Amazon.com CDNOW eBay Levis Reel.com Moviefinder.com Customers who bought Album advisor Feedback profile Style finder Movie matches Match maker Eyes My CDNOW Movie map We predict Amazon.com delivers Book matcher Customer comments
- 8. Taxonomy of recommender systems --Interface Browsing Similar item Email Text comments
- 9. Taxonomy of recommender systems --Interface Average rating Top-N Ordered search result
- 10. Recommender System Examples Business/Application Recommendation Interface Recommendation Technology Finding Recommendations Amazon.com Customers who Bought Similar Item Item to Item Correlation Purchase data Organic Navigation Eyes Email Attribute Based Keywords/freeform Amazon.com Delivers Email Attribute Based Selection options Book Matcher Top N List People to People Correlation Likert Request List Customer Comments Average Rating Text Comments Aggregated Rating Likert Text Organic Navigation
- 11. Recommender System Examples Business/Application Recommendation Interface Recommendation Technology Finding Recommendations CDNOW Album Advisor Similar Item Top N List Item to Item Correlation Purchase data Organic Navigation Keyword/freeform My CDNOW Top N List People to People Correlation Likert Organic Navigation Request List eBay Feedback Profile Average Rating Text Comments Aggregated Rating Likert Text Organic Navigation Levis Style Finder Top N List People to People Correlation Likert Request List
- 12. Recommender System Examples Business/Application Recommendation Interface Recommendation Technology Finding Recommendations Moviefinder.com Match Maker Similar Item Item to Item Correlation Editor’s choice Navigate to an item We Predict Top N List Ordered Search Results Average Rating People to People Correlation Aggregated Rating Likert Keywords/freeform Selection options Organic Navigation Reel.com Movie Matches Similar Item Item to Item Correlation Editor’s choice Organic Navigation Movie Map Browsing Attributed Based Editor’s choice Keywords/freeform
- 13. Taxonomy of recommender systems --Techniques Non-Personalized Attribute-Based Item-to-Item Correlation
- 14. Taxonomy of recommender systems --Techniques People-to-People Correlation User Input Purchase data Likert Text Editor’s choice
- 15. Finding Recommendations Organic Navigation Album Advisor, Movie Matches, Feedback Profile Request Recommendation List Book matcher, Style Finder Selection Options Amazon.com Delivers Keyword/Freeform Eyes; Album Advisor; We Predict, Movie Map
- 17. E-Commerce Opportunities Combine multiple types of data ( algorithms ) Buy-side Sell-side Shared Information
- 18. Conclusion