Sign inSign up
Style in the Long Tail: Discovering Unique Interests with Latent Variable Models in Large Scale Social E-commerce thumbnail
Pause
Mute
Subtitles
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

Style in the Long Tail: Discovering Unique Interests with Latent Variable Models in Large Scale Social E-commerce

Published on Oct 07, 20142991 Views

Diane J. Hu

Purchasing decisions in many product categories are heavily influenced by the shopper's aesthetic preferences. It's insufficient to simply match a shopper with popular items from the category in quest

Industry & Government Sessions

Related categories

Data MiningKnowledge Extraction

Chapter list

Style in the Long Tail Discovering Unique Interests with Latent Variable Models in Large Scale Social E-commerce00:00
Overview - 100:17
ETSY OVERVIEW00:26
How do people typically use Etsy?01:10
How do people decide what to buy? 01:57
How to describe style?04:02
What Personalization Looks Like on Etsy05:22
Overview - 206:10
Solution Overview 07:26
Latent Dirichlet Allocation (LDA) for Discovering Styles - 107:36
Latent Dirichlet Allocation (LDA) for Discovering Styles - 208:21
Different styles discovered by LDA - 111:50
Different styles discovered by LDA - 212:40
Different styles discovered by LDA - 313:50
Overview - 314:14
User Recommendations - 114:17
Item Recommendations - 214:49
Shop Recommendations - 315:12
Shop Recommendations - 416:08
Recommending Styles within Categories16:20
Visualizing Related Topics - 117:24
Visualizing Related Topics - 217:50
Visualizing Related Topics - 318:12
Recommendations in the Activity Feed18:26
User Recommendation Experiments19:07
Conclusion20:12
Thank you!20:52