A prototype of a “Similar Shoe” (Sneaker) Recommender-System with Source Code [Josh Barua]
Josh Barua created https://runningshoesforyou.com/, a recommender-system for shoe recommendations. Users can provide as input either a specific shoe model or their preferences (comfort; weight; looks; …) and then receive 3 recommendations for shoes. Josh explains the recommender system in a blog post, and also releases the source code. It’s not a super sophisticated system but still nice to play around with it.
Being a cross country runner, I wanted to build a recommender system for running shoes. With 100k reviews of 505 running shoes from 18 manufacturers, my recommender system (runningshoesforyou.com) finds shoes that are a closer match with a consumer’s ideal preferences compared to those with the highest overall rating, without the need to read a large number of product reviews. The Python code I wrote for this recommender system is available from one of my GitHub repositories: https://github.com/JoshB02/recommender-system-tools
https://towardsdatascience.com/a-recommender-system-based-on-customer-preferences-and-product-reviews-3575992bb61
Related Posts
It’s No Joke: Recommender System Beats Humans At Making You Laugh [Michael Yeomans et al. / Diana Gerdeman @ Forbes]
Google´s SmartReply comes to YouTube [Rami Al-Rfou @ Google AI Blog]
Bingie is an app for all your streaming recommendations and debates [Anthony Ha @ TechCrunch]
About The Author
Joeran Beel
Founder of Recommender-Systems.com (RS_c) and Professor of Intelligent Systems at the University of Siegen, Germany