Talk Submission at Pycon India 2016

Talk Video

• What it is ??
• How it is done?
• Technologies used
• Data and Models
• Installation
• What is there inside the box 📦 ?
• Contributors
• Issues 🐛

How can we create a recommendation engine that is based both on user browsing history and product reviews? Can I create recommendations purely based on the 'intent' and 'context' of the search?

This talk will showcase how a recommendation engine can be built with user browser history and user-generated reviews using a state of the art technique - word2vec. We will create something that not only matches the existing recommender systems deployed by websites, but goes one step ahead - incorporating context to generate valid and innovative recommendations. The beauty of such a framework is that not only does it support online learning, but is also sensitive to minor changes in user tone and behavior.

The trick/secret sauce is - How do we account for the 'context' and build it in our systems? The talk will answer these questions and showcase effectiveness of such a recommender system.

• First Milestone 🎉

  Subset of the engine's functionality was completed during a project undertaken at IASNLP 2016 held by Language Technology Research Center (LTRC), IIIT Hyderabad

• Google's Word2vec
• Gensim
• Numpy
• Flask, Redis.

• Rest of the models (User & Metadata) can be downloaded from https://s3.amazonaws.com/iasnlp-models/output_models.tar
• Amazon review data will be made available (for research purposes) on request. Please contact Julian McAuley (julian.mcauley@gmail.com) to obtain a link. Sample data files available at: http://jmcauley.ucsd.edu/data/amazon/

• Lets do it !!

You can tweet to Manas Ranjan Kar or Akhil Gupta if you can't get it to work. In fact, you should tweet us anyway.