Skip to content

manasRK/word2vec-recommender

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

word2vec-recommender

GitHub license

Talk Submission at Pycon India 2016

Index

What it is?

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.

How it is done?

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

Technologies used

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

Data and Models

Installation

What is there inside the box?

File Function
semsim_train.py Main file to train models
preProcessing.py Methods to preprocess and clean data before feeding for training
loadReviewModel.py For loading review model
loadRedis.py For loading redis model
loadMetaModel.py For loading meta model

contributors

Author Working As contact @
Manas Ranjan kar Practice Lead @ Juxt Smart Mandate @github
Akhil Gupta Intern @ Amazon @github
Vinay Kumar MS @ IIT-KGP @github

Issues 🐛

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.

About

Recommendation engine based on contextual word embeddings

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published