Skip to content

Latest commit

 

History

History
62 lines (42 loc) · 2.01 KB

README.md

File metadata and controls

62 lines (42 loc) · 2.01 KB
Raw

Cross-Sell Up-Sell Recommender System

A recommender system that enables cross-sell and upsell of products (either new products or already bought products) that will enable higher revenue generation. The data captures material that is sent to the wholesalers over a span of time.

Link for the presentation - https://drive.google.com/file/d/1o8j2kPF_6vMz_LpxZn8uiZ_DAk83tkgU/view?usp=sharing

Here is a video of the working of the platform. Click on it to get directed to the Google Drive link:

Objectives

  • Finding how similar other wholesalers are to W1.
  • Finding wholesalers who buy similar products.
  • Finding wholesalers who buy similar products.
  • Application of a feedback mechanism so that sales team can easily implement their knowledge of incompatible products/customer.
  • To find which products are popular.
  • To recommend the product which will enable higher revenue generation.

The dataset

The dataset has been provided by AB InBev as a part of their hackathon Maverick 2.0: Hack-a-thon where the participants in the Cross-Sell Up-Sell track were to build a Recommender System based on the data given Consumers/Wholesalers and their history of purchase.

Installation and setup

  • Before starting the installation process, please ensure that you have conda/virtualenv installed.
  1. Open terminal and clone the reposotory:
  git clone https://github.com/milonimittal/Cross_Sell-Up_Sell.git
  1. Change into project directory:
  cd Cross_Sell-Up_Sell
  1. Create python environment:
  conda create --name recsys python=3.8.5
  1. Activate environment:
   conda activate recsys
  1. Install dependencies:
   pip install -r requirements.txt
  1. Running the code:
   python main_flask.py

Contributing

Feel free to contribute features / point out errors. Fork this repository and make a pull request.