MarketBasket

This repository contains the implementation of 'Personalized Purchase Prediction of Market Baskets with Wasserstein-Based Sequence Matching', accepted for oral presentation at 25th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2019).

Run

1. Download the dataset containing market basket trajectories.
2. Create product embeddings using the product2vec.py script.
3. Run main.py to compute the distances and predictions of market basket trajectories similar to the ones under investigation

Citation

Please consider citing us if you find this helpful for your work:

@inproceedings{Kraus:2019:PPP:3292500.3330791,
 author = {Kraus, Mathias and Feuerriegel, Stefan},
 title = {Personalized Purchase Prediction of Market Baskets with Wasserstein-Based Sequence Matching},
 booktitle = {Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining},
 series = {KDD '19},
 year = {2019},
 doi = {10.1145/3292500.3330791},
 }