Here we are trying to implement Explicit Collaborative Filtering.
We have prepared a data pipeline to process input data.
We have a built recommender system.
s3 file storage has the following final preprocessed files in parquet format
- ALS_baseline - user_ix, biz_ix, stars
- bizMap - business_id, bis_ix
- userMap- user_id,user_ix
- tip- all columns of tip with user_ix and biz_ix
- review - all columns of review with user_ix and biz_ix