RecSys Challenge 23

Final prediction is ensembled by only 5 models, which are DCNv2, HardShareSEnet, PLE, PLEMLPSEnet, PLESEnet respectively.

Data

run analyze/process.ipynb, data/split_sample.ipynb and feature_engineer/weekday.ipynb to generate *.csv

Path

fix url in RecStudio/recstudio/data/config/*.yaml

Download checkpoint

download DCNv2 and save *.ckpt in saved/DCNv2/

other checkpoints have already been kept in saved/

Predict

run predict.sh to generate the final prediction.

Try more

Please refer to RecStudio, which is a unified, highly-modularized and recommendation-efficient recommendation library based on PyTorch. We welcome more effient models from you.