MARS-Gym: A Gym framework to model, train, and evaluate Recommender Systems for Marketplaces

September 30, 2020 · Entered Twilight · 🏛 2020 International Conference on Data Mining Workshops (ICDMW)

"Last commit was 5.0 years ago (≥5 year threshold)"

Evidence collected by the PWNC Scanner

Repo contents: .bumpversion.cfg, .cookiecutterrc, .coveragerc, .dockerignore, .editorconfig, .gitignore, .readthedocs.yml, .travis.yml, AUTHORS.rst, CHANGELOG.rst, CONTRIBUTING.rst, LICENSE, MANIFEST.in, README.rst, ci, config.py, cuda_luigi, cuda_luigid, docs, environment.yml, images, samples, setup.cfg, setup.py, src, tests, tox.ini

Authors Marlesson R. O. Santana, Luckeciano C. Melo, Fernando H. F. Camargo, Bruno Brandão, Anderson Soares, Renan M. Oliveira, Sandor Caetano arXiv ID 2010.07035 Category cs.IR: Information Retrieval Cross-listed cs.HC, cs.LG, stat.ML Citations 17 Venue 2020 International Conference on Data Mining Workshops (ICDMW) Repository https://github.com/deeplearningbrasil/mars-gym ⭐ 50 Last Checked 1 month ago

Abstract

Recommender Systems are especially challenging for marketplaces since they must maximize user satisfaction while maintaining the healthiness and fairness of such ecosystems. In this context, we observed a lack of resources to design, train, and evaluate agents that learn by interacting within these environments. For this matter, we propose MARS-Gym, an open-source framework to empower researchers and engineers to quickly build and evaluate Reinforcement Learning agents for recommendations in marketplaces. MARS-Gym addresses the whole development pipeline: data processing, model design and optimization, and multi-sided evaluation. We also provide the implementation of a diverse set of baseline agents, with a metrics-driven analysis of them in the Trivago marketplace dataset, to illustrate how to conduct a holistic assessment using the available metrics of recommendation, off-policy estimation, and fairness. With MARS-Gym, we expect to bridge the gap between academic research and production systems, as well as to facilitate the design of new algorithms and applications.