Explainable Recommender Systems development pipeline.
As recommender systems today play an important role in users' online experience and are involved in a wide range of decisions, multiple stakeholders demand explanations for the corresponding algorithmic predictions.
These demands, together with the benefits of explanations (e.g., trust, efficiency, and sometimes even persuasion), have triggered significant interest from researchers in academia and industry. Nonetheless, to the best of our knowledge, no comprehensive toolkit for explainable recommender systems is available to the community yet.
Researchers are frequently faced with the challenge of re-implementing prior algorithms when creating and evaluating new approaches. Aiming to address the resulting need, we present RecoXplainer, a library that includes several state-of-the-art explainability methods, and evaluation metrics.
RecoXplainer is a unified, extendable and easy to use Python toolkit that includes several explainability techniques that are useful for various groups of stakeholders.
The goal of RecoXplainer is to equally help applied data scientists and researchers who focus their efforts on improving the field of XRSs.
To the best of our knowledge, RecoXplainer is one of the first explainability software toolkits for XRSs that is easy to use, and supports code re-use, replication and reproduction of best practices of recommender systems.
To find out more about RecoXplainer, you can check out our presentation of the South Tyrol Free Software Conference - SFSConf 2020, and our tutorial at the 35th AAAI Conference on Artificial Intelligence - AAAI 2021, where we presented the following slides:
To get started with the library, you can check out RecoXplainer Code from the following Github project.
Contact us for any feedback and recommendations, or if you need assistance in getting started!
Please contact us for more information.