Feature Interaction Interpretability: A Case for Explaining Ad-Recommendation Systems via Neural Interaction Detection
This work addresses interpretability and accuracy in ad-recommendation systems, which is important for user trust and effectiveness, though it is incremental as it builds on existing interaction detection methods.
The paper tackled the problem of interpreting and improving black-box recommender systems by detecting and encoding feature interactions, achieving significant performance gains in ad-click prediction.
Recommendation is a prevalent application of machine learning that affects many users; therefore, it is important for recommender models to be accurate and interpretable. In this work, we propose a method to both interpret and augment the predictions of black-box recommender systems. In particular, we propose to interpret feature interactions from a source recommender model and explicitly encode these interactions in a target recommender model, where both source and target models are black-boxes. By not assuming the structure of the recommender system, our approach can be used in general settings. In our experiments, we focus on a prominent use of machine learning recommendation: ad-click prediction. We found that our interaction interpretations are both informative and predictive, e.g., significantly outperforming existing recommender models. What's more, the same approach to interpret interactions can provide new insights into domains even beyond recommendation, such as text and image classification.