# Model-agnostic post-hoc explainability for recommender systems

arXiv: https://arxiv.org/abs/2509.10245 · HTML: https://mlsanity.com/paper/2509.10245/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 41 references that are in the map.
- First posted on arXiv 12 Sep 2025.

## Builds on (most cited first, 15 of 15)

- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [Neural Collaborative Filtering](https://mlsanity.com/paper/1708.05031/) (2017)
- [Bias and Debias in Recommender System: A Survey and Future Directions](https://mlsanity.com/paper/2010.03240/) (2020)
- [Explainable Recommendation: A Survey and New Perspectives](https://mlsanity.com/paper/1804.11192/) (2018)
- [Neural Collaborative Filtering vs. Matrix Factorization Revisited](https://mlsanity.com/paper/2005.09683/) (2020)
- [Feedback Loop and Bias Amplification in Recommender Systems](https://mlsanity.com/paper/2007.13019/) (2020)
- [On Softmax Direct Preference Optimization for Recommendation](https://mlsanity.com/paper/2406.09215/) (2024)
- [Fairness in Recommender Systems: Research Landscape and Future Directions](https://mlsanity.com/paper/2205.11127/) (2022)
- [Fairness in Recommendation: Foundations, Methods and Applications](https://mlsanity.com/paper/2205.13619/) (2022)
- [Streaming Recommender Systems](https://mlsanity.com/paper/1607.06182/) (2016)
- [A Comprehensive Survey of Evaluation Techniques for Recommendation Systems](https://mlsanity.com/paper/2312.16015/) (2023)
- [TiM4Rec: An Efficient Sequential Recommendation Model Based on Time-Aware Structured State Space Duality Model](https://mlsanity.com/paper/2409.16182/) (2024)
- [Contrastive Counterfactual Learning for Causality-aware Interpretable Recommender Systems](https://mlsanity.com/paper/2208.06746/) (2022)
- [RE-RecSys: An End-to-End system for recommending properties in Real-Estate domain](https://mlsanity.com/paper/2404.16553/) (2024)

## Abstract (arXiv)

Recommender systems often benefit from complex feature embeddings and deep learning algorithms, which deliver sophisticated recommendations that enhance user experience, engagement, and revenue. However, these methods frequently reduce the interpretability and transparency of the system. In this research, we develop a systematic application, adaptation, and evaluation of deletion diagnostics in the recommender setting. The method compares the performance of a model to that of a similar model trained without a specific user or item, allowing us to quantify how that observation influences the recommender, either positively or negatively. To demonstrate its model-agnostic nature, the proposal is applied to both Neural Collaborative Filtering (NCF), a widely used deep learning-based recommender, and Singular Value Decomposition (SVD), a classical collaborative filtering technique. Experiments on the MovieLens and Amazon Reviews datasets provide insights into model behavior and highlight the generality of the approach across different recommendation paradigms.