# PRINCE: Provider-side Interpretability with Counterfactual Explanations in Recommender Systems

arXiv: https://arxiv.org/abs/1911.08378 · HTML: https://mlsanity.com/paper/1911.08378/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Nov 2019.

## Built on by (most cited first, 30 of 35)

- [CARLA: A Python Library to Benchmark Algorithmic Recourse and Counterfactual Explanation Algorithms](https://mlsanity.com/paper/2108.00783/) (2021)
- [If Only We Had Better Counterfactual Explanations: Five Key Deficits to Rectify in the Evaluation of Counterfactual XAI Techniques](https://mlsanity.com/paper/2103.01035/) (2021)
- [Counterfactual Explainable Recommendation](https://mlsanity.com/paper/2108.10539/) (2021)
- [Counterfactuals and Causability in Explainable Artificial Intelligence: Theory, Algorithms, and Applications](https://mlsanity.com/paper/2103.04244/) (2021)
- [A Comprehensive Survey on Trustworthy Recommender Systems](https://mlsanity.com/paper/2209.10117/) (2022)
- [Counterfactual Explanations for Neural Recommenders](https://mlsanity.com/paper/2105.05008/) (2021)
- [G-Refer: Graph Retrieval-Augmented Large Language Model for Explainable Recommendation](https://mlsanity.com/paper/2502.12586/) (2025)
- [PaGE-Link: Path-based Graph Neural Network Explanation for Heterogeneous Link Prediction](https://mlsanity.com/paper/2302.12465/) (2023)
- [Causal Deep Learning](https://mlsanity.com/paper/2303.02186/) (2023)
- [Causal Collaborative Filtering](https://mlsanity.com/paper/2102.01868/) (2021)
- [Reinforced Path Reasoning for Counterfactual Explainable Recommendation](https://mlsanity.com/paper/2207.06674/) (2022)
- [Filter Bubbles in Recommender Systems: Fact or Fallacy -- A Systematic Review](https://mlsanity.com/paper/2307.01221/) (2023)
- [From Intrinsic to Counterfactual: On the Explainability of Contextualized Recommender Systems](https://mlsanity.com/paper/2110.14844/) (2021)
- [Towards Unifying Evaluation of Counterfactual Explanations: Leveraging Large Language Models for Human-Centric Assessments](https://mlsanity.com/paper/2410.21131/) (2024)
- [Benchmarking Instance-Centric Counterfactual Algorithms for XAI: From White Box to Black Box](https://mlsanity.com/paper/2203.02399/) (2022)
- [ExplainableFold: Understanding AlphaFold Prediction with Explainable AI](https://mlsanity.com/paper/2301.11765/) (2023)
- [Factual and Personalized Recommendations using Language Models and Reinforcement Learning](https://mlsanity.com/paper/2310.06176/) (2023)
- [ELIXIR: Learning from User Feedback on Explanations to Improve Recommender Models](https://mlsanity.com/paper/2102.09388/) (2021)
- [Counterfactual Collaborative Reasoning](https://mlsanity.com/paper/2307.00165/) (2023)
- [User-Controllable Recommendation via Counterfactual Retrospective and Prospective Explanations](https://mlsanity.com/paper/2308.00894/) (2023)
- [RecRec: Algorithmic Recourse for Recommender Systems](https://mlsanity.com/paper/2308.14916/) (2023)
- [Counterfactually Evaluating Explanations in Recommender Systems](https://mlsanity.com/paper/2203.01310/) (2022)
- [Dynamic Causal Collaborative Filtering](https://mlsanity.com/paper/2208.11094/) (2022)
- [Learning to Counterfactually Explain Recommendations](https://mlsanity.com/paper/2211.09752/) (2022)
- [Explaining Recommendation System Using Counterfactual Textual Explanations](https://mlsanity.com/paper/2303.11160/) (2023)
- [Review of Explainable Graph-Based Recommender Systems](https://mlsanity.com/paper/2408.00166/) (2024)
- [Extracting Interaction-Aware Monosemantic Concepts in Recommender Systems](https://mlsanity.com/paper/2511.18024/) (2025)
- [Explaining Group Recommendations via Counterfactuals](https://mlsanity.com/paper/2601.16882/) (2026)
- [Explainable Recommender with Geometric Information Bottleneck](https://mlsanity.com/paper/2305.05331/) (2023)
- [Explainable History Distillation by Marked Temporal Point Process](https://mlsanity.com/paper/2311.07797/) (2023)

## Abstract (arXiv)

Interpretable explanations for recommender systems and other machine learning models are crucial to gain user trust. Prior works that have focused on paths connecting users and items in a heterogeneous network have several limitations, such as discovering relationships rather than true explanations, or disregarding other users' privacy. In this work, we take a fresh perspective, and present PRINCE: a provider-side mechanism to produce tangible explanations for end-users, where an explanation is defined to be a set of minimal actions performed by the user that, if removed, changes the recommendation to a different item. Given a recommendation, PRINCE uses a polynomial-time optimal algorithm for finding this minimal set of a user's actions from an exponential search space, based on random walks over dynamic graphs. Experiments on two real-world datasets show that PRINCE provides more compact explanations than intuitive baselines, and insights from a crowdsourced user-study demonstrate the viability of such action-based explanations. We thus posit that PRINCE produces scrutable, actionable, and concise explanations, owing to its use of counterfactual evidence, a user's own actions, and minimal sets, respectively.