# Designing an Interpretable Interface for Contextual Bandits

arXiv: https://arxiv.org/abs/2409.15143 · HTML: https://mlsanity.com/paper/2409.15143/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 37 references that are in the map.
- First posted on arXiv 23 Sep 2024.

## Builds on (most cited first, 18 of 18)

- [InterpretML: A Unified Framework for Machine Learning Interpretability](https://mlsanity.com/paper/1909.09223/) (2019)
- [Chat-REC: Towards Interactive and Explainable LLMs-Augmented Recommender System](https://mlsanity.com/paper/2303.14524/) (2023)
- [More Robust Doubly Robust Off-policy Evaluation](https://mlsanity.com/paper/1802.03493/) (2018)
- [Optimal and Adaptive Off-policy Evaluation in Contextual Bandits](https://mlsanity.com/paper/1612.01205/) (2016)
- [Counterfactual Explainable Recommendation](https://mlsanity.com/paper/2108.10539/) (2021)
- [ActiVis: Visual Exploration of Industry-Scale Deep Neural Network Models](https://mlsanity.com/paper/1704.01942/) (2017)
- [An Efficient Bandit Algorithm for Realtime Multivariate Optimization](https://mlsanity.com/paper/1810.09558/) (2018)
- [Why? Why not? When? Visual Explanations of Agent Behavior in Reinforcement Learning](https://mlsanity.com/paper/2104.02818/) (2021)
- [Explainability in Music Recommender Systems](https://mlsanity.com/paper/2201.10528/) (2022)
- [Online Limited Memory Neural-Linear Bandits with Likelihood Matching](https://mlsanity.com/paper/2102.03799/) (2021)
- [Personalized Audiobook Recommendations at Spotify Through Graph Neural Networks](https://mlsanity.com/paper/2403.05185/) (2024)
- [Non-Stationary Latent Bandits](https://mlsanity.com/paper/2012.00386/) (2020)
- [Unifying Clustered and Non-stationary Bandits](https://mlsanity.com/paper/2009.02463/) (2020)
- [Enhancing User Intent Capture in Session-Based Recommendation with Attribute Patterns](https://mlsanity.com/paper/2312.16199/) (2023)
- [Contextual User Browsing Bandits for Large-Scale Online Mobile Recommendation](https://mlsanity.com/paper/2008.09368/) (2020)
- [Contextual Bandit Applications in Customer Support Bot](https://mlsanity.com/paper/2112.03210/) (2021)
- [Democratizing online controlled experiments at Booking.com](https://mlsanity.com/paper/1710.08217/) (2017)
- [Cold-start Problems in Recommendation Systems via Contextual-bandit Algorithms](https://mlsanity.com/paper/1405.7544/) (2014)

## Abstract (arXiv)

Contextual bandits have become an increasingly popular solution for personalized recommender systems. Despite their growing use, the interpretability of these systems remains a significant challenge, particularly for the often non-expert operators tasked with ensuring their optimal performance. In this paper, we address this challenge by designing a new interface to explain to domain experts the underlying behaviour of a bandit. Central is a metric we term "value gain", a measure derived from off-policy evaluation to quantify the real-world impact of sub-components within a bandit. We conduct a qualitative user study to evaluate the effectiveness of our interface. Our findings suggest that by carefully balancing technical rigour with accessible presentation, it is possible to empower non-experts to manage complex machine learning systems. We conclude by outlining guiding principles that other researchers should consider when building similar such interfaces in future.