Saved in:
Bibliographic Details
Main Authors: Maher, Andrew, Gobbo, Matia, Lachartre, Lancelot, Prabanantham, Subash, Swiers, Rowan, Liyanagama, Puli
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2409.15143
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929511031898112
author Maher, Andrew
Gobbo, Matia
Lachartre, Lancelot
Prabanantham, Subash
Swiers, Rowan
Liyanagama, Puli
author_facet Maher, Andrew
Gobbo, Matia
Lachartre, Lancelot
Prabanantham, Subash
Swiers, Rowan
Liyanagama, Puli
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2409_15143
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Designing an Interpretable Interface for Contextual Bandits
Maher, Andrew
Gobbo, Matia
Lachartre, Lancelot
Prabanantham, Subash
Swiers, Rowan
Liyanagama, Puli
Machine Learning
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.
title Designing an Interpretable Interface for Contextual Bandits
topic Machine Learning
url https://arxiv.org/abs/2409.15143