Abstract
Scheduling is the task of assigning a set of scarce resources distributed over time to a set of agents, who typically have preferences about the assignments they would like to get. Due to the constrained nature of these problems, satisfying all agents' preferences is often infeasible, which might lead to some agents not being happy with the resulting schedule. Providing explanations has been shown to increase satisfaction and trust in solutions produced by AI tools. However, it is particularly challenging to explain solutions that are influenced by and impact on multiple agents. In this paper we introduce the EXPRES framework, which can explain why a given preference was unsatisfied in a given optimal schedule. The EXPRES framework consists of: (i) an explanation generator that, based on a Mixed-Integer Linear Programming model, finds the best set of reasons that can explain an unsatisfied preference; and (ii) an explanation parser, which translates the generated explanations into human interpretable ones. Through simulations, we show that the explanation generator can efficiently scale to large instances. Finally, through a set of user studies within J.P. Morgan, we show that employees preferred the explanations generated by EXPRES over human-generated ones when considering workforce scheduling scenarios.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of the 32nd International Conference on Automated Planning and Scheduling, ICAPS 2022 |
| Editors | Akshat Kumar, Sylvie Thiebaux, Pradeep Varakantham, William Yeoh |
| Publisher | Association for the Advancement of Artificial Intelligence |
| Pages | 710-718 |
| Number of pages | 9 |
| ISBN (Electronic) | 9781577358749 |
| DOIs | |
| State | Published - 13 Jun 2022 |
| Event | 32nd International Conference on Automated Planning and Scheduling, ICAPS 2022 - Virtual, Online, Singapore Duration: 13 Jun 2022 → 24 Jun 2022 |
Publication series
| Name | Proceedings International Conference on Automated Planning and Scheduling, ICAPS |
|---|---|
| Volume | 32 |
| ISSN (Print) | 2334-0835 |
| ISSN (Electronic) | 2334-0843 |
Conference
| Conference | 32nd International Conference on Automated Planning and Scheduling, ICAPS 2022 |
|---|---|
| Country/Territory | Singapore |
| City | Virtual, Online |
| Period | 13/06/22 → 24/06/22 |
Bibliographical note
Publisher Copyright:© 2022, Association for the Advancement of Artificial Intelligence.
Funding
This paper was prepared for informational purposes in part by the Artificial Intelligence Research group of JPMorgan Chase & Co. and its affiliates (“JP Morgan”), and is not a product of the Research Department of JP Morgan. JP Morgan makes no representation and warranty whatsoever and disclaims all liability, for the completeness, accuracy or reliability of the information contained herein. This document is not intended as investment research or investment advice, or a recommendation, offer or solicitation for the purchase or sale of any security, financial instrument, financial product or service, or to be used in any way for evaluating the merits of participating in any transaction, and shall not constitute a solicitation under any jurisdiction or to any person, if such solicitation under such jurisdiction or to such person would be unlawful.
| Funders | Funder number |
|---|---|
| Artificial Intelligence Research group of JPMorgan Chase & Co. |