EXALT: EXplainable ALgorithmic Tools for Optimization Problems

TL;DR

EXALT tackles the lack of interpretability in optimization-based decision tools by embedding explainability into the optimization process, starting with the assignment problem. It combines alternative solution generation, input perturbation robustness, interpretable decision trees, and SHAP-based explanations to produce transparent, robust outputs; the framework also integrates expert validation and synthetic-data evaluation to demonstrate practical relevance in domains like sales. The work aims to make algorithmic decisions more trustworthy and accessible, with a modular design that can extend to various optimization tasks. Overall, it proposes a path toward explainable optimization that preserves performance while enhancing human-understandable rationale.

Abstract

Algorithmic solutions have significant potential to improve decision-making across various domains, from healthcare to e-commerce. However, the widespread adoption of these solutions is hindered by a critical challenge: the lack of human-interpretable explanations. Current approaches to Explainable AI (XAI) predominantly focus on complex machine learning models, often producing brittle and non-intuitive explanations. This project proposes a novel approach to developing explainable algorithms by starting with optimization problems, specifically the assignment problem. The developed software library enriches basic algorithms with human-understandable explanations through four key methodologies: generating meaningful alternative solutions, creating robust solutions through input perturbation, generating concise decision trees and providing reports with comprehensive explanation of the results. Currently developed tools are often designed with specific clustering algorithms in mind, which limits their adaptability and flexibility to incorporate alternative techniques. Additionally, many of these tools fail to integrate expert knowledge, which could enhance the clustering process by providing valuable insights and context. This lack of adaptability and integration can hinder the effectiveness and robustness of the clustering outcomes in various applications. The represents a step towards making algorithmic solutions more transparent, trustworthy, and accessible. By collaborating with industry partners in sectors such as sales, we demonstrate the practical relevance and transformative potential of our approach.