E. Arslan
info
Please Note
<p>This page displays the records of the person named above and is not linked to a unique person identifier. This record may need to be merged to a profile.</p>
3 records found
1
SORTeD Rashomon Sets of Sparse Decision Trees
Anytime Enumeration
Conference paper
(2025)
-
Elif Arslan, Jacobus G. M. van der Linden, Serge Hoogendoorn, Marco Rinaldi, Emir Demirović
Sparse decision tree learning provides accurate and interpretable predictive models that are ideal for high-stakes applications by finding the single most accurate tree within a (soft) size limit. Rather than relying on a single “best” tree, Rashomon sets—trees with similar performance but varying structures—can be used to enhance variable importance analysis, enrich explanations, and enable users to choose simpler trees or those that satisfy stakeholder preferences (e.g., fairness) without hard-coding such criteria into the objective function. However, because finding the optimal tree is NP-hard, enumerating the Rashomon set is inherently challenging. Therefore, we introduce SORTD, a novel framework that improves scalability and enumerates trees in the Rashomon set in order of the objective value, thus offering anytime behavior. Our experiments show that SORTD reduces runtime by up to two orders of magnitude compared with the state of the art. Moreover, SORTD can compute Rashomon sets for any separable and totally ordered objective and supports post-evaluating the set using other separable (and partially ordered) objectives. Together, these advances make exploring Rashomon sets more practical in real-world applications.
...
Sparse decision tree learning provides accurate and interpretable predictive models that are ideal for high-stakes applications by finding the single most accurate tree within a (soft) size limit. Rather than relying on a single “best” tree, Rashomon sets—trees with similar performance but varying structures—can be used to enhance variable importance analysis, enrich explanations, and enable users to choose simpler trees or those that satisfy stakeholder preferences (e.g., fairness) without hard-coding such criteria into the objective function. However, because finding the optimal tree is NP-hard, enumerating the Rashomon set is inherently challenging. Therefore, we introduce SORTD, a novel framework that improves scalability and enumerates trees in the Rashomon set in order of the objective value, thus offering anytime behavior. Our experiments show that SORTD reduces runtime by up to two orders of magnitude compared with the state of the art. Moreover, SORTD can compute Rashomon sets for any separable and totally ordered objective and supports post-evaluating the set using other separable (and partially ordered) objectives. Together, these advances make exploring Rashomon sets more practical in real-world applications.
The emergence of ride-hailing services has introduced computational challenges in optimizing vehicle routes. One of these challenges is solving the routing problem for long-term periods, as it requires accurate and explainable demand predictions. This is because explainability influences solution trustworthiness while accuracy determines final optimization outcomes. To address this, we employed Multi-Objective Optimal Regression Tree (MOO-RT) with accuracy and explainability objectives. Comparative analysis against other models, utilizing accuracy (MSE) and explainability (global Shapley Value) metrics, demonstrated MOO-RT’s impact on enhancing explainability whereas Random Forest emerged as the top performer in accuracy. Moreover, using Shapley values our study identified model-independent significant features for passenger prediction.
...
The emergence of ride-hailing services has introduced computational challenges in optimizing vehicle routes. One of these challenges is solving the routing problem for long-term periods, as it requires accurate and explainable demand predictions. This is because explainability influences solution trustworthiness while accuracy determines final optimization outcomes. To address this, we employed Multi-Objective Optimal Regression Tree (MOO-RT) with accuracy and explainability objectives. Comparative analysis against other models, utilizing accuracy (MSE) and explainability (global Shapley Value) metrics, demonstrated MOO-RT’s impact on enhancing explainability whereas Random Forest emerged as the top performer in accuracy. Moreover, using Shapley values our study identified model-independent significant features for passenger prediction.