@article{ART003348237},
author={Ok-Joo Choi and Won Sun Shin},
title={An Explainable AI-based Framework for SQL Query Performance Optimization Recommendation},
journal={ Journal of Software Forensics},
issn={3092-541X},
year={2026},
volume={22},
number={2},
pages={165-177},
doi={10.29056/jsf.2026.06.15}
TY - JOUR
AU - Ok-Joo Choi
AU - Won Sun Shin
TI - An Explainable AI-based Framework for SQL Query Performance Optimization Recommendation
JO - Journal of Software Forensics
PY - 2026
VL - 22
IS - 2
PB - Korea Software Assessment and Valuation Society
SP - 165
EP - 177
SN - 3092-541X
AB - Although recent machine learning-based approaches have shown promise in predicting SQL query performance, most studies primarily focus on improving prediction accuracy, leaving the interpretability of black-box models largely unaddressed. To address this limitation, this study proposes an explainable AI-based SQL query performance optimization recommendation framework that integrates performance prediction with post-hoc explanation techniques. The proposed framework was evaluated in a PostgreSQL environment using the 22 standard TPC-H benchmark queries. Experimental results demonstrated strong prediction performance on the test set, achieving a MAE of 359.846 ms, an RMSE of 466.056 ms, and an R² score of 0.9563. Furthermore, SHAP analysis revealed that statistical features of execution time and structural features of the execution plan were the major factors affecting performance, while LIME analysis demonstrated that the prediction results could be explained at the level of individual SQL queries.
KW - Explainable AI(XAI);SQL Query Optimization;Query Execution Plan;SHAP;LIME
DO - 10.29056/jsf.2026.06.15
ER -
Ok-Joo Choi and Won Sun Shin. (2026). An Explainable AI-based Framework for SQL Query Performance Optimization Recommendation. Journal of Software Forensics, 22(2), 165-177.
Ok-Joo Choi and Won Sun Shin. 2026, "An Explainable AI-based Framework for SQL Query Performance Optimization Recommendation", Journal of Software Forensics, vol.22, no.2 pp.165-177. Available from: doi:10.29056/jsf.2026.06.15
Ok-Joo Choi, Won Sun Shin "An Explainable AI-based Framework for SQL Query Performance Optimization Recommendation" Journal of Software Forensics 22.2 pp.165-177 (2026) : 165.
Ok-Joo Choi, Won Sun Shin. An Explainable AI-based Framework for SQL Query Performance Optimization Recommendation. 2026; 22(2), 165-177. Available from: doi:10.29056/jsf.2026.06.15
Ok-Joo Choi and Won Sun Shin. "An Explainable AI-based Framework for SQL Query Performance Optimization Recommendation" Journal of Software Forensics 22, no.2 (2026) : 165-177.doi: 10.29056/jsf.2026.06.15
Ok-Joo Choi; Won Sun Shin. An Explainable AI-based Framework for SQL Query Performance Optimization Recommendation. Journal of Software Forensics, 22(2), 165-177. doi: 10.29056/jsf.2026.06.15
Ok-Joo Choi; Won Sun Shin. An Explainable AI-based Framework for SQL Query Performance Optimization Recommendation. Journal of Software Forensics. 2026; 22(2) 165-177. doi: 10.29056/jsf.2026.06.15
Ok-Joo Choi, Won Sun Shin. An Explainable AI-based Framework for SQL Query Performance Optimization Recommendation. 2026; 22(2), 165-177. Available from: doi:10.29056/jsf.2026.06.15
Ok-Joo Choi and Won Sun Shin. "An Explainable AI-based Framework for SQL Query Performance Optimization Recommendation" Journal of Software Forensics 22, no.2 (2026) : 165-177.doi: 10.29056/jsf.2026.06.15
