91��Ƭ�S�ϼ�

SMU Lyle School of Engineering faculty members Dr. Miju Ahn and Dr. Harsha Gangammanavar from the Department of Operations Research and Engineering Management have received a grant to integrate machine learning and optimization more effectively within the realm of data science.

By leveraging mathematical optimization models, machine learning methods, and extensive datasets, researchers and practitioners have enhanced the ability to make informed decisions. However, a crucial aspect of this process—accurately estimating model parameters—has revealed notable gaps that this research project aims to address.

“The evolution of data science is ongoing, and the convergence of machine learning and optimization not only enhances decision-making but also paves the way for innovative solutions to complex problems,” said Dr. Gangammanavar. “We hope to gain valuable insights and methodologies that will contribute to the field's growth, demonstrating the importance of interdisciplinary collaboration in addressing modern challenges.”

The decision-making process typically involves formulating a model based on historical data, estimating its parameters, and then using optimization techniques to derive the best possible decision. Traditionally, machine learning has been employed to predict these parameters from past records. While this approach has demonstrated promising results in simulations, it often leads to suboptimal outcomes. This is primarily because the performance of machine learning models is assessed based on prediction errors, which do not necessarily align with the effectiveness of the decisions generated by the optimization framework.

The main objectives of the research are to design innovative loss functions that better capture the value of decisions, develop tractable reformulations of optimization models, and apply large-scale computational algorithms to solve these challenges efficiently. By focusing on three distinct types of loss—prescription value, prescription optimality, and first-order conditions—this research will relax existing assumptions about machine learning models and their mathematical properties.

Undergraduate and graduate students will gain hands-on experience by collaborating on projects that validate the proposed methods against complex interdisciplinary challenges in data science. The partnership with the US National Science Foundation's Institute for Foundations of Data Science will provide additional support, including guidance on course design and the development of educational materials.

“By improving decision-making processes in various fields—ranging from finance and healthcare to logistics and environmental science—this project has the potential to drive significant advancements in operational efficiency and effectiveness,” said Dr. Ahn.

About the Bobby B. Lyle School of Engineering
SMU's Lyle School of Engineering thrives on innovation that transcends traditional boundaries. We strongly believe in the power of externally funded, industry-supported research to drive progress and provide exceptional students with valuable industry insights. Our mission is to lead the way in digital transformation within engineering education, all while ensuring that every student graduates as a confident leader. Founded in 1925, SMU Lyle is one of the oldest engineering schools in the Southwest, offering undergraduate and graduate programs, including master's and doctoral degrees.

About SMU 
SMU is the nationally ranked global research university in the dynamic city of Dallas. SMU’s alumni, faculty and nearly 12,000 students in eight degree-granting schools demonstrate an entrepreneurial spirit as they lead change in their professions, community and the world.