Published in IEEE Transactions on Semiconductor Manufacturing, 2021

Industrial application of Bayesian optimization resulting in significant yield improvements and cost reductions in semiconductor manufacturing through intelligent process parameter optimization.

Advanced frameworks for automated machine learning pipeline optimization, reducing manual tuning effort while improving model performance across diverse applications.

Development of probabilistic methods for reliability assessment and risk quantification in complex engineering applications, enabling safer and more robust system design.

End-to-end machine learning solutions for industrial forecasting, maintenance scheduling, and resource optimization, deployed in real-world manufacturing environments.

Collaboration with MIT on advanced manufacturing optimization, developing AI-driven solutions for process control and quality assurance in industrial settings.

Built predictive models for Samsung business units to optimize sales campaigns and forecast revenue, incorporating market dynamics and customer behavior analysis.

Bayesian machine learning solutions for supply chain management, including demand forecasting, inventory optimization, and logistics planning.