Learning in Dynamic Markets

Adaptive learning and decision-making in dynamic markets

Markets evolve continuously under uncertainty. My research develops learning-based strategies that adapt to changing conditions, imperfect predictions, and delayed or partially observed outcomes.

Applications include real-time bidding in online advertising and pairs trading in financial markets, with an emphasis on robust decisions, structural changes, and efficient use of market feedback.

Keywords

Reinforcement LearningReal-Time BiddingPairs TradingMarket Dynamics

Selected Publications

A Market-Aware Real-Time Bidding Strategy Using Censored Data with Reinforcement Learning in Online Advertising 2025 · IEEE BigData

A Robust Real Time Bidding Strategy Against Inaccurate CTR Predictions by Using Cluster Expected Win Rate 2023 · IEEE Access

Pairs Trading Strategy Optimization Using Proximal Policy Optimization Algorithms 2023 · IEEE BigComp

Structural break-aware pairs trading strategy using deep reinforcement learning 2022 · J. Supercomput.