Ying Yin

I'm a postdoc researcher at Rotterdam School of Management in the Netherlands, within the Technology and Operations Management Department. My research is part of the AI in Port Catalyzer project, where I work on topics related to AI-enabled terminal decision support systems.

Prior to my postdoc, I started my PhD from Leiden University, focusing on capacity planning, trust, and contracting in platform-based economies. There, I am currently completing my PhD under the supervision of Prof. dr. S. Jong Kon Chin, Prof. dr. R.A. Zuidwijk, and Dr. X. Li. My work integrates analytical modeling, experimental methods, and real-world applications.

I am interested in platform economy, and AI-enabled decision support. My research focuses on understanding and optimizing complex service systems by combining analytical modeling and behavioral insights.

E-mail  /  CV  /  Google Scholar /  LinkedIn

Research

We develop a game-theoretical model of platform–supplier contracting that incorporates trust and fairness under different information- and revenue-sharing structures. We characterize the optimal contracts and show how trustworthiness and fairness concern shape outcomes, revealing conditions that lead to compliance or fairness-driven opportunism.

We propose a two-step lifecycle forecasting approach for consumer technology products with limited early-stage sales data, combining product clustering and aggregated Bass model estimation. Using real-world data from Philips, we show that aggregation significantly improves forecast accuracy for new products.

We develop a V2G power dispatching model integrated with a revenue-sharing contract to coordinate stakeholders in an urban microgrid. Using real and synthetic data from CAR2GO in Amsterdam, we show the policy improves aggregator cost efficiency, user revenue, and environmental outcomes while enabling trade-offs between revenue sharing and operational performance.

We design a classroom decision lab to teach personalized platform–supplier contracting through experiential learning, incorporating trust, fairness, and behavioral factors into students’ decision-making tasks. Through iterative implementation and refinement, we show that integrating analytical benchmarks and structured debriefing significantly improves students’ ability to apply theory in practice.

We develop a two-stage mixed-integer optimization model that integrates demand response into shared electric vehicle planning, jointly addressing charging facility location and vehicle relocation under supply and demand uncertainty. Using a real-world case study in Amsterdam, we show that demand response improves operational efficiency and grid reliability, highlighting trade-offs between cost, data availability, and charging technology performance.

Academic activities

My academic journey