Jingtong Zhao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Jingtong Zhao has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Jie Song
Peking University
5 shared publications - Ziwei Wang
Peking University
5 shared publications - Hanqi Wen
Department of Industrial Engineering and Management, College of Engineering, Peking University, Beijing, China
2 shared publications Jie Song
2 shared publicationsYixuan Liu
2 shared publications- Andrew A. Li
Tepper School of Business, Carnegie Mellon University, Pittsburgh, Pennsylvania 15213
1 shared publication
Latest Publications
- 22 September 2025
- Published by Elsevier in European Journal of Operational Research
- Vol. 331 (1) , 186-199
Reinforcement learning algorithm for reusable resource allocation with unknown rental time distribution
- 22 September 2025
- Published by Elsevier in European Journal of Operational Research
- Vol. 331 (1) , 186-199
Reinforcement learning algorithm for reusable resource allocation with unknown rental time distribution
- 16 November 2024
- Published by Elsevier in Information Sciences
- Vol. 693
Intelligent influencer selection in social networks for product promotions with crowd effect
- 16 November 2024
- Published by Elsevier in Information Sciences
- Vol. 693
Intelligent influencer selection in social networks for product promotions with crowd effect
- Open Access
- 1 January 2024
- Published by Elsevier in SSRN Electronic Journal
Reinforcement Learning Algorithm for Reusable Resource Allocation with Time-varying Reward
We explore a scenario where a platform must decide on the price and type of reusable resources for sequentially arriving customers. The product is rented for a random period, during which the platform also extracts rewards based on a prearranged agreement. The expected reward varies during the usage time, and the platform aims to maximize revenue over a finite horizon. Two primary challenges are encountered: the stochastic usage time introduces uncertainty, affecting product availability, and the platform lacks initial knowledge about reward and usage time distributions. In contrast to conventional online learning, where usage time distributions are parametric, our problem allows for unknown distribution types. To overcome these challenges, we formulate the problem as a Markov Decision Process and model the usage time distribution using a hazard rate. We first introduce an offline allocation method with a performance guarantee and then develop a reinforcement learning algorithm to address the cold start problem, accommodating non-parametric distributions and time-varying rewards. We further prove that the algorithm achieves sublinear regret against the offline benchmark. Numerical experiments on synthetic data demonstrate the superiority of our method over other benchmark policies.
- 1 January 2024
- Published by Elsevier in SSRN Electronic Journal
Open AccessReinforcement Learning Algorithm for Reusable Resource Allocation with Time-varying Reward
We explore a scenario where a platform must decide on the price and type of reusable resources for sequentially arriving customers. The product is rented for a random period, during which the platform also extracts rewards based on a prearranged agreement. The expected reward varies during the usage time, and the platform aims to maximize revenue over a finite horizon. Two primary challenges are encountered: the stochastic usage time introduces uncertainty, affecting product availability, and the platform lacks initial knowledge about reward and usage time distributions. In contrast to conventional online learning, where usage time distributions are parametric, our problem allows for unknown distribution types. To overcome these challenges, we formulate the problem as a Markov Decision Process and model the usage time distribution using a hazard rate. We first introduce an offline allocation method with a performance guarantee and then develop a reinforcement learning algorithm to address the cold start problem, accommodating non-parametric distributions and time-varying rewards. We further prove that the algorithm achieves sublinear regret against the offline benchmark. Numerical experiments on synthetic data demonstrate the superiority of our method over other benchmark policies.
- 7 December 2023
- Published by Taylor & Francis in IISE Transactions
- Vol. 57 (1) , 16-29
Ranking and pricing under a cascade model of consumer review browsing
- 7 December 2023
- Published by Taylor & Francis in IISE Transactions
- Vol. 57 (1) , 16-29
Ranking and pricing under a cascade model of consumer review browsing
- 28 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Engineering Management
- Vol. 71 (00189391) , 1613-1628
Enhancing Product Promotion in Social Networks: Leveraging Adaptive Discount-Offering and the Crowd Effect
Product promotion on social media platforms has revolutionized advertising, with the crowd effect playing a crucial role. This effect capitalizes on individuals’ exposure to product opinions shared online. People are more likely to make purchases when they see others endorsing the product through likes and positive feedback. In our study, we integrate this crowd effect into our modeling of information diffusion on social networks. Our goal is to optimize influence through adaptive discount offering to prospective customers. To achieve this, we develop a model based on two widely used diffusion models, namely the independent cascade and linear threshold models. We formulate our decision problem as a Markov decision process. Then, we demonstrate that our problem does not satisfy the adaptive submodular property due to an additional global state variable, rendering the greedy policy suboptimal without performance guarantees. To tackle this challenge, we propose a rolling horizon method with fluid approximation, utilizing an offline upper bound to guide our online decision-making process. We also conduct numerical experiments to evaluate our method on random and real networks. Our method outperforms benchmark methods by a significant margin, achieving up to double the performance on random graphs and up to 63.12% improvement on real networks.
- 28 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Engineering Management
- Vol. 71 (00189391) , 1613-1628
Enhancing Product Promotion in Social Networks: Leveraging Adaptive Discount-Offering and the Crowd Effect
Product promotion on social media platforms has revolutionized advertising, with the crowd effect playing a crucial role. This effect capitalizes on individuals’ exposure to product opinions shared online. People are more likely to make purchases when they see others endorsing the product through likes and positive feedback. In our study, we integrate this crowd effect into our modeling of information diffusion on social networks. Our goal is to optimize influence through adaptive discount offering to prospective customers. To achieve this, we develop a model based on two widely used diffusion models, namely the independent cascade and linear threshold models. We formulate our decision problem as a Markov decision process. Then, we demonstrate that our problem does not satisfy the adaptive submodular property due to an additional global state variable, rendering the greedy policy suboptimal without performance guarantees. To tackle this challenge, we propose a rolling horizon method with fluid approximation, utilizing an offline upper bound to guide our online decision-making process. We also conduct numerical experiments to evaluate our method on random and real networks. Our method outperforms benchmark methods by a significant margin, achieving up to double the performance on random graphs and up to 63.12% improvement on real networks.
- 13 July 2023
- Published by Taylor & Francis in IISE Transactions
- Vol. 56 (4) , 471-484
Dynamic expansions of social followings with lotteries and give-aways
- 13 July 2023
- Published by Taylor & Francis in IISE Transactions
- Vol. 56 (4) , 471-484
Dynamic expansions of social followings with lotteries and give-aways
- 11 December 2022
- Published by Springer Nature
- p. 217-234
Dynamic Ranking of Physicians in Online Healthcare Platforms with Multiple Service Types
- 11 December 2022
- Published by Springer Nature
- p. 217-234
Dynamic Ranking of Physicians in Online Healthcare Platforms with Multiple Service Types
- 20 March 2021
- Published by Springer Nature in Flexible Services and Manufacturing Journal
- Vol. 34 (4) , 859-878
Dynamic planning with reusable healthcare resources: application to appointment scheduling
- 20 March 2021
- Published by Springer Nature in Flexible Services and Manufacturing Journal
- Vol. 34 (4) , 859-878
Dynamic planning with reusable healthcare resources: application to appointment scheduling
- 8 March 2021
- Published by Springer Nature in Journal of Systems Science and Systems Engineering
- Vol. 30 (3) , 276-287
Synergy between Customer Segmentation and Personalization
- 8 March 2021
- Published by Springer Nature in Journal of Systems Science and Systems Engineering
- Vol. 30 (3) , 276-287
Synergy between Customer Segmentation and Personalization
- 9 December 2015
- Published by Cambridge University Press (CUP) in Probability in the Engineering and Informational Sciences
- Vol. 30 (2) , 185-211
STAFFING TO STABILIZE BLOCKING IN LOSS MODELS WITH TIME-VARYING ARRIVAL RATES
The modified-offered-load approximation can be used to choose a staffing function (the time-varying number of servers) to stabilize delay probabilities at target levels in multi-server delay models with time-varying arrival rates, with or without customer abandonment. In contrast, as we confirm with simulations, it is not possible to stabilize blocking probabilities to the same extent in corresponding loss models, without extra waiting space, because these probabilities necessarily change dramatically after each staffing change. Nevertheless, blocking probabilities can be stabilized provided that we either randomize the times of staffing changes or average the blocking probabilities over a suitably small time interval. We develop systematic procedures and study how to choose the averaging parameters.
- 9 December 2015
- Published by Cambridge University Press (CUP) in Probability in the Engineering and Informational Sciences
- Vol. 30 (2) , 185-211
STAFFING TO STABILIZE BLOCKING IN LOSS MODELS WITH TIME-VARYING ARRIVAL RATES
The modified-offered-load approximation can be used to choose a staffing function (the time-varying number of servers) to stabilize delay probabilities at target levels in multi-server delay models with time-varying arrival rates, with or without customer abandonment. In contrast, as we confirm with simulations, it is not possible to stabilize blocking probabilities to the same extent in corresponding loss models, without extra waiting space, because these probabilities necessarily change dramatically after each staffing change. Nevertheless, blocking probabilities can be stabilized provided that we either randomize the times of staffing changes or average the blocking probabilities over a suitably small time interval. We develop systematic procedures and study how to choose the averaging parameters.