photo
Wangsheng Zhu
Welcome to my website!
Hi, I am Wangsheng Zhu (朱旺盛 in Chinese). I am an assistant professor in the Department of Information Systems, Business Statistics and Operations Management (ISOM) at the Business School, Hong Kong University of Science and Technology (HKUST). I received my B.S. and M.S. from Renmin University of China and received my Ph.D. from University of Texas at Dallas.
Download CV:
Social Media:
Email: wangshengzhu@ust.hk

About Me

  Work

Assistant Professor, July 2024 ~

Department of Information Systems, Business Statistics and Operations Management (ISOM), the Business School, Hong Kong University of Science and Technology, Hong Kong, China

 

Education

Ph.D. in Management Science, 2024

Naveen Jindal School of Management, University of Texas at Dallas, Texas, US

Dissertation committee: Vijay Mookerjee (co-chair), Subodha Kumar (co-chair), Shaojie Tang, Ayvaci Mehmet

M.S. in Management Science, 2018

Renmin Business School, Renmin University of China, Beijing, China

Advisor: Kanliang Wang

B.S. in Management Science, 2018

Renmin Business School, Renmin University of China, Beijing, China

Advisor: Ping Li

 

Skills

Python

95%

Matlab

85%

Java

95%

R

85%

SQL

90%

Research

* updated at April 2024.   ** click the research interest to filter the projects.   *** click the project title to expand the project details.
Research Interests
Topics:  
 Reinforcement Learning  
 Prescriptive Anaytics  
 Digital Advertising  
 Recommender System
Methods:  
 Structural modeling  
 Control Theory  
 Mechanism design  
 Machine learning  
[Reset to All]
 Publication
Coordination in Multibrand Multichannel Advertising: Is it Always a Good Thing?
Wangsheng Zhu, Subodha Kumar, and Vijay Mookerjee Information Systems Research [link]
Abstract: The growing online retail market has led to the prevalence of multichannel retailing. Meanwhile, retailers are increasingly combining multichannel retailing with a multibranding strategy. While this can further increase the retailer's sales, it brings new advertising challenges. Multibrand, multichannel retailers usually launch advertising campaigns for different brands on multiple media. Thus, the retailer's advertising efforts fall into a set of brand-media units. Each unit's advertising efforts can affect the sales of all brands on all channels. Therefore, retailers need to coordinate the advertising efforts of different units to maximize advertising efficiency in propelling sales. So far, the optimization problem of multibrand, multimedia advertising has not been analyzed in the literature, and our study aims to bridge this gap. We develop a stochastic differential equation model to estimate the impact of multimedia advertising on sales in a multibrand, multichannel context. Using the data from a jewelry retailer in the U.S., we show that our model is effective in predicting future sales driven by advertising. Afterward, we formulate the advertising optimization problems under four coordination strategies: (i) non-coordination, (ii) brand coordination, (iii) media coordination, and (iv) global coordination. By solving the problem for each strategy, the retailers can obtain the optimal expenditure for each unit under that strategy. Finally, we compare the retailer’s profits under four strategies. Interestingly, we find that brand or media coordination may result in a profit lower than non-coordination. Our findings provide insights regarding the selection of coordination strategies for multibrand, multichannel retailers with multimedia advertising campaigns, especially when they cannot do global coordination.
Keywords: multibrand retailer, multichannel retailer, multimedia advertising, advertising optimization, advertising coordination, stochastic differential equations
 Working Paper
Should Ad-Exchanges Subsidize the Acquisition of Targeting Data in Ad Auctions?
Wangsheng Zhu, Shaojie Tang, and Vijay Mookerjee Major Revision, ISR
Abstract: Large volumes of online impressions are sold daily via real-time auctions to deliver targeted ads to consumers. Advertisers use data to learn about user preferences and select the most appropriate ad for each user, which also helps them optimize their bids in an ad auction. While ad exchanges may provide some user data to advertisers, it is usually limited, and advertisers often acquire data from various sources to improve targeting performance. The acquisition of such data can significantly influence the revenue of the ad exchange, which has mainly been passive about advertisers' data acquisition process. Previous studies have examined the impact of ad exchanges revealing their data to advertisers, but little attention has been paid to the active role that ad exchanges can play when advertisers acquire data themselves. To address this gap, we propose three subsidy frameworks to increase ad exchange revenue by inducing more advertisers to acquire data: All-subsidized (AS), Winner-subsidized (WS), and Loser-subsidized (LS). Using a stylized game-theoretic model, we analyze the impact of subsidy provisions on the platform's net revenue. Our results show that WS can be better or worse than AS, depending on the cost of data acquisition, its beneficial impact on ad selection, and how impression value is distributed. We also consider an extension of our model wherein advertisers have heterogeneous abilities to leverage data for targeting and analyze how this heterogeneity affects the platform's revenue under the optimal subsidy framework.
Keywords: targeted advertising, ad auctions, targeting data acquisition, subsidy frameworks
A Recommendation Framework for Crowdsourcing Contest Design
Wangsheng Zhu, Jiahui Mo, Syam Menon, and Sumit Sarkar Under Review, Management Science
Abstract: Crowdsourcing contests are popular mechanisms for firms to obtain solutions to tasks from external sources. Platforms allow firms to select from various features they make available, in addition to setting essential contest attributes like prize amounts and duration. The combination of features selected when posting a contest can have a significant impact on the probability that it will succeed in attracting acceptable solutions. This study develops a framework that first identifies an effective prediction model, and then incorporates it into an optimization model to maximize the predicted probability that a crowdsourcing contest will succeed. Since the outcome of a contest depends not just on its own design but also on the other contests on the platform, we consider both contest and environmental attributes as inputs to the prediction model, while allowing for interactions among them. Motivated by practices commonly observed on such platforms, we formulate several versions of the contest design problem as variants of the mixed linear and nonlinear knapsack problems. We identify useful analytical properties that help interpret the optimal solution (and thereby, the basis for making the recommendation), and propose solution procedures. We validate our framework using data collected from a leading crowdsourcing contest platform. The results from computational experiments leveraging our findings show that the contest designs recommended by the proposed framework can increase predicted success probabilities significantly relative to seeker-specified designs.
Keywords: success probability, prediction, optimization, mixed knapsack problem, predict-then-optimize
 Work-in-progress
Managing Ad Campaigns on Digital Billboards under Supply Disruptions
Wangsheng Zhu, Shaojie Tang, and Vijay Mookerjee Work-in-progress
Abstract: The digitization of billboards has facilitated the sale of advertising slots through real-time auctions. Consequently, there has been a rise in the number of agents who assist advertisers in bidding and acquiring these slots. These agents enter into contracts with advertisers to secure a specific number of slots within designated time periods. To fulfill these contracts, agents participate in auctions to win the desired slots. However, accepting numerous contracts may require the agent to place higher bids in auctions, potentially impacting their profitability. Therefore, it is crucial to strike a balance between contract acceptance and the bidding strategy employed.
Motivated by these observations, we address two key aspects: (1) identifying the optimal set of advertisers for the agent to contract with, and (2) determining the appropriate bidding strategy based on the contracted advertisers' demands. We formulate a two-stage optimization problem for agents, followed by the proposal of a near-optimal solution to the bidding optimization problem. Through this near-optimal solution, we demonstrate that the objective function in the resulting advertiser selection problem exhibits the properties of a submodular set function. To solve the advertiser selection problem, we introduce a greedy algorithm.
Keywords: digital billboard, advertiser selection, bidding strategy
Recommendation System for Designing Customized Tours
Wangsheng Zhu, Syam Menon, and Sumit Sarkar Work-in-progress
Abstract:
Keywords:
When should ad-exchanges release user information to advertisers
Wangsheng Zhu, Shaojie Tang, and Vijay Mookerje Work-in-progress
Abstract:
Keywords:
Use Reinforcement Learning for Strcutural Model Identification
Kai Sun, Wangsheng Zhu, and Vijay MookerjeWork-in-progress
Abstract:
Keywords:

Teaching

Introduction to Programming
Naveen Jindal School of Management, University of Texas at DallasFall 2021, Fall 2022
Using the language Java, this course covers fundamental programming concepts including data types, control structures (selections, loops, and methods), objects, classes, iterations, functions, and arrays. Besides, students will learn the mechanics of running, testing, and debugging programs.
Object-oriented Programming with Python
Naveen Jindal School of Management, University of Texas at DallasSpring 2023
This course covers (1) object declaration and inheritance, (2) object-oriented programming (OOP) thinking, (3) exception handling, (4) file input and output, and (5) graphical user interface (GUI).

Awards and Honors

Dean's Excellence Scholarship
Naveen Jindal School of Management, University of Texas at Dallas2023
First-class Scholarship of Outstanding Academic Performance
Renmin Business School, Renmin University of China2016
Second-class Scholarship of Outstanding Academic Performance
Renmin Business School, Renmin University of China2015
Outstanding Bachelor Thesis Award
Renmin Business School, Renmin University of China2015
RUC Scholarship of Outstanding Academic Performance
Renmin Business School, Renmin University of China2014
RUC Scholarship of Outstanding Academic Performance
Renmin Business School, Renmin University of China2012

Miscellaneous

photo
photo

Blog

I do not know what I will write here.

photo
photo

Gallery

Unforgettable moments in my life

photo
photo

Footprint

A record of the cities I have been to before