Blog
Algorithm-driven Personalization and Digital Addiction--A Field Experiment on Tiktok (Douyin)
Abstract: This paper investigates how the short-video platforms affect users through a field experiment on Douyin (the Chinese Tiktok). We incentivized the participants to deactivate the personalization system or stop using Douyin for four weeks. Relative to the control, the no personalization group significantly reduces Douyin usage after the intervention and reports higher work/study efficiency as well as more negative attitude toward Douyin. The intervention causes no significant change ...
Trust and Trustworthiness--Experiments with Artificial Intelligence (AI) Agents
Abstract: The trust game, a simple two-person economic exchange, has been extensively used as experimental measures for trust and trustworthiness of individuals. Here, we develop deep neural network-based artificial intelligence (AI) agents to participate a series of experiments based upon the trust game. These artificial agents are trained by playing with one another without any prior knowledge or assumption regarding trust. We find that artificial agents can mimic trusting and trustworthy...
The Value of Auto-Replenishment--Evidence from a Field Experiment
Abstract: Many firms leverage data-driven algorithms to aid operational decision-making and meanwhile allow managers’ discretion to override the algorithmic recommendations. However, this practice may introduce managers’ non-compliance with algorithmic recommendations due to their behavioral biases. In this study, we study the impact of the auto-replenishment system on store managers’ ordering behavior and the resulting inventory performance. We find the managers may not comply with the alg...
Identification and Estimation of Long-term Treatment Effects via Data Combination
Abstract: In this talk, I will talk about the problem of identifying and estimating the treatment effect of a certain intervention (e.g., new product design or new therapy) on some long-term outcome of interest (e.g., users’ long-term satisfaction or patients’ long-term health). This problem is very challenging: randomized experiments are often expensive and have short durations, so long-term outcome observations may not be available; observational studies can be cheaper and more likely to ...
Abstract: Problem definition: We study the joint optimization policy for electricity merchants with both energy storage and renewable power plants. We also identify the conditions when it is beneficial for the merchant to let independent system operators (ISOs) dispatch her energy storage directly. Methodology: We approximate market impact via a linear function of the electricity traded by the merchant, and employ dynamic programming, adaptive decisions making (ADM) based on rolling price ...
Does Blockchain Facilitate Responsible Sourcing? An Application to the Diamond Supply Chain
Abstract: Problem definition: Blockchain technology has become widely accepted to demonstrate the provenance of physical goods, but there are open questions about its practical implementation and overall effect on ethical sourcing. In the diamond industry, blockchain enables credibility of the certificate of origin and therefore, allows to charge a premium for responsibly produced goods. Thus, one would expect blockchain to be the enabler of responsible sourcing. But does blockchain provide...
Is That Decision Fair? A Formal Model to Assess an Individual's Belief on the Fairness of a Decision
Abstract: The concept of fairness has been addressed by many disciplines on various dimensions, including determining how individuals react under various scenarios, the fair distribution of resources, and designing intelligent systems that make fair decisions. However, prior studies have not attempted to formally represent individuals’ view of a fair decision mathematically nor determined how to represent the degree to which a decision is viewed as fair by individuals. Based on the concept ...
Abstract: Crowding in the emergency department (ED) has been a significant and growing problem for the hospitals in the United States and around the world. In recent years, the full capacity protocol (FCP), a set of hospital-wide guidelines to alleviate ED crowding, has seen rather wide adoption as an intervention to ease crowding and access block in the ED. Yet, academic literature evaluating its effectiveness is sparse. Using the data from an ED of a large urban teaching hospital in the U...