Research Interests
Field
Quantitative Marketing
Topics
Marketing Methodology, Innovation and Creativity, Targeting, Incentive Design,
Marketing and Society
Marketing and Society
Methods
Active Learning, Machine Learning, Game Theory, Causal Inference
Research Projects
Targeted Marketing with Large Batches
Joint work with Duncan Simester
ASA Statistics in Marketing Doctoral Dissertation Research Award, Finalist
► Show Abstract
Adaptive learning policies that guide how firms trade off acquiring new information to improve a current targeting policy, versus exploiting the current policy to harvest, typically focus on settings in which customers arrive individually, in a frequent sequence. However, in practice, firms often conduct marketing campaigns in batches, in which they target a large group of customers with personalized marketing actions together. This has an important implication for how firms resolve the tradeoff between acquiring new information and exploiting the current policy. The large number of customers in each batch (campaign) introduces an information externality: the incremental information contributed by a single customer depends upon the assignment decisions for other customers in the batch. We investigate how to optimally acquire and coordinate information in these settings. The algorithm we propose uses Gaussian Processes to estimate the value of incremental information, while accounting for the information externality between customers in the same batch. We validate our findings using data from a field experiment.
When Customer Search Stifles Product Innovations
► Show Abstract
Conventional wisdom suggests that when an incumbent fails to innovate, there is a greater risk to the incumbent of competition from other innovators. I show conditions in which the opposite is true: by delaying innovation, an incumbent can create entry barriers that deter innovation by competitors. Consequently, both competition and innovation are suppressed. The key insight driving these outcomes is that customer search is endogenous, and absence of innovation today can disincentivize customers from searching in the future. Since customers need to search to discover innovations, when they search less, it both creates entry barriers for competitors, and reduces the competitors' incentives to innovate. Postponing innovation can benefit incumbents if it motivates customers to search less, and thus competitors to innovate less. Notably, I show that searching less is a rational customer response.
The Invisible Hand Behind Luxury Consumption in China
Joint work with Liyin Jin, Hongju Liu, Qiaowei Shen, reject and resubmit at Marketing Science
► Show Abstract
This paper studies customer demand in a non-market-oriented economy. The economics and marketing literature has focused on market economies and studies factors such as price and advertising when analyzing customer demand. When it comes to a non-market-oriented economy, social factors like corruption have a significant influence on customer decisions. In particular, the paper's focus is on the demand for luxury products, which are widely used for gift-giving and even bribery in emerging markets. A possible mechanism is that, when the relative size of non-market-oriented sectors in the local economy increases, luxury products can be used to identify those who have a higher willingness-to-pay for (scarce) resources. As a result, the demand for luxury products moves together with the degree of corruption. Leveraging natural experiments of top-down anti-corruption campaigns that put a pause on this channel, an empirical study is performed using a comprehensive data set that covers the sales of all cigarette brands and the local social environment in China. The results suggest that these social factors can have an unanticipated impact on luxury products' demand.
Learning from Rookies
Joint work with Lei Huang, Juanjuan Zhang, Yuting Zhu
► Show Working Abstract
People often learn from experts. In this project, we argue that we can sometimes learn more from rookies than experts. This happens when rookies make uninformed decisions, which renders their actions closer to random trials. The observed relationship between rookies’ actions and outcomes can thus be more causally meaningful. We investigate this possibility in the context of a major content platform, where we study the relationship between content design and content engagement. Preliminary analysis suggests that, consistent with our argument, rookie content predicts disproportionately better out of sample than expert content.