Yu Jeffrey Hu

Yu Jeffrey Hu

Auto-generated profile, based on publicly available information

Yu Jeffrey Hu

Maastricht University Purdue University

Research Focus & Metrics

Academic Career Length

18Years (2009-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
20 July 2009 in Economic Inquiry
Verified
Journal Article
Closed access
PDF file
DSDuncan Simester
Duncan Simester
YHYu (Jeffrey) Hu
Yu (Jeffrey) Hu
EBErik Brynjolfsson
Erik Brynjolfsson
EAEric T. Anderson
Eric T. Anderson

19 November 2023 in arXiv
Verified
Preprint
Open access
PDF file
RZRuiqi Rich Zhu
Ruiqi Rich Zhu
CHCheng He
Cheng He
YHYu Jeffrey Hu
Yu Jeffrey Hu
Despite the popularity of product recommendations on online investment platforms, few studies have explored their impact on investor behaviors. Using data from a global e-commerce platform, we apply regression discontinuity design to causally examine the effects of product recommendations on online investors' mutual fund investments. Our findings indicate that recommended funds experience a significant rise in purchases, especially among low socioeconomic status investors who are most influenced by these recommendations. However, investors tend to suffer significantly worse investment returns after purchasing recommended funds, and this negative impact is also most significant for investors with low socioeconomic status. To explain this disparity, we find investors tend to gather less information and expend reduced effort in fund research when buying recommended funds. Furthermore, investors' redemption timing of recommended funds is less optimal than non-recommended funds. We also find that recommended funds experience a larger return reversal than non-recommended funds. In conclusion, product recommendations make investors behave more irrationally and these negative consequences are most significant for investors with low socioeconomic status, which can amplify wealth inequality among investors in financial markets.

23 April 2025 in arXiv
Verified
Preprint
Open access
PDF file
YHYu Jeffrey Hu
Yu Jeffrey Hu
JRJeroen Rombouts
Jeroen Rombouts
IWInes Wilms
Ines Wilms
Machine learning models are widely recognized for their strong performance in forecasting. To keep that performance in streaming data settings, they have to be monitored and frequently re-trained. This can be done with machine learning operations (MLOps) techniques under supervision of an MLOps engineer. However, in digital platform settings where the number of data streams is typically large and unstable, standard monitoring becomes either suboptimal or too labor intensive for the MLOps engineer. As a consequence, companies often fall back on very simple worse performing ML models without monitoring. We solve this problem by adopting a design science approach and introducing a new monitoring framework, the Machine Learning Monitoring Agent (MLMA), that is designed to work at scale for any ML model with reasonable labor cost. A key feature of our framework concerns test-based automated re-training based on a data-adaptive reference loss batch. The MLOps engineer is kept in the loop via key metrics and also acts, pro-actively or retrospectively, to maintain performance of the ML model in the production stage. We conduct a large-scale test at a last-mile delivery platform to empirically validate our monitoring framework.