Ying-Kai Huang


4516 Wesley W. Posvar Hall
Pittsburgh, PA 15260

Research Interest

Financial Forecasting, Applied Econometrics

Job-market Paper

"From Econometrics to Machine Learning: Application of Recurrent Neural Networks on Yield Curve Forecasting"

Financial derivatives and interest rates correlate strongly with United States government bonds. Among many characteristics of government bonds, the term structure or the so-called yield curve is one of the main targets that investors always attempt to forecast. In this paper, I construct a model with autoencoder structures and recurrent neural networks (RNN) and focus on the point forecasting of the yield curve to explore the possibility of having a better forecast for the term structure. In addition, the similarities between RNN and the state-space models allow me to show that the newly proposed neural-network method is closely linked with previous financial econometric forecasting literature and can be considered as a generalization of the dynamic Nelson-Siegel method (Diebold and Li, 2006). While allowing similar interpretation as previous econometric methods, the neural network model in this paper shows better forecasting accuracy.

Other Works

Attribution Bias on Online Reputation Systems
Consumers benefit from reading ratings online before making their purchases, yet this information aggregation process may have some potential problems that were not previously credited in the literature. Through an empirical approach, I show how people could review businesses inconsistently when their expectations are formed by ratings on crowd-sourced review websites. Using data from Yelp, I tested how potential disappointments may affect customers' reviews by applying a regression discontinuity design to control for unobserved factors that may also simultaneously influence ratings. In addition, I developed a model illustrating rating behaviors with reference-dependent utilities to establish testable hypotheses and showed that comparisons between their true experience and expectation, when consumers write their reviews, could impede their assessment of businesses' qualities and cause attribution bias. After carefully excluding confounding factors, my results support the hypothesis that consumers have attribution bias when they write reviews. Several robustness checks support these findings and shed further light onto this example of attribution bias.  This paper links to an emerging literature of attribution bias in economics and provides empirical evidence and implications of attribution bias on online reputation systems.


When Hope Hurts: How Special Occasions Lead to Attribution Bias (Joint with David Min-Heng Wang and Shuyan Zhan)
This paper incorporates computational linguistics and the theories of reference-dependent preferences to test whether consuming in a restaurant on special occasions or special days, such as one's birthday, anniversary, commencement, etc., would increase one's “expectation” and would result in low ratings for consumption experiences. In our study, we analyzed text reviews and conducted a sentiment analysis to capture users' emotions. After controlling for many characteristics of users, we found evidence that an individual's review is not only dependent on what they consume but also how high they set their expectations. 

Job Market Paper Link