--- Academic Activities
An On-line Machine Learning Return Prediction, Pacific-Basin Finance Journal 79, 2023, 102049
with Weidong Tian
INFORMS Seth Bonder Foundation Ph.D. Grant (2020)
Abstract: This paper introduces a novel methodology for predicting relative asset returns using a large dataset. Our approach utilizes on-line universal portfolio construction and generates a closed-form prediction formula based solely on historical data. Our results demonstrate that the predictive error can be as low as 2% and is robust. These findings suggest that on-line machine learning techniques have the potential to predict relative asset returns when sufficient data is available.
Addressing Systemic Risk Using Contingent Convertible Debt - A Network Analysis, European Journal of Operational Research 290(1), 2021, 263--277
with Aparna Gupta and Runzu Wang
FMA Best Paper Award in Derivatives & Options (2018), INFORMS Best Student Paper Award Finalist (2018), Global Association of Risk Professionals Research Fellowship (2017)
Abstract: We construct a balance sheet network model to study the interconnectedness of a banking system. A simulation analysis of the buffer effect of contingent convertible (CoCo) debt in controlling contagion in a theoretical banking network model is followed by calibrating the model using 13F filings. We find that CoCo debt conversion significantly mitigates systemic risk, with a dual-trigger CoCo debt design being more effective in protecting the surviving banks. A two-tranche CoCo debt design combines the benefits of single and dual-trigger CoCo debt. The trade-offs in different designs of CoCo triggers can be evaluated in a network simulation model, as developed in this work.
Macroeconomic Trends and Equity Risk Premium Forecast (with Yufeng Han and Guofu Zhou) (current Version: March, 2023)
Presentations: 2022 FMA, 2022 FMA Doctoral Consortium, 2022 International Symposium on Forecasting
Abstract: We present the first evidence on how macroeconomic trends affect equity risk premium, going beyond the literature that rely on only the most recent values. Our results show that macro trends are important, and they contribute statistically and economically to the out-of-sample aggregate market return predictability. Moreover, we present novel evidence that nonlinearity matters in market return predictability by combining macro trends with neural networks, yielding an out-of-sample R2 OS statistic as high as 1.6%. We find that pooling time-series trends helps to track more closely the important macroeconomic fluctuations and to regulate more effectively the forecast variability, thereby generating superior and robust forecasting gains consistently over time.
[NEW] Market Risk Premium Expectation: Combining Option Theory with Traditional Predictors (with Hong Liu, Weike Xu and Guofu Zhou) (current Version: March, 2023)
Presentations: 2024 AFA (to be presented), WashU Brownbag
Abstract: The market risk premium is central in finance, and has been analyzed by numerous studies in the time-series predictability literature and by growing studies in the options literature. In this paper, we provide a novel link between the two literatures. Theoretically, we derive a lower bound on the market risk premium in terms of option prices and state variables. Empirically, we show that combining information from both options and investor sentiment significantly improves the out-of-sample predictability of the market risk premium versus using either type of information alone, and that adding an economic upper bound raises predictability further.
Equity Forward Return from Derivatives (with Weidong Tian and Steven P. Clark) (current Version: January, 2023)
Presentations: 2022 FMA, 2021 CICF (China International Conference in Finance), 2022 AFA, The 4th Derivatives Youth Forum
Abstract: This paper develops a theory of forward returns for an equity index. We obtain the forward returns using information from derivatives markets, including index option prices and gammas, VIX-futures, and prices of VIX-options. We document a pro-cyclical term structure of S&P500 forward returns and a robust short-term reversal pattern. Moreover, by designing and implementing a market-timing strategy, we demonstrate that forward equity returns provide real-time trading signals with substantial economic value.
Mispricing and Anomalies: An Exogenous Shock to Short Selling from JGTRRA (with Yufeng Han, Weike Xu and Guofu Zhou) (current Version: April, 2023)
Presentations: 2022 CICF, 2021 SFS Cavalcade North America, 2021 AFA, 2021 MFA, 2021 FMA
Abstract: Whether anomalies are due to mispricing or risk is an important question. We study the causal effect of short-sale constraints on anomalies by examining an extensive set of 182 anomalies documented in the accounting, finance and economics literature. Our identification strategy relies on a persistent, robust and plausibly exogenous shock to short-selling supply induced by the dividend tax law change in the Job and Growth Tax Relief Reconciliation Act (JGTRRA) of 2003. We find that anomalies become stronger following the dividend record months, driven by stronger overpricing as opposed to underpricing in the post-JGTRRA periods. Interestingly, while the shock magnifies returns to most anomaly types, we find that valuation anomalies seem unlikely to be driven by mispricing.