Working papers      


New Option Expected Hedging Demand

with Xiaoxiao Tang and Zhaoque (Chosen) Zhou (current Version: Feb., 2024).

The increasing option volume and ratio of option volume to stock volume in recent year indicate that options market makers' delta hedging has a growing impact on underlying stock prices. We introduce a novel approach utilizing real-time options information to calculate the spot elasticity of delta (ED) and expected hedging demand (EHD). Empirical results show that the EHD significantly predicts future stock returns in the cross section and such a positive impact on stock prices lasts up to five trading days and then a reversal follows. The empirical evidence of heterogeneous EHD-return relationship, influenced by ED, leads to varied options market maker behaviors and is consistent with conventional economic theory. Finally, we conclude that EHD has a minimal correlation with other popular firm characteristics.



New ChatGPT, Stock Market Predictability and Links to the Macroeconomy

with Jian Chen, Guohao Tang and Wu Zhu (current Version: December, 2023).

This paper examines whether ChatGPT can identify useful news content for the aggregate stock market and macroeconomy, using the news headlines and alerts on front pages of Wall Street Journal. We find that the information extracted by ChatGPT is highly related to macroeconomic conditions. Investors tend to underreact to the positive contents, especially during periods of economic downturns, high information uncertainty and high novelty of news, which leads to significant market predictability by ChatGPT. By contrast, the negative news is only associated with contemporaneous returns, and it cannot predict future market. Traditional methods of textual analysis, such as word lists or small large language models (LLMs) like BERT, can barely find any predictability in either positive news nor negative news. In short, ChatGPT appears the best of its kind and is capable of discerning economic-related news that drive the stock market.



New Unusual Financial Communication: Evidence from ChatGPT, Earnings Calls, and the Stock Market

with Lars Beckmann, Heiner Beckmeyer, Ilias Filippou, Stefan Menze and Wu Zhu (current Version: January, 2024).

The introduction of ChatGPT has changed how humans process textual data. We devise a prompting strategy for ChatGPT to identify and analyze unusual aspects of financial communication, focusing on earnings calls of S&P 500 firms. Utilizing the latest GPT-4-Turbo model, we identify and categorize unusual financial communication across 25 dimensions, which fall into four categories: unusual communication by executives, by financial analysts, unusual content, and technical issues. A significant portion of earnings calls displays unusual financial communication, which correlates with certain firm characteristics and fluctuates with the business cycles. The stock market reacts negatively to unusual communication, with an elevated trading activity. We highlight the potential of large language models like ChatGPT in financial analyses, offering new insights into the interpretation of complex textual data and its economic consequences on market impacts.



A New Option Momentum: Compensation for Risk

with Heiner Beckmeyer, Ilias Filippou (current Version: Feb., 2024).

We show that option market risk is highly persistent over time and propose a cross-sectional option momentum strategy to exploit this pattern. Our proposed systematic momentum is highly profitable for different formation and holding periods, and it is more profitable than the recently discovered option momentum strategy of Heston, Jones, Khorram, Li, and Mo (2023). We show further that the systematic option momentum is unrelated to standard option momentum, is not subject to crash risk, and does not suffer from long-term reversals. We also examine various components of the risk drivers of the strategy and find that fundamental risks are generally well compensated to those investors who trade on the risk-based momentum.

Best paper award, FMA Asset Mgt Consortium at Cambridge, 2024; to be Presented at Inquire UK-Inquire Europe, 2024.



Market Risk Premium Expectation: Combining Option Theory with Traditional Predictors

with Hong Liu, Yueliang (Jacques) Lu and Weike Xu (current Version: Dec, 2023).

Recently there is a growing literature on predicting the market risk premium from the option market, shedding new insights on the traditional voluminous literature of market predictability that relies on economic state variables. This paper provides a novel link between these literatures. Theoretically, we derive a generalized lower bound on the expected market risk premium that combines both options and state variables. Empirically, we find that the new bound significantly enhances the out-of-sample market predictability compared to using either type of information alone, with gains more pronounced in the short horizons such as one to three months.

Presented at AFA 2024



Maximizing the Sharpe Ratio: A Genetic Programming Approach

with Yang Liu and Yingzi Zhu (current Version: Dec., 2023).

(On-line Appendix)

While existing studies focus on minimizing model errors, we consider maximizing the Sharpe ratio of investing in the usual spread portfolio. In contrast to popular machine learning methods, we find that GP can double their performance in the US, and outperform them internationally, because GP captures nonlinearity in comparison with linear methods like the LASSO and it requires smaller sample size than the nonlinear neural network. We also apply GP to maximize the Sharpe ratio of all the underlying stocks, and find that its value is 60% greater than before, indicating the loss of relying on spread portfolios can be substantial.

Presented at AFA 2024, and at 2021 CICF



New Pockets of Factor Pricing

with Sophia Zhengzi Li and Peixuan Yuan (current Version: December, 2023).

Current factor models assume certain pre-specified factors can price or explain asset returns with the same level of ability across time. In contrast with this conventional wisdom, we find that factor's pricing ability exhibit notable temporal variations, and it tends to cluster in certain periods referred to as "pockets." We propose a real-time approach to effectively identify the pockets, and apply it to a comprehensive set of firm characteristics. We find episodic and distinct dynamics of return predictability for different types of characteristics, contradicting the notion of continuous presence of the same factors with the same pricing ability. Exploiting factor's time-varying predictive power, we construct a composite predictor/factor that achieves a value-weighted hedge return of 3.94% per month with a high t-statistic of 13.87. Additionally, the composite factor pricing model, which incorporates a selection of factors with factor timing, demonstrates superior effectiveness in both explaining and predicting market anomalies. The factor also provides a comprehensive explanation for factor momentum, which is shown a consequence of the past performance of factor returns.



New Did Retail Traders Take Over Wall Street? A Tick-by-Tick Analysis of GameStop's Price Surge

with Zhaoque (Chosen) Zhou (current Version: Oct., 2023).

In January 2021, GameStop experienced an extraordinary surge in its stock price, soaring from $17.25 on January 4 to a pre-market value of $514.50 on January 28. In contrast to previous studies, we use tick-by-tick data of stock and options trading to demonstrate that this remarkable surge come mainly from overnight trading, driven mainly by institutional orders rather than those from retail investors. Although sophisticated option traders typically maintain a positive gamma position, option market makers skillfully regulate their gamma exposure by participating in retail option trades. However, an “after-hours gamma squeeze” was initiated by a twitter catalyst, causing eventually the well-known GameStop short squeeze. We also provide an extended model of Brunnermeier and Pedersen (2005) that explains some of our major findings.



New Expected Index Option Return: What Can We Learn From Macro and Anomalies

with Heiner Beckmeyer and Guoshi Tong (current Version: Jan., 2024).

We provide the first study on whether the expected returns on stock index option is predictable and how, extending the large literature on the predictability of the stock market in a new direction. We find that the stock index option is predictable by common macroeconomic predictors whose predictive power on options is even stronger than on the underlying. We find also that, although stock market inefficiency, as captures by anomalies, explains the future option returns, option market inefficiency plays a greater role. The economic value of incorporating the option predictability versus ignoring it can be substantial.



Risk Momentum: A New Class of Price Patterns

with Sophia Zhengzi Li and Peixuan Yuan (current Version: Oct., 2023).

We uncover a new pattern: the stock risk component exhibits momentum. This risk momentum yields a return momentum: stocks sorted by risk have persistent positive returns. In comparison with the extremely popular and extensively studied Jegadeesh and Titman (1993) momentum sorted by return, which is valid only monthly and only for stocks, our risk-based return momentum holds intraday, daily, weekly, and monthly, and exists for not only stocks, but also for corporate bonds and other asset classes. Furthermore, our risk momentum, the strongest ever discovered, is different from the factor momentum of Ehsani and Linnainmaa (2022) sorted by factor performance.

Presented at MFA 2023, and SFS Cavalcade North America 2023



ETFs, Anomalies and Market Efficiency

with Ilias Filippou, Songrun He, and Sophia Zhengzi Li (current Version: Oct., 2023).

Investigating how ETF ownership impacts anomalies and market efficiency, we find that low ETF ownership stocks yield higher returns, greater Sharpe ratios, and more significant alphas versus high ETF ownership stocks. Moreover, high ETF ownership stocks exhibit more pronounced information flow, reducing mispricing and enhancing efficiency. These findings hold when we match the two groups by characteristics to have similar short-sales constraint, arbitrage costs, and information environment, and remain robust to controlling for those effects in Fama-MacBeth regressions. Using Russell index reconstitution as a natural experiment, we find causal evidence of ETF ownership attenuating anomaly profits.

Presented SGF 2023, and WFA 2023; would have been presented at TAU Finance Conference 2023



Earnings Announcements: Ex-ante Risk Premia

with Hong Liu, Yingdong Mao and Xiaoxiao Tang (current Version: Jan., 2023).

In this paper, we provide an estimate of the ex-ante risk premia on earnings announcements based on the option market. We find that the risk premia are time-varying and have predictive power on future stock returns. The well-documented positive post-earnings-announcement drift (PEAD) is present only when the risk premia are high. After controlling for the announcement risk premia, the PEAD factor of the literature no longer has any abnormal returns. Moreover, while trading option straddles is not profitable in general, its performance improves substantially during announcements with high risk.



No Sparsity in Asset Pricing: Evidence from a Generic Statistical Test

with Junnan He and Lingxiao Zhao (current Version: Feb., 2024).

We provide a generic statistical test to discern whether there is sparsity of in high-dimensional factor models. Applying the test to recent characteristic-based factor models, we find that the null hypothesis of fewer than ten factors capable of explaining the cross-section of stock returns is rejected. Moreover, a dense model representation outperforms sparse models both in pricing in the cross-section and as an investment strategy, which provides an economic explanation for the testing result. Overall, there is no sparsity in asset pricing in the large space of characteristic-based factors.



Useful Factors Are Fewer Than You Think After Accounting for False-Discovery

with Bin Chen and Qiyang Yu (current Version: February, 2024).

We examine how many factors out of a wide range of 207 that have incremental information in explaining cross-sectional stock returns. First, we find that the significance of each factor changes drastically over time. After accounting for false discovery rate (FDR), only 157 out of 207 factors are significant from 1967 to 2021, and only 56 from 2000 to 2021. Second, from 2000 to 2021, we find strikingly that only 3 clusters of factors that have incremental information. We further propose a new flexible time-varying latent factor model, and test in an alternative way on the number of factors that capture the information of the 56 significant factors while controlling for FDR, and find only 3, the market plus 2 latent ones, a number much fewer than widely believed.



Interpretable Factors of Firm Characteristics

with Yuxiao Jiao and Yingzi Zhu (current Version: February, 2024).

We propose a new approach to construct factors from firm characteristics. In contrast to existing studies, each of our factors comes from the same group of statistically related firm characteristics, making its economic interpretation possible. The number of groups is not chosen ad hocly, but rather determined by data. Applying our method to a set of 94 representative firm characteristics, we find that the factors chosen by our approach are not only easy to interpret economically, but they also outperforms typical machine learning models. We also apply our approach to the recent and highly effective IPCA model of Kelly, Pruitt and Su (2019), and find that our factors not only are well linked apparent economic risks, but also can price assets no worse than the standard IPCA model.



How Accurate Are Survey Forecasts on the Market?

with Songrun He and Jiaen Li (current Version: February, 2024).

In this paper, we provide a novel performance analysis of three widely used survey forecasts by investigating how well they predict the stock market. Judging by their out-of-sample $R^2$s, a standard measure in the market predictability literature, we find that none of the survey forecasts outperforms a simple random walk forecast, which predicts the future returns simply by their past sample mean. In addition, we find that the surveys are not very informative about investor's attitudes toward risk. Our study raises important questions on how to safeguard the use of the survey forecasts and how to properly interpret the results from the large literature that relies on the survey forecasts. On the other hand, we show that naive Bayesian macroeconomic learning can outperform the random walk model, suggesting that the expectation of an AI robot can potentially be more important and deserve more attention than the survey forecasts.



Macroeconomic Trends and Equity Risk Premium

with Yufeng Han and Yueliang (Jacques) Lu (current Version: March, 2023).

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 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.



Principal Portfolios: The Multi-Signal Case

with Songrun He and Ming Yuan (current Version: October, 2022).

In this paper, we extend Kelly, Malamud, and Pederson"s (2021) new asset pricing framework to allow incorporating multiple predictive signals into optimal principal portfolios. Empirically, we find that the multi-signal theory is valuable for combining signals, improving a naive combination of single signal principal portfolios.



Anomaly Returns and FOMC

with Lin Tan and Xiaoyan Zhang (current Version: April, 2023).

We find that anomaly returns are generally unchanged during FOMC days. The average return on the long- and short-leg, of a comprehensive set of 207 anomalies, increases by 26.3 bps and 28.8 bps, respectively, prior to the FOMC and reverses back afterwards. But for a small group of anomalies that do have substantial changes, their profitability tends to go down with absolute pricing errors greater than usual. Our evidence challenges existing studies that find the CAPM perform better during the FOMC period. Furthermore, we uncover that the less participation of retail investors contributes to the decline of profitability.

Presented at 2023 CICF



Information Transmission from Corporate Bonds to the Aggregate Stock Market

with Sophia Zhengzi Li and Peixuan Yuan (current Version: February, 2024).

We provide perhaps the first strong empirical evidence that the corporate bond market leads the aggregate stock market: the cross-sectional skewness of the corporate bond returns predict the stock market returns both in- and out-of-sample. The predictability arises from informed bond trading and gradual information diffusion due to market segmentation. Additionally, the bond predictors contain valuable information about future aggregate firm fundamentals and real economic activity. The lead-lag relationship becomes more prominent when the two markets are less integrated. Moreover, the predictive power extends to stock portfolios sorted by size, value, and industries.



Anomalies as New Hedge Fund Factors: A Machine Learning Approach

with Yong Chen, Sophia Zhengzi Li and Yushan Tang (current Version: Feb, 2024).

We identify a parsimonious set of factors from a large set of candidates that can potentially explain hedge fund returns, ranging from equity market factor, anomaly factors, trend-following factors to macroeconomic factors. The resulting nine-factor model, including five anomaly factors, outperforms existing hedge fund models both in-sample and out-of-sample, with a significant reduction in alphas while maintaining substantial cross-sectional performance heterogeneity. Further analysis reveals evidence of strategy shifts by hedge funds over time, making necessary the addition of the anomaly factors. Our results suggest the importance of periodically updating factors for the hedge fund industry.



Unspanned Risk and Risk-Return Tradeoff

with Huacheng Zhang (current Version: Dec, 2023).

A major tenet of modern finance is the risk-return tradeoff, and yet there is a lack of empirical evidence supporting it. We provide an unspanned risk explanation, which, measured as uncertainty beyond financial markets, is well approximated by the macro uncertainty index of Baker, Bloom, and Davis (2016), 90% of which can be attributed to unspanned uncertainty. We find the first out-of-sample evidence that there is a positive risk-return tradeoff after all. In addition, we find that the unspanned risk matters at stock level too: a high-minus-low unspanned risk portfolio can generate an annualized return of 3.5%.



Hide in the Herd: Macroeconomic Uncertainty and Analyst Forecasts Dispersion

with Shen Zhao (current Version: Jan., 2023).

We uncover a negative correlation between macroeconomic uncertainty and security analyst earning forecasts dispersion, and explain it through herding behavior bias of the analysts. We find that the herding firms, whose analysts suffer the herding bias, have greater firm-level uncertainty than non-herding firms. The stock prices of the herding firms have stronger momentum and tend to under-react more to the both firm and macro news. Moreover, the herding firms' stocks are more likely to be overpriced and earn lower subsequent returns. Our study links the interaction between macro-uncertainty and micro-dispersion to the firms' characteristics and our findings support the notion that greater uncertainty leaves more room for psychological biases, which further leads to informational inefficiency.



Betting Against the Crowd: Option Trading and Market Risk Premium

with Jie Cao, Gang Li and Xintong Zhan (current Version: Dec., 2022).

We study how equity option trading affects the market risk premium. We find that a measure of aggregate call order imbalance (ACIB), defined as the cross-sectional average of the difference between open-buy and open-sell volume, negatively forecasts future stock market returns significantly from days to months. Moreover, ACIB represents an option-based investor sentiment measure that accounts for excess option buying or selling, and is highly correlated with the stock investor sentiment. Our findings shed new insights on the distinctions for call and put option trading, index and equity option trading, and cross-sectional and time-series predictions.

Presented at 2023 CICF



Investor Sentiment and Asset Returns: Actions Speak Louder than Words

with Dat Mai and Kuntara Pukthuanthong (current Version: Nov., 2022).

We analyze the daily predictability of investor sentiment across four major asset classes and compare sentiment measures based on news and social media with those based on trade information. For the majority of assets, trade-based sentiment measures outperform their text-based equivalents for both in-sample and out-of-sample predictions. This outperformance is particularly noticeable in long-term forecasts. However, real-time mean-variance investors can only achieve economic gains using Bitcoin trade sentiment, suggesting the challenge of transforming sentiment into daily profitable trading strategies.



Commodity Inflation Risk Premium and Stock Market Returns

with Ai Jun Hou, Emmanouil Platanakis and Xiaoxia Ye (current Version: Dec, 2023).

We propose a novel measure of commodity inflation risk premium (cIRP) based on a term structure model of commodity futures. The cIRP, capturing forward-looking information in the futures markets, outperforms well-known characteristics in explaining the cross-section of commodity returns. The associated cIRP factor has the highest Sharpe ratio among the existing factors, and has substantial new information beyond them. Moreover, various aggregations of the individual cIRP predict stock market returns significantly, even after controlling for major economic predictors including the usual inflation measure. The link between commodities and the stock market is stronger than previously thought.



International Corporate Bond Market: Uncovering Risks Using Machine Learning

with Delong Li, Lei Lu and Zhen Qi (current Version: June, 2022).

In this paper, we explore what factors drive expected corporate bond returns all over the world. With a novel dataset, and utilizing machine learning models, we find there is strong predictability of corporate bond returns in international markets. However, the documented factors that drive bonds in the U.S. and non-U.S. developed markets are substantially different from factors that impact bonds in the emerging markets, where inflation, downside risk, duration, illiquidity, and volatility are more influential. Moreover, U.S.-based equity and bond factors do not contribute predictive power to non-U.S. corporate bonds, indicating that international corporate bond markets are not well integrated.



Heterogeneous Response: Fama-MacBeth Regression Extended

with Xiaoxiao Tang and Xiwei Tang (current Version: October, 2023).

We extend the widely used Fama-MacBeth regression to allow different stock returns to respond differently to their risk exposures, generalizing group-level heterogeneity originated by Patton and Weller (2022) to individual-level heterogeneity. Using 15 representative firm characteristics from Lewellen (2015), we find that the Sharpe ratio of long-short portfolios based on the prediction of our model almost doubles that based on the Fama-MacBeth model. Our approach also outperforms recent machine learning models, even in a high-dimensional setting with 94 characteristics, which suggests that economic structures can add value beyond artificial intelligence techniques. We confirm the existence of heterogeneity, which is more pervasive during recession periods.



Asymmetry in Variance: Does It Matter to Stock Returns?

with Xiaoxiao Tang (current Version: December, 2023).

We propose a new measure, AVar, of asymmetry in variance of an asset return. Theoretically, we link the ranking of stocks by AVar based on the physical measure to that based on the risk-neutral measure, enabling us to use forward-looking information from the options market to estimate AVar. Empirically, we find that, in the cross section of stocks, the greater the AVar, the greater the stocks returns. The term structure of AVar also reflects future time variation in stock returns. Economically, we explain the compensation for bearing the asymmetry risk by interpreting AVar, under certain conditions, as a measure that effectively reflects the asymmetry in investors’ utility curvature between losses and gains, thus highlighting investors’ greater disutility from losses compared to equivalent gains.



Labor Flow Shocks Matter for Asset Pricing

with Jian Chen, Chunmian Ge, and Jiaquan Yao (current Version: Feb., 2023).

(On-line Appendix)

Using a novel dataset based on individual resumes of public firm employees, we propose a monthly index of labor flows and decompose it into an expected level and unexpected shock component. We find that shocks strongly predict short-term market excess returns, while levels of labor hiring have insignificant forecasting power in the short run. The substantial return predictability of hiring shocks remains out of the sample and delivers sizable economic value in asset allocation. Our findings cannot be explained by existing labor-related predictors and common economic variables. To exploit the underlying economic mechanism, we show that concerns about economic conditions are more likely to influence return predictability.



ESG and the Market Return

with with Liya Chu, Kent Wang and Bohui Zhang (current Version: Dec., 2022).

We propose an environmental, social, and governance (ESG) index. We find that it has significant power in predicting the stock market risk premium, both in- and out-of-sample, and delivers sizable economic gains for mean-variance investors in asset allocation. Although the index is extracted by using the PLS method, its predictability is robust to using alternative machine learning tools. We find further that the aggregate of environmental variables captures short-term forecasting power, while that of social or governance captures long-term. The predictive power of the ESG index stems from both cash flow and discount rate channels.



Does Compensation Matter? Evidence from CD&A Disclosures

with Xiumin Martin and Jie (Jane) Xu (current Version: April, 2021).

We study whether the similarity of firm disclosures on the Compensation Discussion and Analysis (CD&A) has predictability for future stock returns. We find that changes to the language and construction of the CD&As predict firms' future stock returns. A portfolio that longs the CD&A "non-changers" and shorts the "changers" earns a significant Fama-French 5-factor alpha of 5.86% (annualized), for the period of 2008-2020. We further find that companies with low CD&A similarities invest less in R&D, are more likely to be targeted by short-sellers, and have greater forced CEO turnovers. Our results provide new and strong evidence on the role of executive compensation in the cross-section of stock returns.



Seeing is Believing: Annual Report 'Graphicity' and Stock Returns Predictability

with Xiahu Deng, Lei Gao and Bo Hu (current Version: June, 2022).

Why do firms graphically enhance their annual reports that appear redundant to the 10-Ks? We develop a novel rational model to explain this. Using a large dataset, we report the first evidence that firms earn approximately 3.5% abnormal returns in the next 3 to 6 months after they initiate graphic annual reports. This is accompanied by an increase in institutional investors' holdings, consistent with our theory that firms create visuals to overcome investor inattention and help communicate subtle information to fundamental investors. This is also consistent with the fact that such firms tend to increase their R&D investments afterwards.

Presented at 2022 CICF (China International Conference in Finance)



Option Characteristics as Cross-Sectional Predictors

with Andreas Neuhierl, Xiaoxiao Tang and Rasmus Tangsgaard Varneskov (current Version: June, 2022).

We provide the first comprehensive analysis of option information for pricing the cross-section of stock returns by jointly examining extensive sets of firm and option characteristics. Using portfolio sorts and high-dimensional methods, we show that certain option measures have significant predictive power, even after controlling for firm characteristics, earning a Fama-French three-factor alpha in excess of 20% per annum. Our analysis further reveals that the strongest option characteristics are associated with information about asset mispricing and future tail return realizations. Our findings are consistent with models of informed trading and limits to arbitrage.

Presented at 2023 AFA in New Orleans



Mispricing and Market Efficiency: An Exogenous Shock to Short Selling from the Dividend Tax Law Change

with Yufeng Han, Yueliang (Jacques) Lu and Weike Xu (current Version: July, 2022).

We study the causal effect of short-sale constraints on market efficiency 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 overpricing as opposed to underpricing becomes stronger following the dividend record months in the post-JGTRRA periods. While the shock magnifies returns to most anomaly types, we find that valuation anomalies seem unlikely to be driven by mispricing. Collectively, our results highlight the importance of tax policies on market efficiency.

Presented at 2021 SFS Cavalcade North America, 2021 AFA, and 2022 CICF (China International Conference in Finance)



Cross-Sectional Expected Returns: New Fama-MacBeth Regressions in the Era of Machine Learning

with Yufeng Han, Ai He and David Rapach (current Version: April, 2023).

(Online Appendix)

We extend the Fama-MacBeth regression framework for cross-sectional return prediction to incorporate big data and machine learning. Extensions for improving cross-sectional return prediction include penalized regression, forecast ensembles, and random features to accommodate nonlinearities. We also develop tools for assessing cross-sectional return forecasts using the Fama-MacBeth approach, including a generalization of the popular out-of-sample R2 statistic. Applying our new methods to predict cross-sectional stock returns using over 200 firm characteristics, we find that the Fama-MacBeth regression framework augmented by machine learning significantly improves cross-sectional return forecasts.

Presented at 2019 AFA in Atlanta



Lottery Preference and Anomalies

with Lei Jiang, Quan Wen, and Yifeng Zhu (current version: Nov., 2022).

We construct a lottery factor based on 13 commonly used lottery proxies and show that this factor adds significant explanatory power to prominent factor models for anomalies, especially for those in the skewness and value groups. We find that anomaly returns are significantly stronger among stocks with high lottery features and are mainly driven by the short leg of lottery stocks instead of financial distress. We find further that lottery stocks are often associated with low short volume and high shorting fees, indicating that retail investors' preference to hold lottery stocks leads to a low lendable supply of such shares.



Economic Fundamentals and Short-Run Exchange Rate Prediction: A Machine Learning Perspective

with Ilias Filippou, David Rapach and Mark Taylor (current version: Dec., 2023)


We establish the out-of-sample predictability of monthly exchange rates via machine learning techniques based on 70 predictors capturing country characteristics, global variables, and their interactions. To better guard against overfitting in our high-dimensional and noisy data environment, we adjust “off-the-shelf” implementations of machine learning techniques to induce adequate shrinkage. The resulting forecasts consistently outperform the no-change benchmark, which has proven difficult to beat. Variable importance analysis indicates that country characteristics are important for forecasting, once they interact with global variables. Machine learning forecasts also markedly improve the performance of a carry trade portfolio, especially since the Global Financial Crisis.

Presented at Vienna Symposium on Foreign Exchange Markets, 2021, and 5th Workshop in Financial Markets and Nonlinear Dynamics, 2021.



Fundamental Extrapolation and Stock Returns

with Dashan Huang, Huacheng Zhang and Yingzi Zhu (current version: January, 2022).

We propose an economic objective-driven pooling strategy to extrapolate multiple fundamentals simultaneously. This strategy outperforms naive extrapolation strategies that use a single fundamental variable and strategies that use past prices or analyst forecasts, and performs similarly as a machine learning-based pooling strategy. We propose a model to show that fundamental extrapolation has dual price effects: a cash flow effect that pushes stock price up relative to its fundamental value and a discount rate effect that depresses stock price via increasing the expected volatility. Our empirical results suggest that the discount rate effect dominates the cash flow effect.

Presented at AFA 2022 and EFA 2020.



Momentum, Reversal, and the Firm Fundamental Cycle

with Yufeng Han, Zhaodan Huang, and Weidong Tian (current version: April, 2021).

We propose a firm fundamental index (FFI) to summarize the firm’s broad range of business activities, and document that firm fundamentals experience economic cycles similar to business cycles of the economy. We find that FFIs explain well the momentum and long-term reversal: due to repeated positive (negative) shocks in fundamentals, investors continue to raise (lower) prices for winner (loser) firms, yielding momentum; but, due to cyclicality, the shocks decrease in magnitude over time and eventually reverse, generating the reversal pattern. We further show that they also explain an extensive list of momentum/reversal anomalies including return seasonality.

Best Paper Award, The World Finance Conference, 2019



Twin Momentum: Fundamental Trends Matter

with Dashan Huang, and Huacheng Zhang (current version: June, 2021).

Using trends in firm fundamentals, we find that there is a fundamental momentum in the stock market. Buying stocks in the top quintile of fundamental trends and selling stocks in the bottom earns a monthly average return of 0.85% comparable to price momentum. Combining both price and fundamental momentum produces a twin momentum, that earns an average return that exceeds their sum and is difficult to explain by short-sell impediment. Our results not only support the view that fundamental analysis is as important as technical analysis, but also indicate that trends contain incremental information beyond often used lagged fundamental predictors.



Sparse Macro Factors

with David Rapach (current version: January, 2021).

(Factor Data: Mkt, Yield and Housing)

We use machine-learning techniques to estimate sparse principal components (PCs) for 120 monthly macroeconomic variables from the FRED-MD database. Each sparse PC is a sparse linear combination of the underlying macroeconomic variables, whose active weights allow for their economic interpretation. Innovations to the sparse PCs constitute a set of sparse macro factors. Robust tests indicate that sparse macro factors corresponding to yields and housing earn statistically and economically significant risk premia. A three-factor model comprised of the market factor and mimicking portfolio returns for the yields and housing factors performs well compared to leading multifactor models in explaining numerous anomalies.

Best paper award, Inquire UK and Inquire Europe, 2019



Investor Sentiment and the Cross-Section of Corporate Bond Returns

with Xu Guo, Hai Lin and Chunchi Wu (current version: January, 2021).

This paper constructs an investor sentiment measure at both individual bond and aggregate levels, uncovering the first evidence that investor sentiment has strong cross-sectional predictive power for corporate bond returns. High bond investor sentiment leads to low future returns. A portfolio that longs low sentiment bonds and shorts high sentiment ones generates an average monthly return of 0.87% for top-quality bonds and 1.48% for speculative-grade bonds. The results are robust to controlling for risk factors and bond characteristics. The cross-sectional predictability of bond returns is countercyclical, and the predictability appears to stem from its predictive power on macroeconomic conditions.

Presented at 2022 CICF (China International Conference in Finance)



An Information Factor: Can Informed Traders Make Abnormal Profits?

with Matthew Ma, Xiumin Martin and Matthew Ringgenberg (current Version: September, 2019).

We construct an information factor (INFO) using the informed stock buying of corporate insiders and the informed selling of short sellers and option traders. INFO strongly predicts future stock returns -- a long-short portfolio formed on INFO earns monthly alphas of 1.24%, substantially outperforming existing strategies including momentum. INFO explains hedge fund returns in the time-series and cross-section. Higher values of INFO are associated with increases in aggregate hedge fund value. Moreover, funds with higher covariation between their returns and INFO outperform by 0.28% per month. The results show information processing skill is an important source of return variation.



Corporate Activities and the Market Risk Premium

with Erik Lie, Bo Meng and Yiming Qian (current version: October, 2017).

While existing asset pricing studies focus on macroeconomic variables to predict stock market risk premium, we find that an aggregate index of corporate activities has substantially greater predictive power both in- and out-of sample, and yields much greater economic gain for a mean-variance investor. The predictive ability of the corporate index stems from its information content about future cash flows. Cross-sectionally, the corporate index performs particularly well for stocks with great information asymmetry.



Sentiment Across Asset Markets

with Dashan Huang, Heikki Lehkonen and Kuntara Pukthuanthong (current version: June, 2018)

In this paper, we study investor sentiment in five major asset markets: stocks, bonds, commodities, currencies, and housing. Based on Thomson Reuter's sentiment measures extracted from 235 news and social media sources, we find that each market is predicted by its own sentiment. Cross-markets, kitchen sink regressions reveal that the stock market is influenced only by bond sentiment, while bond market is affected just by currency market, which is largely unexplained by others; the commodities are related to currencies and housing, and housing can be predicted by stock and bond sentiment. In an efficient information aggregation by the partial least square (PLS), the predictability of each market increases substantially by using information of all markets vs using only its own sentiment.



Cost Behavior and Stock Returns

with Dashan Huang, Fuwei Jiang and Jun Tu (current version: April, 2017).

This paper shows that investors do not fully incorporate cost behavior information into valuation. Firms with higher growth in operating costs generate substantially lower future stock returns. A long-short spread portfolio earns an average return of about 12% per year after controlling for extant risk factors and firm characteristics. Mean-variance spanning tests show that an investor can benefit from investing in this spread portfolio in addition to well-known factors. Firms with high cost growth also suffer from deteriorations in future operating performance. The negative cost growth-return relation is much stronger around earnings announcement days, among firms with lower investor attention, higher idiosyncratic volatility, and higher transaction costs, suggesting that investor underreaction and limits to arbitrage mainly drive the effect.



Taming Momentum Crashes: A Simple Stop-loss Strategy

with Yufeng Han and Yingzi Zhu (current version: August, 2015).

In this paper, we propose a stop-loss strategy to limit the downside risk of the well-known momentum strategy. At a stop-level of 10%, we find, with data from January 1926 to December 2013, that the maximum monthly losses of the equal- and value-weighted momentum strategies go down from -49.79% to -11.36% and from -64.97% to -23.28%, while the Sharpe ratios are more than doubled at the same time. We also provide a general equilibrium model of stop-loss traders and non-stop traders and show that the market price differs from the price in the case of no stop-loss traders by a barrier option.



Which Hedge Fund Styles Hedge Against Bad Times?

with Charles Cao and David Rapach (current Version: February, 2015).

We examine hedge fund style performance in bad versus good times defined as (1) up and down equity market regimes derived from the 200-day moving average of the S&P 500 price index or (2) nonstressed and stressed financial market regimes determined endogenously using the Federal Reserve Bank of Kansas City Financial Stress Index and threshold estimation. We show that hedge fund styles often exhibit significant changes in risk factor exposures across good and bad times. For certain hedge fund styles, changes in factor exposures represent valuable hedges against bad times; in contrast, other hedge fund styles become more exposed to risk factors during bad times in a manner that magnifies downside risk exposure. In the context of “balanced” 40-30-30 portfolios that allocate across U.S. stocks, bonds, and individual hedge fund styles, we find that the Global Macro, Managed Futures, and Multi-Strategy styles provide investors with especially valuable hedges against bad times.



Forecasting Bond Risk Premia Using Technical Indicators

with Jeremy Goh, Fuwei Jiang, and Jun Tu (current Version: July, 2013).

While economic variables have been used extensively to forecast the U.S. bond risk premia, little attention has been paid to the use of technical indicators which are widely employed by practitioners. In this paper, we fill this gap by studying the predictive ability of using a variety of technical indicators vis-a-vis the economic variables. We find that the technical indicators have statistically and economically significant in- and out-of-sample forecasting power. Moreover, we find that utilizing information from both technical indicators and economic variables substantially increases the forecasting performances relative to using just economic variables.



Forecasting Stock Returns During Good and Bad Times

with Dashan Huang, Fuwei Jiang and Jun Tu (current version: May, 2015).

We show that stock returns can be significantly predicted by past realized returns in both good and bad times, in and out of sample. We extend the model in Fama and French (1988) to show that stock returns display mean reversion and momentum over time, which is dependent on the market state. Specifically, past stock returns predict future returns negatively in good times and positively in bad times, which is consistent consistent with the change and level effects in P´astor and Stambaugh (2009).



Hansen-Jagannathan Distance: Geometry and Exact Distribution

with Raymond Kan; November, 2002.

This paper provides an in-depth analysis of the Hansen-Jagannathan (HJ) distance, which is a measure that is widely used for diagnosis of asset pricing models, and also as a tool for model selection. In the mean and standard deviation space of portfolio returns, we provide a geometric interpretation of the HJ-distance. In relation to the traditional regression approach of testing asset pricing models, we show that the HJ-distance is a scaled version of the aggregate pricing errors, and it is closely related to Shanken's (1985) cross-sectional regression test (CSRT) statistic, with the only major difference in how the zero-beta rate is estimated. For the statistical properties, we provide the exact distribution of the sample HJ-distance and also a simple numerical procedure for computing its distribution function. In addition, we propose a new test of equality of HJ-distance for two nested models. Simulation evidence shows that the asymptotic distribution for sample HJ-distance is grossly inappropriate for typical number of test assets and time series observations, making the small sample analysis empirically relevant.


Toward a Better Understanding of the Beta Method and the Stochastic Discount Factor Method

with Raymond Kan; May, 2002.

In a standardized factor model, Kan and Zhou (1999) show the stochastic discount factor (SDF) method yields less efficient estimates than the beta method when both are based on the generalized method of moments (GMM). By modifying the common use of the SDF [via adding more moment conditions to the practice before the publication of Kan and Zhou (1999)], Jagannathan and Wang (2001) and Cochrane (2000a,b) find that the two methods have the same asymptotic variance for the new GMM estimator (which no longer admits analytical solution). Moreover, their analysis relies on a joint normality assumption of both the asset returns and factors. In this paper, we show that: 1) once the normality assumption is relaxed, the modified SDF method is highly sensitive to factor skewness and kurtosis whereas the beta method is not, implying that the SDF estimates can be less reliable in realistic situations where the factors are leptokurtic; 2) in conditional asset pricing models, the modified SDF is in general still strictly dominated by the beta method in terms of estimation accuracy; 3) while it is not well understood and almost never used in the SDF formulation of an asset pricing model, the maximum likelihood method is well defined and has both strictly more efficient estimates and more powerful tests than the SDF method; 4) the SDF tests can have much less power than the beta method in conditional asset pricing models. In short, while the SDF set-up is an elegant theoretical formation, empirical estimation and tests should pay as much attention to the beta method as to the SDF if not more (one more reason is that, as shown by Jagannathan and Wang (2001), estimated model pricing errors have smaller variance by using the beta method than the SDF one).


The End