Classification of intraday S&P500 returns with a Random Forest

Stock markets can be interpreted to a certain extent as prediction markets, since they can incorporate and represent the different opinions of investors who disagree on the implications of the available information on past and expected events and trade on their beliefs in order to achieve profits. Many forecast models have been developed for predicting the future state of stock markets, with the aim of using this knowledge in a trading strategy. This paper interprets the classification of the S&P500 open-to-close returns as a four-class problem. We compare four trading strategies based on a random forest classifier to a buy-and-hold strategy. The results show that predicting the classes with higher absolute returns, ‘strong positive’ and ‘strong negative’, contributed the most to the trading strategies on average. This finding can help shed light on the way in which using additional event outcomes for the classification beyond a simple upward or downward movement can potentially improve a trading strategy.     

An empirical test of individual and institutional trading patterns in Japan, Hong Kong, and Taiwan

We examine the pattern of daily stock returns in Japan, Hong Kong, and Taiwan. Our results support the information-processing hypothesis: Average returns on Monday are lower than on other days of the week, particularly when the previous trading day’s return is negative. Our results also support the positive-feedback-trading hypothesis: Daily returns exhibit positive autocorrelation, particularly when the previous trading day’s return is positive. Further analysis reveals that institutional investors (Japan), individual investors (Taiwan), or both (Hong Kong) can cause these patterns. Our findings are consistent with the relative importance of institutional and individual investors in each of these markets. We thank three anonymous reviewers for helpful comments and suggestions.     

Pair trading based on quantile forecasting of smooth transition GARCH models

Pair trading is a statistical arbitrage strategy used on similar assets with dissimilar valuations. We utilize smooth transition heteroskedastic models with a second-order logistic function to generate trading entry and exit signals and suggest two pair trading strategies: the first uses the upper and lower threshold values in the proposed model as trading entry and exit signals, while the second strategy instead takes one-step-ahead quantile forecasts obtained from the same model. We employ Bayesian Markov chain Monte Carlo sampling methods for updating the estimates and quantile forecasts. As an illustration, we conduct a simulation study and empirical analysis of the daily stock returns of 36 stocks from U.S. stock markets. We use the minimum square distance method to select ten stock pairs, choose additional five pairs consisting of two companies in the same industrial sector, and then finally consider pair trading profits for two out-of-sample periods in 2014 within a six-month time frame as well as for the entire year. The proposed strategies yield average annualized returns of at least 35.5% without a transaction cost and at least 18.4% with a transaction cost.     

Forecasting the direction of the US stock market with dynamic binary probit models

Several empirical studies have documented that the signs of excess stock returns are, to some extent, predictable. In this paper, we consider the predictive ability of the binary dependent dynamic probit model in predicting the direction of monthly excess stock returns. The recession forecast obtained from the model for a binary recession indicator appears to be the most useful predictive variable, and once it is employed, the sign of the excess return is predictable in-sample. The new dynamic “error correction” probit model proposed in the paper yields better out-of-sample sign forecasts, with the resulting average trading returns being higher than those of either the buy-and-hold strategy or trading rules based on ARMAX models.     

Overnight stock returns,intraday returns,and firm-specific investor sentiment

In this study, we propose a new index for measuring firm-specific investor sentiment using overnight and intraday stock returns. We use actual equity data to construct the firm-level investor sentiment index and find that the new index has characteristics expected of a sentiment measure. In addition, we propose a novel sentiment-weighted trading strategy and apply it to momentum and short-term reversal strategies. We find that the sentiment-weighted trading strategy generates better performance in momentum and short-term reversal strategies. The sentiment-weighted trading strategy’s superior performance is evidence that our firm-level investor sentiment index possesses predictive powers with regard to future returns.     

Size and value effects in high-tech industries: The role of R&D investment

We use monthly US stock data over 55 years from 1962 to 2017 to show that the R&D intensity at firms adds another important dimension to the size and value effects in describing stock returns, especially for small high-tech firms. A trading strategy that double sorts on R&D intensity and size or book-to-market ratio outperforms a simple small-minus-big (SMB) or high-minus-low (HML) strategy in producing higher and more significant portfolio returns. The most profitable schemes involve triple sorts by size, BM, and R&D intensity: the payoffs of buying high-BM/R&D-Active portfolio and selling low-BM/R&D-Inactive portfolio in the small-size/high-tech group and that of buying high-tech/high-BM and selling low-tech/low-BM in the small-size/R&D-active group generate a return of more than 2% on a monthly basis. Our results are robust to alternative classification method of assigning stocks in portfolios.     

The impacts of investor sentiment on returns and conditional volatility of international stock markets

One of the main arguments of behavioral finance is that some properties of asset prices are most probably regarded as deviations from fundamental value and they are generated by the participation of traders who are not fully rational, thus called noise traders. Noise trader theory postulates that sentiment traders have greater impact during high-sentiment periods than during low-sentiment periods, and sentiment traders miscalculate the variance of returns undermining the mean-variance relation. The main objective of this research is to construct a model to evaluate the returns and conditional volatility of various stock market indexes considering the changes in the investor sentiment by measuring the effects of noise trader demand shocks on returns and volatility. EGARCH model is used to determine whether earning shocks have more influence on the conditional volatility in high sentiment periods weakening the mean–variance relation. This paper takes an international approach using weekly market index returns of U.S., Japan, Hong Kong, U.K., France, Germany, and Turkey. Weekly trading volumes of these indexes are regressed against a group of macroeconomic variables and the residuals are used as proxies for investor sentiment and significant evidence is found that there is asymmetric volatility in these market indexes and earning shocks have more influence on conditional volatility when the sentiment is high.     

Chinese Lunar New Year effect in Asian stock markets, 1999–2012

This study investigates the Chinese Lunar New Year (CLNY) holiday effect in major Asian stock markets. These are China, Hong Kong, Japan, Malaysia, South Korea and Taiwan. For robustness test, India is also examined in this paper. Daily stock index returns for each market are analysed for the period of 01/09/1999 to 28/03/2012. Using an ARMA(1,1)-GARCH (1,1) model, we find that there is a significantly positive pre-CLNY holiday effect for all cases. The findings are robust for most cases with the exception of China. It is found that high pre-CLNY returns for China are rewards for high risk, whereas for the other markets, high returns are caused by unknown factors, other than the conditional risk.     

Order aggressiveness, pre-trade transparency, and long memory in an order-driven market

Recent empirical research has documented that the state of the limit order book influences stock investors' strategies. Investors place more aggressive orders when the same side of the order book is thicker, and less aggressive orders when it is thinner. We conjecture and demonstrate that this behavior is related to long memories of trading volume, volatility, and order signs in stock markets. We investigate our conjecture in two types of artificial stock markets: a transparent market, in which agents observe all limit orders on both sides of the book and order volumes at those prices before they trade; and a less transparent market, in which agents observe only the best five bid and ask quotes with the depth available at these limit prices. The first market structure resembles certain actual stock exchanges in the level of pre-trade transparency, such as the Australian Stock Exchange, NYSE OpenBook, and the London Stock Exchange, whereas the second market structure is consistent with stock exchanges such as Euronext Paris, the Toronto Stock Exchange, the Tokyo Stock Exchange, and Hong Kong Exchanges and Clearing. We demonstrate that our long memory results are robust with different levels of pre-trade transparency, implying that the strategy constructed by the state of the order book is key for explaining long memories in many actual stock exchanges.     

Trading cost expectations: Evidence from S&P 500 index replacement stock announcements

This paper tests the effect on stock value of an expected change in future trading costs. The capitalized value of a reduction in trading costs is hypothesized to increase the stock value, a trading cost effect. Improved liquidity reduces trading costs. Inclusion as an S&P 500 Index replacement stock is an event hypothesized to increase liquidity. We use 114 observations between January 1, 1983 and October 12, 1989 of stocks added to the Index as replacements for stocks removed. The abnormal return of each stock is regressed against the ratio of the bidask spread to the price of the stock, the change in trading volume of the stock, and the open interest in the Index futures contracts at the close of the month prior to the replacement announcement. We find that the positive abnormal returns for replacement stocks are related to increased daily trading volume after inclusion in the Index. Further, the trading cost effect is proportional to percentage bid-ask spreads prior to inclusion. The trading cost effect increases as trading in derivatives of the Index increases. The volume and stock price changes after replacement are not transitory, indicating an improvement in liquidity. Three alternate hypotheses suggested in prior research to explain the abnormal returns for replacement stocks are tested. Testing each of the three models previously considered: price pressure, inelastic demand curves, and information, we find that none can be accepted with statistical confidence. The abnormal returns of Index replacement stocks are consistent with rational pricing of an anticipated reduction in future transaction costs. This anticipated reduction is capitalized in the value of the stock at the time of the replacement announcement. These results are consistent with a trading cost effect.     

Asymmetric risk spillovers between Shanghai and Hong Kong stock markets under China’s capital account liberalization

In this paper, we investigate the asymmetric risk spillovers between Shanghai and Hong Kong stock markets under the backdrop of China’s capital account liberalization by measuring the Conditional Value-at-Risk (CoVaR) based on adjusted realized volatilities and variational mode decomposition based copula model. The empirical results show that, the asymmetric features of risk spillovers between the two markets are significant and manifest different states before and after the Shanghai-Hong Kong Stock Connect and Shenzhen-Hong Kong Stock Connect schemes. More specifically, first, the downside risk spillovers from Hong Kong to Shanghai are significantly larger than its upside risk spillovers, while the risk spillovers from Shanghai to Hong Kong is on the contrary. Second, the short-run risk spillovers are more drastic than the long-run risk spillovers, except the risk spillovers from Shanghai to Hong Kong after the Shenzhen-Hong Kong Stock Connect scheme. Finally, by comparing the risk spillovers from two directions, the importance of Shanghai stock market gradually rises up with the implementations of Stock Connect schemes.     

Price effects after one-day abnormal returns in developed and emerging markets: ESG versus traditional indices

This paper examines price effects related to one day abnormal returns on the stock market indices of both developed and emerging countries while accounting for differences between environmental, social, governance (ESG), and conventional indices. Using daily data from MSCI family indices from 2007 to 2020 and various methods to avoid methodological bias, the following hypotheses are tested: after one-day abnormal returns, specific price effects (momentum/contrarian) appear (H1) in cases of positive (H1.1) and negative (H1.2) returns, price effects after one-day abnormal returns are stronger in the case of traditional indices as compared to ESG indices (H2), price effects after one-day abnormal returns are stronger during the crisis period (H3), a dynamic trigger approach is more appropriate for defining abnormal returns than a static approach (H4), price effects after one-day abnormal returns are stronger in emerging markets as compared to developed ones (H5). The results are mixed in the case of H1 and provide no evidence in favor of H2-H5. They also show no significant differences between ESG and conventional indices. The types of detected price effects are the same for the cases of ESG and conventional indices; their power is different in some cases. Overall, a strong contrarian effect is observed in the US stock market after one-day abnormal returns; a trading strategy constructed based on this observation could generate profits from trading. The main results offer additional evidence against the Efficient Market Hypothesis and provide implications that can assist practitioners in beating the market.     

Do real estate investors trade on momentum?

Real estate markets are known to be less-than-efficient for many reasons, but what roles short-term trading plays are unclear. Do short-term investors bring additional risk to the market and cause prices to deviate from fundamental values? Based on an extensive dataset of property transactions and a policy shock that substantially raised the cost of short-term trading in Hong Kong, we estimate ‘real estate risk’ with and without short-term trading based on return predictability, return volatility, and price dispersion. Our results show that as short-term investors exit the market, market returns are less predictable and less volatile, while prices are less dispersed cross-sectionally. Consistent with herding models in behavioral finance, the findings suggest that short-term investors are momentum traders who do not enhance price efficiency.     

Modeling dynamic conditional correlations with leverage effects and volatility spillover effects: Evidence from the Chinese and US stock markets affected by the recent trade friction

In this article, we investigate the dynamic conditional correlations (DCCs) with leverage effects and volatility spillover effects that consider time difference and long memory of returns, between the Chinese and US stock markets, in the Sino-US trade friction and previous stable periods. The widespread belief that the developed markets dominate the emerging markets in stock market interactions is challenged by our findings that both the mean and volatility spillovers are bidirectional. We do find that most of the shocks to these DCCs between the two stock markets are symmetric, and all the symmetric shocks to these DCCs are highly persistent between Shanghai’s trading return and S&P 500′s trading or overnight return, however all the shocks to these DCCs are short-lived between S&P 500′s trading return and Shanghai’s trading or overnight return. We also find clear evidence that the DCC between Shanghai’s trading return and S&P 500′s overnight return has a downward trend with a structural break, perhaps due to the “America First” policy, after which it rebounds and fluctuates sharply in the middle and later periods of trade friction. These findings have important implications for investors to pursue profits.     

Firm Characteristics and Chinese Stocks

This paper presents a comprehensive study on predicting the cross section of Chinese stock market returns with a large panel of 75 individual firm characteristics. We use not only the traditional Fama-MacBeth regression, but also the “big-data” econometric methods: principal component analysis (PCA), partial least squares (PLS), and forecast combination to extract information from all the 75 firm characteristics. These characteristics are important return predictors, with statistical and economic significance. Furthermore, firm characteristics that are related to trading frictions, momentum, and profitability are the most effective predictors of future stock returns in the Chinese stock market.     

Forecasting abnormal stock returns and trading volume using investor sentiment: Evidence from online search

We examine the ability of online ticker searches (e.g. XOM for Exxon Mobil) to forecast abnormal stock returns and trading volumes. Specifically, we argue that online ticker searches serve as a valid proxy for investor sentiment — a set of beliefs about cash flows and investment risks that are not necessarily justified by the facts at hand — which is generally associated with less sophisticated, retail investors. Based on prior research on investor sentiment, we expect online search intensity to forecast stock returns and trading volume, and also expect that highly volatile stocks, which are more difficult to arbitrage, will be more sensitive to search intensity than less volatile stocks. In a sample of S&P 500 firms over the period 2005-2008, we find that, over a weekly horizon, online search intensity reliably predicts abnormal stock returns and trading volumes, and that the sensitivity of returns to search intensity is positively related to the difficulty of a stock being arbitraged. More broadly, our study highlights the potential of employing online search data for other forecasting applications.     

The costs of suboptimal dynamic asset allocation: General results and applications to interest rate risk, stock volatility risk, and growth/value tilts

The recent theoretical asset allocation literature has derived optimal dynamic investment strategies in various advanced models of asset returns. But how sensitive is investor welfare to deviations from the theoretically optimal strategy? Will unsophisticated investors do almost as well as sophisticated investors? This paper develops a general theoretical framework for answering such questions and applies it to three specific models of interest rate risk, stochastic stock volatility, and mean reversion and growth/value tilts of stock portfolios. Among other things, we find that growth/value tilts are highly valuable, but the hedging of time-varying stock risk premia is less important.     

Modeling and forecasting trading volume index: GARCH versus TGARCH approach

Volatility has been described as an indicator of uncertainty which has implications for investment decisions, risk management as well as monetary policy. This paper investigates the pattern of volatility in the daily trading volume index of Hong Kong stock exchange. The empirical evidence provided in this paper suggests that TGARCH specification is superior to GARCH specification. This is particularly important when one is dealing with the case of asymmetric information that captures the leverage effect of the volatile stock market.     

Positional momentum and liquidity management; a bivariate rank approach

This paper introduces a new positional momentum management strategy based on the expected future ranks of asset returns and trade volume changes predicted by a bivariate Vector Autoregressive (VAR) model. The new method is applied to a dataset of 1330 stocks traded on the NASDAQ between 2008 and 2016. It is shown that return ranks are correlated with their own past values and the current and past ranks of trade volume changes. This results leads to a new expected positional momentum strategy providing portfolios of predicted winners, conditional on past ranks of returns and volume changes. This approach further extends to positional liquidity management. The expected liquid positional strategy selects portfolios of stocks with the strongest realized or predicted increase in trading volume. These new positional management strategies outperform the standard momentum strategies and the equally weighted portfolio in terms of average returns and Sharpe ratio.     

Family ownership,corporate governance,and top executive compensation

In this study we investigate how top management pay is determined in a family firm environment where even listed firms are effectively controlled by a single individual or a single family. Using data from Hong Kong, we find that executive directors' pay is reduced if the directors have substantial stockholdings. Moreover, pay is related to profits but not to stock returns. Our results are consistent with external blockholders and independent non‐executive directors persuading firms to base top management compensation on a firm's profitability. Copyright © 2006 John Wiley & Sons, Ltd.