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.     

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.     

A comparative study of technical trading strategies and return predictability: an extension of using NYSE and NASDAQ indices

This study extends the work of Brock et al.’s (1992) empirical analysis on technical trading rules (price and momentum) by including trading volume moving averages; broader indices (New York Stock Exchange (NYSE) and National Association of Security Dealers Automatic Quotations (NASDAQ)) covering both large-cap and small-cap firms using market weightings; and focusing on a time period that includes great innovations in trading and disseminating data to the market. Similar to their study, we base our conclusions on nonparametric analysis. By extending the t-test analysis through a residual bootstrap methodology utilizing a random walk, a generalized autoregressive conditional heteroskedasticity in mean (GARCH-M), and a GARCH-M with instrument variables, criticisms of earlier technical analysis are mitigated. Overall, the results support Brock et al.’s (1992) price-weighted index (Dow Jones Industrial Average (DJIA)) analysis by showing that the technical trading rules add value by capturing profit opportunities when compared to a buy-and-hold strategy. When the analysis of the trading rules are applied to different time periods, the results reveal a weakening in profit potential over time. This may imply that the market is becoming more efficient in disseminating information to a wider range of investors.     

The economic profitability of pre-IPO earnings management and IPO underperformance

The purpose of this paper is to test the market performance of a zero-investment trading strategy based on the knowledge of IPO underperformance and estimates of pre-IPO earnings management. This trading strategy is implemented by forming two-firm portfolios that take short positions in the IPOs and long positions in control firms matched by industry and market capitalization. The first test shows that significant positive abnormal returns can be earned trading on the knowledge of IPO underperformance. However, the relationship between the level of abnormal returns and the level of pre-IPO earnings management is not found to be significant. Overall, our results suggest that existent pre-IPO earnings management plays important roles although investors may not sophisticated enough to measure the level of earnings management.     

The persistence of the small firm/January effect: Is it consistent with investors’ learning and arbitrage efforts?

Using improved methodology and an expanded research design, we examine whether the small firm/January effect (Keim, D. B. (1983). Size-related anomalies and stock return seasonality: further empirical evidence. Journal of Financial Economics 12:13–32), is declining over time due to market efficiency. First, we find that January returns are smaller after 1963–1979, but have simply reverted to levels that existed before that time. Second, we show that the January effect is not limited to mature markets but also appears in firms trading on the relatively new NASDAQ exchange in the 1970s. Third, trading volume for small firms in December and January is not different from other months, implying that traders are not actively arbitraging the anomaly. Together, our results suggest that this anomaly continues to defy rational explanation in an efficient market.     

The Profitability of Trading Strategies Based on Book Value and Earnings in Hong Kong: Market Inefficiency vs. Risk Premia

Using a sample of Hong Kong firms, we have examined the relative and incremental usefulness of book-to-price ratio (B/P), and earnings-to-price ratio (E/P) for providing profitable trading strategies or for predicting stock returns. Our results show that trading strategies based on B/P or E/P yield significant excess returns for various holding periods up to two years, and that B/P and E/P are not only individually but also incrementally useful for predicting stock returns. Further, results of various tests indicate that trading profits observed from the B/P strategy are likely to be a result of B/P proxying for risk differentials, while those from the E/P strategy are related to gains from exploitation of market inefficiency or mispricing. The two ratios appear to capture different aspects of firm value in Hong Kong.     

A strategy for trading the S&P 500 futures market

A system for trading the S&P 500 futures market is proposed. The system is applied to S&P 500 futures data during the period from September 14, 1987, to September 27, 1999. The system uses a momentum oscillator for generating entry or exit prices. In addition, the system uses another indicator for predicting the direction of the trend. When only the oscillator is used for selecting trades, the system is not, in general, as good as buy-and-hold. However, when the trend indicator is used as a filter, the trading system is, at least, as good as buy-and-hold.     

Does Mad Money make the market go mad?

Empirical studies of numerous popular investment advisory services find statistically significant abnormal returns at the time of their broadcast or published investment recommendations. Our analysis of returns and trading volume around stock recommendations aired on charismatic host Jim Cramer's Mad Money program reveals statistical evidence of response to both his buy and sell opinions, with most of the full-day return following an on-air buy recommendation captured by that day's opening price. Trading strategy analysis suggests that individuals with limited funds should be wary of short-term trading to exploit the show's suggestions, while professional investors may be able to exploit buy picks with a contra strategy.     

Non-linear,hybrid exchange rate modeling and trading profitability in the foreign exchange market

A neuro-fuzzy decision-making technology is designed and implemented to obtain the optimal daily currency trading rule. It is found that a non-linear, artificial neural network exchange rate microstructure (hybrid) model combined with a fuzzy logic controller generates a set of trading strategies that earn a higher rate of return compared to the simple buy-and-hold strategy. After accounting for realistic transaction costs, the gains from utilizing a dynamic, neuro-fuzzy model are still present.     

Jumps in cross‐sectional rank and expected returns: a mixture model

We propose a new nonlinear time series model of expected returns based on the dynamics of the cross‐sectional rank of realized returns. We model the joint dynamics of a sharp jump in the cross‐sectional rank and the asset return by analyzing (1) the marginal probability distribution of a jump in the cross‐sectional rank within the context of a duration model, and (2) the probability distribution of the asset return conditional on a jump, for which we specify different dynamics depending upon whether or not a jump has taken place. As a result, the expected returns are generated by a mixture of normal distributions weighted by the probability of jumping. The model is estimated for the weekly returns of the constituents of the SP500 index from 1990 to 2000, and its performance is assessed in an out‐of‐sample exercise from 2001 to 2005. Based on the one‐step‐ahead forecast of the mixture model we propose a trading rule, which is evaluated according to several forecast evaluation criteria and compared to 18 alternative trading rules. We find that the proposed trading strategy is the dominant rule by providing superior risk‐adjusted mean trading returns and accurate value‐at‐risk forecasts. Copyright © 2008 John Wiley & Sons, Ltd.     

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.     

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.     

Institutional investors' attention to environmental information,trading strategies,and market impacts: Evidence from China

Using a large proprietary database of intraday high‐frequency trading, we investigate the trading strategies of institutional investors in dealing with the negative environmental event disclosure of listed companies and their impact on markets, aiming to reveal the mechanism of the lack of “green efficiency” in China's capital market from the perspective of institutional investors. The results show that institutional investors react to negative environmental events prior to the announcements, indicating premature information leakage in the market; in addition, their trading behaviors mitigate the immediate effect of negative environmental event announcements on stock price. After the event is disclosed, institutional investors engage in short‐term selling and long‐term buy and hold. This trading strategy undermines the irrational selling of individual investors in the event of disclosure, short‐term decline in stock price, and long‐term reversal of market overreaction. In a China context, institutional investors generally take environmental information into consideration. However, they fail to recognize the long‐term value effect of negative environmental events and instead cater to trading strategies towards market volatility.     

Beating the market? A mathematical puzzle for market efficiency

The efficient market hypothesis is highly discussed in economic literature. In its strongest form, it states that there are no price trends. When weakening the non-trending assumption to arbitrary short, small, and fully unknown trends, we mathematically prove for a specific class of control-based trading strategies positive expected gains. These strategies are model free, i.e., a trader neither has to think about predictable patterns nor has to estimate market parameters such as the trend’s sign like momentum traders have to do. That means, since the trader does not have to know any trend, even trends too small to find are enough to beat the market. Adjustments for risk and comparisons with buy-and-hold strategies do not satisfactorily solve the problem. In detail, we generalize results from the literature on control-based trading strategies to market settings without specific model assumptions, but with time-varying parameters in discrete and continuous time. We give closed-form formulae for the expected gain as well as the gain’s variance and generalize control-based trading rules to a setting where older information counts less. In addition, we perform an exemplary backtesting study taking transaction costs and bid-ask spreads into account and still observe—on average—positive gains.

     

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.     

Risk aversion,public disclosure,and partially informed outsiders

In this paper, we examine the impact of public disclosure and partially informed outsiders on a risk-averse insider’s trading behavior, market efficiency, and market depth. In our model, under disclosure requirements, except for the final auction, market depth is the same at every auction. When informed outsiders are risk-neutral, in contrast to the case of a risk-averse insider with no informed outsiders, the insider is more concerned about the uncertainty about future price risk. When the number of informed outsiders increases, market liquidity improves, and the insider increases the variance of her random component to conceal her trading strategy. However, since the insider is relatively more risk-averse, she pays less attention to doing this on her own. Besides, the order flow provided by informed outsiders and randomly added by the insider injects additional liquidity into the market. When informed outsiders are risk-averse, compared to risk-neutral informed outsiders, an insider is most concerned about trading risks brought by informed outsiders at the beginning of trading. Furthermore, whether the trader is an insider or informed outsider, the more risk-averse trader has lower expected profits. Moreover, outsiders’ greater risk aversion leads to a smaller market depth.     

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.     

Dissecting returns of non-fungible tokens (NFTs): Evidence from CryptoPunks

We use transaction data on CryptoPunks to dissect the factors affecting the returns of non-fungible tokens (NFTs). Our results show that trading volume in the short period before a trader buys (sells) CryptoPunk relates negatively (positively) to the returns on NFTs, suggesting that when market trading volume is at a high level, NFT owners are better off on the sell side, and investors interested in NFTs should avoid joining the herd. Turnover of a token tends to harm its returns. Finally, both traders’ willingness to purchase and trading experience have a positive impact on NFT returns within short-term investment horizons.     

Individual investors surpass their reputation: Trading behaviour on the Polish futures market

This paper examines individual investors’ trading behaviour by testing the presence of Monday and January anomalies on the Polish futures market, where individuals are the predominant trader type. Both anomalies are well established in the literature, and they are at least partially attributed to individual investors’ trading activities. We conduct an intraday analysis of trading volume, open interest, returns, and return volatility on the futures market in Poland and find the contribution of individuals to market anomalies to be grossly overstated. Hence, individual investors’ trading on the Polish futures market surpasses the prediction by the majority of investigations for mature stock markets.     

Stock prices and the location of trade: Evidence from China-backed ADRs

This study examines whether the trading location affects equity returns of China-backed American Depository Receipts (ADRs) traded in the US. If International Financial Markets are integrated, stock prices should be affected only by their fundamentals; otherwise, stock prices may also be affected by their trading locations/investor sentiment. We find that China ADRs’ returns are affected more by the US market fluctuations than by Chinese market returns. We interpret the results as suggesting that International Financial Markets are at least partially segmented and country-specific investor sentiment affects stock prices.