Profitable Trading Strategies Research Articles

On stock price overreactions: frequency, seasonality and information content

ABSTRACTThis paper explores the frequency of price overreactions in the US stock market by focusing on the Dow Jones Industrial Index over the period 1990–2017. It uses two different methods (static and dynamic) to detect overreactions and then carries out various statistical tests (both parametric and non-parametric) including correlation analysis, augmented Dickey–Fuller tests (ADF), Phillips-Perron (PP) tests, Granger causality tests, and regression analysis with dummy variables. The following hypotheses are tested: whether or not the frequency of overreactions varies over time (H1), is informative about crises (H2) and/or price movements (H3), and exhibits seasonality (H4). The null cannot be rejected except for H4, i.e., no seasonality is found. On the whole, it appears that the frequency of overreactions can provide useful information about market developments. A sharp increase in the number of overreactions occurs in crisis periods. The frequency of overreactions is linked to the VIX index and therefore could be used as an alternative measure of market sentiment and market fear, and it also affects stock returns. Further, our findings provide evidence supporting market inefficiency since price predictability can allow investors to design profitable trading strategies; in addition, the fact that the frequency of overreactions varies over time is consistent with the Adaptive Expectations Hypothesis.

Performance of technical trading rules: evidence from the crude oil market

ABSTRACTThis study investigates the debatable success of technical trading rules, through the years, on the trending energy market of crude oil. In particular, the large universe of 7846 trading rules proposed by Sullivan, Timmermann, and White (1999. “Data-Snooping, Technical Trading Rule Performance, and the Bootstrap.” The Journal of Finance 54 (5): 1647–1691. doi:10.1111/0022-1082.00163), divided into five families (filter rules, moving averages, support and resistance rules, channel breakouts, and on-balance volume averages), is applied to the daily prices of West Texas Intermediate (WTI) light, sweet crude oil futures as well as the United States Oil (USO) fund, from 2006 onwards. We employ the k-familywise error rate (k-FWER) and false discovery rate (FDR) techniques proposed by Romano, J. P., and M. Wolf. (2007. “Control of Generalized Error Rates in Multiple Testing.” The Annals of Statistics 35 (4): 1378–1408. doi:10.1214/009053606000001622) and Bajgrowicz, P., and O. Scaillet. (2012. “Technical Trading Revisited: False Discoveries, Persistence Tests, and Transaction Costs.” Journal of Financial Economics 106 (3): 473–491. doi:10.1016/j.jfineco.2012.06.001) respectively, accounting for data snooping in order to identify significantly profitable trading strategies. Our findings explain that there is no persistent nature in rules performance, contrary to the in-sample outstanding results, although tiny profits can be achieved in some periods. Overall, our results seem to be in favor of interim market inefficiencies.

The value of publicly available predicted earnings surprises

This paper demonstrates how to collect and manage free predicted earnings surprises available in the public domain. The predicted earnings surprises we collect are expected to be more accurate than the corresponding consensus estimates and other predicted earnings, but have not been studied in the academic literature until very recently. We find a number of unexpected and problematic idiosyncrasies with the source of the data and the predicted earnings surprises themselves. The data are hard to work with, perhaps by design, and contain both big and small extreme values that are unexpected given their origin. It is unclear how these observations are selected for public release. After the data science exercise of managing and merging the predicted earnings surprises with other freely available public information (specifically ticker symbols and return data), we examine the predicted earnings surprises and investigate how the predicted earnings surprises affect short-term stock prices. We find evidence of a linear association between the predicted earnings surprises and subsequent short-term returns, although the significance is driven by extreme outliers. Most importantly, we use the predicted earnings surprises to form short-term trading strategies. The most profitable trading strategy that exploits the predicted earnings surprises is a contrarian trading strategy.

Do Indian stock market sentiments impact contemporaneous returns?

PurposeThe purpose of this paper is to analyse the impact of Indian investor sentiments on contemporaneous stock returns of Bombay Stock Exchange, National Stock Exchange and various sectoral indices in India by developing a sentiment index.Design/methodology/approachThe study uses principal component analysis to develop a sentiment index as a proxy for Indian stock market sentiments over a time frame from April 1996 to January 2017. It uses an exploratory approach to identify relevant proxies in building a sentiment index using indirect market measures and macro variables of Indian and US markets.FindingsThe study finds that there is a significant positive correlation between the sentiment index and stock index returns. Sectors which are more dependent on institutional fund flows show a significant impact of the change in sentiments on their respective sectoral indices.Research limitations/implicationsThe study has used data at a monthly frequency. Analysing higher frequency data can explain short-term temporal dynamics between sentiments and returns better. Further studies can be done to explore whether sentiments can be used to predict stock returns.Practical implicationsThe results imply that one can develop profitable trading strategies by investing in sectors like metals and capital goods, which are more susceptible to generate positive returns when the sentiment index is high.Originality/valueThe study supplements the existing literature on the impact of investor sentiments on contemporaneous stock returns in the context of a developing market. It identifies relevant proxies of investor sentiments for the Indian stock market.

A Machine Learning View on Momentum and Reversal Trading

Momentum and reversal effects are important phenomena in stock markets. In academia, relevant studies have been conducted for years. Researchers have attempted to analyze these phenomena using statistical methods and to give some plausible explanations. However, those explanations are sometimes unconvincing. Furthermore, it is very difficult to transfer the findings of these studies to real-world investment trading strategies due to the lack of predictive ability. This paper represents the first attempt to adopt machine learning techniques for investigating the momentum and reversal effects occurring in any stock market. In the study, various machine learning techniques, including the Decision Tree (DT), Support Vector Machine (SVM), Multilayer Perceptron Neural Network (MLP), and Long Short-Term Memory Neural Network (LSTM) were explored and compared carefully. Several models built on these machine learning approaches were used to predict the momentum or reversal effect on the stock market of mainland China, thus allowing investors to build corresponding trading strategies. The experimental results demonstrated that these machine learning approaches, especially the SVM, are beneficial for capturing the relevant momentum and reversal effects, and possibly building profitable trading strategies. Moreover, we propose the corresponding trading strategies in terms of market states to acquire the best investment returns.

Measuring and Trading Volatility on the US Stock Market: A Regime Switching Approach

The volatility premium is a well-documented phenomenon, which can be approximated by the difference between the previous month level of the VIX Index and the rolling 30-day close-to-close volatility. In concordance with existing literature, we show evidence that VIX is generally above the 30-day rolling volatility giving rise to the volatility premium, so that selling volatility can become a profitable trading strategy as long as proper risk management is under place. As a contribution, we introduce the implementation of a Hidden Markov Model (HMM), identifying two and three states of the nature and showing that the volatility premium undergoes temporal breaks in its behavior. Based on this, we formulate different trading strategies by selling volatility and switching to medium-term U.S. Treasury Bills when appropriated. We test the performance of the strategies using the conventional Carhart four-factor model showing positive and statistically significant alphas, even after considering transaction costs.

Bitcoin Poison? Anecdotal Evidence from Bitcoin Miners Revenue

This paper explores the predictive qualities of Bitcoin Miners Revenue on Bitcoin Returns. Using data on Bitcoin in the cryptocurrency market from July 1, 2010 to February 20, 2018, we reflect intervariable correlations not previously examined. We analyze those relationships with a conditional regression analysis adjusting for calendar effects. We separate the sample, and use the last 17 trading days (month) to test a strategy based on the probability of Bitcoin Returns moving higher. After a slight modification to the logistic regression analysis, we find a profitable trading strategy exists based solely on Bitcoin Miners Revenue and the probability of Bitcoin Returns moving higher.

Does Foreign Exchange Volume Activity Predict Foreign Exchange Returns? Evidence from Buy-Sell Volume in the Euro-Dollar Market

This paper investigates the predictive ability of lagged buy-sell volume on current foreign exchange returns. Using novel Euro-Dollar foreign exchange market data from 2007 to 2015, we show that the buy-sell volume has an inverse correlation with current foreign exchange returns. Using conditional regression analysis, buy-sell volumes predict subsequent Euro-Dollar returns. We divide the data into two sub-samples. We use the first sub-sample to create a trading rule, and we use the second sub-sample to test the rule. After adjusting for time-varying calendar effects, we find that a profitable trading strategy exists using only buy-sell volume to predict returns.

Practical Applications Report Popularity versus Profitability: Evidence from Bollinger Bands

Practical Applications Summary Despite questions about its profitability, technical analysis remains popular among investors, and some of the most widely used techniques involve Bollinger Bands, which were introduced by John Bollinger in 1983. Since then, Bollinger Bands have gradually gained popularity, especially since 2001 when Bollinger published his book, Bollinger on Bollinger Bands. Within four years, it had been translated into 12 languages, and the English version had been through seven editions. Bollinger Bands are an interesting case study of whether a trading strategy’s popularity affects its profitability, and, if so, how. In their article, Popularity versus Profitability: Evidence from Bollinger Bands, published in the Summer 2017 issue of The Journal of Portfolio Management , Jiali Fang, Ben Jacobsen , and Yafeng Qin investigate the effects of increasing popularity on the profit potential of Bollinger Band–based trading strategies. Their results indicate that potentially profitable trading strategies self-destruct with increasing popularity. As use of Bollinger Bands grew, there was a gradual downward profitability from their use, and since 2001, the year Bollinger’s book was published, Bollinger Bands have largely lost their predictive ability in major stock markets.

Algorithmic Trading of Bitcoin Using Wikipedia and Google Search Volume

Trading and speculating on Bitcoin is difficult. With large daily price movements and frequent price crashes, implementing quantitative trading strategies can be challenging. This paper presents a simple trading algorithm which uses the volume of Wikipedia and Google Trends search terms to generate trading signals for buying or selling Bitcoin. By exploiting the collective interest in Bitcoin as measured by search volume, findings suggest that highly profitable trading strategies can be constructed that avoid market crashes. The strategy based on the“Bitcoin” Google and Wikipedia search terms generates a cumulative return of 9418.04% and 3549.05% respectively.

Behavioral biases in the corporate bond market

This paper investigates the behavioral biases in the corporate bond market through the cross-section association between retail and institutional trades and corporate bond returns. The study finds that bonds heavily bought by retail investors in one month underperform in the next month relative to bonds heavily sold, and the opposite holds for institutional investors. The alpha of the high-low portfolio (formed based on decile sorting on the buy–sell trade imbalance) relative to the usual market factors is significant for retail investors, but insignificant for institutional investors. The overall results indicate that retail investors in the corporate bond market suffer from behavioral biases but institutional investors do not. However, when the spread between the purchase and sell prices is factored into the returns, no profitable trading strategies exist, consistent with limits to arbitrage.

Influence of individual rationality on continuous double auction markets with networked traders

This paper investigates the influence of individual rationality of buyers and sellers on continuous double auction market outcomes in terms of the proportion of boundedly-rational buyers and sellers. The individual rationality is discussed in a social network artificial stock market model by embedding network formation and information set. Traders automatically select the most profitable trading strategy based on individual and social learning of the profits and trading strategies of themselves and their neighbors, and submit orders to markets. The results show that (i) a higher proportion of boundedly-rational sellers induces a higher market price, higher sellers’ profits and a higher market efficiency; (ii) a higher proportion of boundedly-rational sellers induces a lower number of trades and lower buyers’ profits; (iii) a higher proportion of boundedly-rational buyers induces a lower market price, a lower number of trades, and lower sellers’ profits; (iv) a higher proportion of boundedly-rational buyers induces higher buyers’ profits and a higher market efficiency.

Earnings Momentum in International Markets

This paper examines the profitability of earnings momentum strategies based on analyst forecast revisions in eleven international equity markets. While analyst forecast revisions exhibit persistence in all countries, the profitability of trading strategies based on these revisions varies. Specifically, earnings momentum yields significant profits in Australia, Canada, France, Germany, Hong Kong, and the United Kingdom, but not in Malaysia, South Korea, Japan, Singapore, or Taiwan. Interestingly, price momentum exists only in those countries where earnings momentum is profitable. In general, markets with high levels of corruption (low investor protection) exhibit weak momentum. Collectively, these findings suggest that the momentum phenomenon is related to information dissemination mechanisms within a country.

An uncertainty quantification framework for the achievability of backtesting results of trading strategies

Backtesting has always been indispensable in analyzing the profitability of trading strategies in the empirical finance literature. When measuring return, while most of the literature implicitly assumes that a trade can be implemented at the same closing price as the one generating the trading signal, some empirical evidence has been found suggesting that this assumption presents a significant challenge to the robustness of their results. Hence, several alternative return measurements have been proposed, including the incorporation of a one-day delay to mitigate this execution latency. The mix of opinions on this issue prompted us to quantify whether backtesting results could be achieved with such implementation uncertainty. In particular, we propose a framework for implementing and backtesting trading strategies. A new concept called return-at-risk is introduced to quantify such an ability, and we illustrate our proposed framework using a representative class of trading strategies. Our results show that a significant number of technical trading strategies with positive returns are found to be unviable in the presence of implementation uncertainty.

Popularity versus Profitability: Evidence from Bollinger Bands

Many so-called return predictability anomalies disappear over time. One theoretical explanation is that investors arbitrage profits away through their trading. But investors have used technical analysis strategies for ages, so this argument may not necessarily hold for seemingly profitable technical analysis trading strategies. To verify whether such an argument has merit, we investigate what would happen if a completely new technical trading rule appeared that investors had never used before but which became more popular over time. Bollinger Bands, introduced in 1983, provide a natural experiment. Before their introduction, trading on Bollinger Bands would have been an extremely profitable trading strategy in international stock markets. However, ever since their introduction, their predictive power seems to have gradually decreased and has largely disappeared since the influential publication on Bollinger Bands in 2001. Moreover, their predictability disappeared in the US market first, where Bollinger Bands originated, and then in other international markets.

Can Big Data Help Predict Financial Market Dynamics?: Evidence from the Korean Stock Market

This study quantifies the dynamic interrelationship between the KOSPI index return and search query data derived from the Naver DataLab. The empirical estimation using a bivariate GARCH model reveals that negative contemporaneous correlations between the stock return and the search frequency prevail during the sample period. Meanwhile, the search frequency has a negative association with the one-week-ahead stock return but not vice versa. In addition to identifying dynamic correlations, the paper also aims to serve as a test bed in which the existence of profitable trading strategies based on big data is explored. Specifically, the strategy interpreting the heightened investor attention as a negative signal for future returns appears to have been superior to the benchmark strategy in terms of the expected utility over wealth. This paper also demonstrates that the big data-based option trading strategy might be able to beat the market under certain conditions. These results highlight the possibility of big data as a potential source-which has been left largely untapped-for establishing profitable trading strategies as well as developing insights on stock market dynamics.

Can Big Data Help Predict Financial Market Dynamics?: Evidence from the Korean Stock Market

(ProQuest: ... denotes formulae omitted.)I. INTRODUCTIONThis paper estimates dynamic relationships between the Korean stock market index and the related online search queries within a multivariate GARCH framework. In addition, the paper also attempts to investigate whether the information from search query data can be served as a potential source for designing profitable trading strategies in the Korean stock market.The emergence of internet and social networking services combined with the extensive dissemination of smart phones have revolutionized the way we communicate and exchange information. Consequently, big data continuously flowing from increasing online activities by users have become a buzz word for recent years because of its potentials for various uses including marketing, political predictions, disease epidemics, social dynamics, etc.1Economists are one of the late professions who delves into the investigation of possible use of big data mainly for forecasting market dynamics and related issues.2 The seminal paper by Choi and Varian (2012) shows the use of Google search query data as a key predictor for various economic activities including auto sales, travels, etc.3 It stimulates subsequent studies in the field of economics, which mostly concentrates on exploiting big data to increase the prediction power of forecasting models for economic variables of own interests.The idea that the search query might contain information about subsequent actions by users is based on the premise that economic agents living in a contemporary society largely rely on the prior information-search process before making important economic decisions such as the purchase of durable goods and financial investments.However, the motivaton of information demand does not always run in this direction; the heightened information-gathering activity itself can be the manifestation of a simple endogenous response to major events in markets in quest of more information, which might yield possible effects on market developments in next rounds. These intricacies in the causal relationship between the information demand and the market outcomes make it difficult to assess correctly the real importance of big data. In spite of this complicacy, the predictive power of information generated from online big data for market activity is supported by numerous studies ranging from stock markets to housing markets.4The empirical analysis on the Korean stock market in this study reveals that the search frequency related to the Korean stock market has negative contemporaneous correlations with the KOSPI return for the majority of time with the occasional tightening of its magnitude. Furthermore, a negative association between the search query and the one-week-ahead stock return is observed, while the stock return has no statitically significant impact on the level of the future search query.Based on these observations, we experiment with a hypothetical trading strategy that interprets the increased level of online search activity as a negative signal for future stock returns so as to examine whether profitable trading schemes can be constructed out of big data. The result from this simple exercise demonstrates that the big data-based strategy outperforms the benchmark strategy in terms of the expected utility over wealth. The other experiment also shows that the big data-based option trading strategy can beat the market for certain KOSPI200 option contracts.As a result, this study is the first attempt to analyse the relationship between the KOSPI return and the degree of investor attention5 using the Korean stock market data and a Korean-based internet platform. We conjecture that the contribution is not limited to quantifying the dynamic relationships between stock retums and investor attention and estimating time-varying volatilities; it also explores the potential of big data as one of the practical tools for financial investment strategies, which is rarely pursued in the related literature. …

Order Flow, Volatility and Fuzzy Logic: Technical Analyses for Currency Trading

This paper proposes a multivariate fuzzy logic approach to boosting the profitability of technical analysis for currency trading. The approach incorporates information on underlying market volatility in addition to order-flow-based exchange-rate return forecasts. We show the superiority of our approach by comparing it with the performances of various strategies such as simple trading rules and neural-fuzzy-logic trading rules proposed in the literature. Our approach yields consistently and remarkably higher Sharpe ratios for all the three major and all the three commodity exchange rates investigated. The results provide currency traders with a useful guide to conceiving profitable trading strategies.

Deep networks for predicting direction of change in foreign exchange rates

SummaryTrillions of dollars are traded daily on the foreign exchange (forex) market, making it the largest financial market in the world. Accurate forecasting of forex rates is a necessary element in any effective hedging or speculation strategy in the forex market. Time series models and shallow neural networks provide acceptable point estimates for future rates but are poor at predicting the direction of change and, hence, are not very useful for supporting profitable trading strategies. Machine learning classifiers trained on input features crafted based on domain knowledge produce marginally better results. The recent success of deep networks is partially attributable to their ability to learn abstract features from raw data. This motivates us to investigate the ability of deep convolution neural networks to predict the direction of change in forex rates. Exchange rates for the currency pairs EUR/USD, GBP/USD and JPY/USD are used in experiments. Results demonstrate that trained deep networks achieve satisfactory out‐of‐sample prediction accuracy.

Existence and Exploitability of Financial Analysts' Informational Leadership

This paper bridges two recent studies on the role of analysts to provide new and relevant information to investors. On the one hand, the contribution of analysts to long-term price discovery on the US market is rather low. Considering earnings per share forecasts as the main output of analysts’ reports, their information share amounts to only 4.6% on average. On the other hand, trading strategies set up on these EPS forecasts are quite profitable. Self-financing portfolios yield excess returns of more than 5% over the S&P 100 index for a time period of 36 years, which is persistent after controlling for the well-known risk factors. In this paper, we discuss the link between the low information shares and the high abnormal returns. We argue that information shares of analysts cannot be higher, because otherwise their forecasts would lead to excessively profitable trading strategies which are very unlikely to persist over such a long period of time.