Trading Signals Research Articles

Additional Limit Conditions for Breakout Trading Strategies

One of the most popular trading methods used in financial markets is the Turtle strategy. Long time passed since the middle of 1983 when Richard Dennis and Bill Eckhardt disputed about whether great traders were born or made. To decide the matter, they recruited and trained some traders (the Turtles) and give them real accounts and a complete trading strategy to see which idea is right. That was a breakout trading strategy, meaning they bought when the price exceeded the maximum 20 or 50 days value, and sold when the price fell below the minimum of the same interval. Since then many changes have occurred in financial markets. Electronic trading was widespread released and financial trading has become accessible to everyone. Algorithmic trading became the significant part of the trading decision systems and high-frequency trading pushed the volatility of the financial markets to new and incredible limits nowadays. The orders are built and sent almost instantly by smart computers using advanced mathematical algorithms. With all these changes there are many questions today regarding the breakouts strategies. Are the Turtle rules still functional? How can the Turtle strategy be automated for algorithmic trading? Are the results comparable with other modern trading strategies? After a short display of the history and the system’s rules, this paper will find some answers to all these questions. We will reveal a method to automate a breakout strategy. More different trading strategies originating from the Turtle rules will be presented. A mathematical model to build the trading signals will be described in order to automate the trading process. It was found that all of these rules have a positive expectancy when they are combined with modern limit conditions. The paper will also include trading results obtained with the methods presented in order to compare and to analyze this capital investment methodology adapted especially for algorithmic trading.

Follow the money: Investor trading around investor-paid credit rating changes

Using institutional equity trading data, we find that a set of small institutional investors consistently follow credit ratings issued by an investor-paid rating agency in their trading decisions. Although rating information is credit related, we find that these followers often respond more strongly to investor-paid ratings than to influential trading signals, such as earnings announcements, analysts' earnings forecast revisions, and recommendation changes. Followers outperform non-followers, and show improved trading performance after becoming followers. We conclude that investor-paid rating agencies offer small institutional investors a cost-effective alternative to in-house research.

Large data sets and machine learning: Applications to statistical arbitrage

Abstract Machine learning algorithms and big data are transforming all industries including the finance and portfolio management sectors. While these techniques, such as Deep Belief Networks or Random Forests, are becoming more and more popular on the market, the academic literature is relatively sparse. Through a series of applications involving hundreds of variables/predictors and stocks, this article presents some of the state-of-the-art techniques and how they can be implemented to manage a long-short portfolio. Numerous practical and empirical issues are developed. One of the main questions beyond big data use is the value of information. Does an increase in the number of predictors improve the portfolio performance? Which features are the most important? A large number of predictors means, potentially, a high level of noise. How do the algorithms manage this? This article develops an application using a 22-year trading period, up to 300 U.S. large caps and around 600 predictors. The empirical results underline the ability of these techniques to generate useful trading signals for portfolios with important turnovers and short holding periods (one or five days). Positive excess returns are reported between 1993 and 2008. They are strongly reduced after accounting for transaction costs and traditional risk factors. When these machine learning tools were readily available in the market, excess returns turned into the negative in most recent times. Results also show that adding features is far from being a guarantee to boost the alpha of the portfolio.

Predicting Nigerian Stock Returns using Technical Analysis and Machine Learning

Models of stock price prediction have customarily utilized technical indicators alone to produce trading signals. In this paper, we construct trading techniques by applying machine-learning methods to technical analysis indicators and stock market returns data. The resulting prediction models can be utilized as an artificial trader used to trade on any given stock trade. Here the issue of stock trading decision prediction is enunciated as a classification problem with two class values representing the buy and sell signals. The stacking technique utilized in this paper is to assist trader with applying the proposed algorithms in their trading using random forest which was staked with different algorithms which incorporates Logistic Regression (LR), Random Forest (RF), Support Vector Machine (SVM) and Neural Network (NN). The experimental results indicated that Top Layer of Random Forest (TRF) produced the best performance among all the algorithms compared. This is an indication that it is a promising strategy for forecasting Nigerian stock returns.

Trading as sharp movements in oil prices and technical trading signals emitted with big data concerns

The sentiments of market participants may be aroused when a sharp rise (fall) in oil prices is emitted. In this study, we take the trading signal emitted by the technical indicator into account accompanied with the sharp rise (fall) in oil prices into account in trading stocks. We explore whether investors will profit by trading stocks when a sharp rise (fall) in oil prices and technical trading signal are emitted together. Owing to big data concerns in employing the constituent stocks of DJ 30, FTSE 100, and SSE 50 as our samples, investors can beat the market in trading stocks. The sharp fall in oil prices, such as over 5%, and the oversold technical trading signals by the SOI occurring together can lead to better performance than trading stocks and the sharp movement in oil prices emitted only. Results revealed are for trading the constituent stocks of DJ 30, FTSE 100, and SSE 50 without exception after taking big data into account.

Selection of the optimal trading model for stock investment in different industries.

In general, the stock prices of the same industry have a similar trend, but those of different industries do not. When investing in stocks of different industries, one should select the optimal model from lots of trading models for each industry because any model may not be suitable for capturing the stock trends of all industries. However, the study has not been carried out at present. In this paper, firstly we select 424 S&P 500 index component stocks (SPICS) and 185 CSI 300 index component stocks (CSICS) as the research objects from 2010 to 2017, divide them into 9 industries such as finance and energy respectively. Secondly, we apply 12 widely used machine learning algorithms to generate stock trading signals in different industries and execute the back-testing based on the trading signals. Thirdly, we use a non-parametric statistical test to evaluate whether there are significant differences among the trading performance evaluation indicators (PEI) of different models in the same industry. Finally, we propose a series of rules to select the optimal models for stock investment of every industry. The analytical results on SPICS and CSICS show that we can find the optimal trading models for each industry based on the statistical tests and the rules. Most importantly, the PEI of the best algorithms can be significantly better than that of the benchmark index and “Buy and Hold” strategy. Therefore, the algorithms can be used for making profits from industry stock trading.

Combining Principal Component Analysis, Discrete Wavelet Transform and XGBoost to trade in the financial markets

When investing in financial markets it is crucial to determine a trading signal that can provide the investor with the best entry and exit points of the financial market, however this is a difficult task and has become a very popular research topic in the financial area. This paper presents an expert system in the financial area that combines Principal Component Analysis (PCA), Discrete Wavelet Transform (DWT), Extreme Gradient Boosting (XGBoost) and a Multi-Objective Optimization Genetic Algorithm (MOO-GA) in order to achieve high returns with a low level of risk. PCA is used to reduce the dimensionality of the financial input data set and the DWT is used to perform a noise reduction to every feature. The resultant data set is then fed to an XGBoost binary classifier that has its hyperparameters optimized by a MOO-GA. The importance of the PCA is analyzed and the results obtained show that it greatly improves the performance of the system. In order to improve even more the results obtained in the system using PCA, the PCA and the DWT are then applied together in one system and the results obtained show that this system is capable of outperforming the Buy and Hold (B&H) strategy in three of the five analyzed financial markets, achieving an average rate of return of 49.26% in the portfolio, while the B&H achieves on average 32.41%.

Higher Moments and Exchange Rate Behavior

AbstractThis paper uses 15‐minute exchange rate returns data for the six most liquid currencies (i.e., the Australian dollar, British pound, Canadian dollar, Euro, Japanese yen, and Swiss franc) vis‐à‐vis the United States dollar to examine whether a GARCH model augmented with higher moments (HM‐GARCH) performs better than a traditional GARCH (TG) model. Two findings are unraveled. First, the inclusion of odd/even moments in modeling the return/variance improves the statistical performance of the HM‐GARCH model. Second, trading strategies that extract buy and sell trading signals based on exchange rate forecasts from HM‐GARCH models are more profitable than those that depend on TG models.

The Case for Long-Only Agnostic Allocation Portfolios

We advocate the use of Agnostic Allocation for the construction of long-only portfolios of stocks. We show that Agnostic Allocation Portfolios (AAPs) are a special member of a family of risk-based portfolios that are able to mitigate certain extreme features (excess concentration, high turnover, strong exposure to low-risk factors) of classical portfolio construction methods, while achieving similar performance. AAPs thus represent a very attractive alternative risk-based portfolio construction framework that can be implemented in different situations, with or without an active trading signal.

Stochastic and Momentum Analysis of Nepalese Stock Market

The stochastic oscillator is one of the popular tools used by technical analysts. The tools are used mainly to find the overbought and oversold position in the stock market. The stochastic values are between 0-100 which helps to determine the market scenario. The two stochastic indicators are comprised of two lines namely; %K and %D. The investors using the short-term moving average follows %K and for long-term moving average for %D. Though, both are used for buy signal or sell signal by the investors. The basic concept is if, the value of %K is seen above %D, which reflects to sell position, which in context to Nepalese stock market, the scenario is seen during the month of June-July of every fiscal year. At the same time, momentum uses transaction signal or trade signal or the zero ‘0’ line to find the bearish or bullish trend of the market. The momentum of NEPSE index clearly pictures out the bullish and the bearish trend for a specific duration. If the momentum line touches the ‘zero line’, the NEPSE has changed its trend.

Trading Performance Analysis: A Comparisons Between the Original MA Crossover and Modified MA Crossover Strategy

This paper empirically analyses the Trading Performance by using technical analysis approach. The original moving-average (MA) crossover strategy as compare with the modified moving-average crossover strategy. The modified trading rules are the rules that been established to trading rules such as entry rule, exit rule, holding rule, and stop-loss rule. The results show The MAshort of 10-period for modified strategy underperform the original strategy, except for MA (10,100). The modified MA (20,200), (50,100), (50,200), and (100,200) underperform the original strategy. Only modified MA (20,50) and (20,100) outperform the original strategy. The outperformance and underperformance due to the stricter additional trading rule that reduces trading signals, and thus lower number of trades.

Does stronger corporate governance constrain insider trading? Asymmetric evidence from Australia

AbstractWe investigate the role of internal corporate governance in limiting opportunities for ASX company ‘insiders’ to extract abnormal returns from trading ‘own shares’. We show that stronger governance translates into more restrictive insider trading policies and, while not resulting in lower insider purchase volumes, values or profits, it does reduce insider selling profitability. Firm size and increasing trading policy restrictiveness is associated with reduced insider purchase profitability while insider sale profitability is reduced by aggregate governance, trading restrictions and increasing trading policy restrictiveness. We conclude that internal firm governance constrains insider sales but not purchases, providing contrarian trading signals.

Reliable Signals and Limit Conditions for Automated Trading Systems

Abstract Automated trading software is a significant part of the business intelligence system in a modern investment company today. The buy and sell orders are built and sent almost instantly by computers using special trading and computational strategies. The trading decisions are made by automated algorithms. In this paper it will be presented one of these mathematical models which generate trading signals based only on the time price series. The algorithm combines several known computing techniques to build a trading indicator to automate the trades. With this method, buy decisions on oversold intervals and sell decisions on overbought price values can be built. Limit conditions in order to close the long and short trades can be also automatically generated. More trading signal types based on this model will be revealed. Trading results obtained with all these signals will be presented in order to qualify this methodology developed especially for algorithmic trading.

Combining robust dynamic neural networks with traditional technical indicators for generating mechanic trading signals

Forecasting assets’ prices is the aim of each trader, although the trading approaches employed may vary a lot. The development of machine learning techniques has brought the opportunity to design mechanic trading systems based on dynamic artificial neural networks. The aim of this paper is to combine traditional technical indicators [such as exponential weighted moving average (EWMA), percentage volume oscillator (PVO) and stochastic indicator — %K and %D] with the nonlinear autoregressive networks (NAR and NARX). The first part of the paper describes how neural networks designed for forecasting time series work, the second one performs a deeper validation of the code and the third one combines the dynamic networks with traditional technical indicators in order to generate reliable mechanic signals. The article ends with a back testing of the trading system performed on Dow Jones Industrial Average and on Nasdaq Composite Indexes.

Climate change impacts on China's agriculture: The responses from market and trade

China's food security has been facing several challenges, which are likely to be worsened due to climate change. The purpose of this paper is to provide an evidence on the impacts of climate change on China's agriculture, with particular attention to the market and trade responses. Using projected crop yield changes for China and its' main trading partners under changing climate, we employ an agricultural partial equilibrium model (CAPSiM) and a linked national and global equilibrium model (CAPSiM-GTAP) to assess the impacts on food production, price, trade and self-sufficiency of China. Our results show that climate change will have significant effects on crop production though with large differences among crops. Under the worst climate change scenario RCP 8.5, wheat yield in China is projected to decline by 9.4% by 2050, which is the biggest yield reduction among the crops. However, the market can also respond to the climate change, as farmers can change inputs in response to reduced yields and rising prices. As a result, production losses for most crops are dampened. For example, wheat production loss under RCP8.5 reduces to only 4.3% due to market response. The adverse impacts on crop production will be further reduced after accounting for the trade response as farmers adjust production to much higher prices in the more severely affected countries. The paper concludes that we need to learn more from farmers who optimize their production decisions in response to the market and trade signals during climate change. A major policy implication is that policymakers need to mainstream the market and trade responses into national plans for climate adaptation.

Leveraging a call-put ratio as a trading signal

We examine whether a put-call ratio, derived from a unique set of market data, can be used to predict directional moves in asset prices during various market conditions between March 2005 and December 2012. Our findings show: (1) specific market participant's options trading volume is a predecessor to asset price movements, and (2) portfolios based on the put-call ratio adjusted for four factors Carhart model and transaction costs exhibit abnormal excess returns.

Risk-Neutral Skewness and Informed Trading

This paper uses the volatility surface data from options contracts to document a strong, robust, and positive cross-sectional relation between risk-neutral skewness (RNS) and subsequent stock returns. The differential return between high and low RNS stocks amounts to 0.17% per week. Pre-announcement RNS is positively related to earnings announcement returns, and the positive RNS-return relation is more pronounced for other non-scheduled news releases, suggesting that it is informed trading that drives the positive relation between RNS and returns. We also find that RNS contains incremental information beyond trading signals captured by option implied volatility and volume.

Integrating principle component analysis and weighted support vector machine for stock trading signals prediction

Abstract This study investigates stock trading signals prediction that is an interesting yet challenging research topic in the area of financial investment, since the stock market is an unstable and complex system affected by many interrelated factors and a small improvement in predictive performance can be profitable. To realize trading signals detection, several methods have been developed, among which artificial intelligence methods have drawn more and more attention by both investors and researchers. In this paper, we propose a complete and efficient method which integrates principal component analysis (PCA) into weighted support vector machine (WSVM) to forecast trading points of the stock (PCA-WSVM). Firstly, we model the stock trading signals prediction as a weighted four-class classification problem. Then, PCA is applied to clean the original data set and re-arrange it to a new data structure. Thirdly, WSVM is used with the transformed data set to forecast the turning points of the stock. Finally, we conduct a series of experiments among PCA-WSVM, WSVM, PCA-ANN and Buy-and-Hold strategy on stocks from two well-known Chinese stock exchange markets, Shanghai and Shenzhen stock exchange markets, to test the performance of our established model. The experiment results reflect that with our proposed model the prediction capability and profitability with different investment strategies are all the best, which indicates PCA-WSVM is effective and can be applied to forecast the stock trading signals in the real-world application.

A stock market trading system based on foreign and domestic information

This paper investigates whether a particular magnitude and direction of inter-regional return signal transmission dominates the performance of domestic trading in American, European and Australasian stock markets. A trading system design, based on fuzzy logic rules, combines direct and indirect channels of foreign information transmission, modelled by stochastic parameter regressions, with domestic momentum information to generate stock market trading signals. Filters that control for magnitude and direction of trading signals are then used to investigate incremental impact on economic performance of the proposed investment system. The results indicate that at reasonable levels of transaction costs very profitable trades that are fewer in number do not increase investment performance as much as trades based on foreign information of a specific low-to-medium daily return magnitude of 0.5% to 0.75%. These information-based strategies are profitable on risk-adjusted bases and relative to a market, but performance declines considerably when tradable instruments are used.

An investor sentiment reward-based trading system using Gaussian inverse reinforcement learning algorithm

Investor sentiment has been shown as an important factor that influences market returns, and a number of profitable trading systems have been proposed by taking advantage of investor sentiment signals. In this paper, we aim to design an investor sentiment reward-based trading system using Gaussian inverse reinforcement learning method. Our hypothesis is that while markets interact with investor’s sentiment, there exists an intrinsic mapping between investor’s sentiment and market conditions revealing future market directions. We propose an investor sentiment reward based trading system aimed at extracting only signals that generate either negative or positive market responses. Such a reward extraction mechanism is based not only on market returns but also market volatility representing a succinct and robust feature space. The back-test results show that the proposed sentiment reward-based trading system is superior to various benchmark strategies on S&P 500 index and market-based ETFs as well as few other existing news sentiment-based trading signals. Moreover, we find that sentiment reward trading system is much more effective in a volatile market, but it is sensitive to transaction costs.