Technical Trading Systems Research Articles

Advance Sequential Models for Asset Trading: Leveraging LSTM & RNN with Stochastic RSI and MACD Indicators

Abstract: The goal of stock market prediction is to forecast a company's financial stocks' future worth. The application of machine learning, which creates predictions based on the values of the current stock market indices by training on their prior values, is a recent trend in stock market prediction technologies. Machine learning utilises many models to facilitate accurate and reliable prediction. The study focuses on stock value prediction using regression and LSTM-based machine learning. Considered factors are volume, low, high, open, and closed. We also employ algorithmic trading, which is a technique for automatically executing orders based on pre-programmed trading instructions that take volume, price, and time into account. This kind of trading aims to take advantage of a computer's speed and computational power in comparison to human traders. Algorithmic trading has become more popular in the twenty-first century, prompting traders to respond. According to a 2019 research, 92% of traders use algorithms rather than people. The moving average convergence & divergence and the relative strength index are our primary tools. One technical tool employed in financial market analysis is the relative strength index, or RSI. Charting a stock's historical and present strength or weakness with retail and institutional traders is the goal. Investment banks, mutual funds, pension funds, and hedge funds all utilise it extensively when they need to perform trades. based on the closing prices of a recent trading period, too fast for a human or the market. It is important to distinguish the indicator from relative strength. The RSI measures the speed and size of price changes and is categorised as a momentum oscillator. The rate at which prices rise or fall is known as momentum. The ratio of higher closes to lower closes, where closures are defined as averages of absolute values of price changes, is the relative strength, or RS. The RSI determines momentum by dividing higher closes by overall closes, or stocks with more or stronger positive moves. The RSI is most commonly employed during a 14-day period and is scaled from 0 to 100, with 70 and 30 representing the high and low readings, respectively. Alternately shorter or longer outlooks are associated with shorter or longer time frames. Although they happen less frequently, high and low levels— 80 and 20, or 90 and 10—indicate increased momentum. J. Welles Wilder created the relative strength index, which was first published in the June 1978 issue of commodities magazine and in his 1978 book New concepts in technical trading systems, and in commodities magazine in the June 1978 issue.

Is Technical Analysis Profitable on Renewable Energy Stocks? Evidence from Trend-Reinforcing, Mean-Reverting and Hybrid Fractal Trading Systems

Demand for power sources is gradually shifting from ozone-depleting-substances towards renewable and sustainable energy resources. The growth prospects of the renewable energy industry coupled with improved cost efficiency means that renewable energy companies offer potential returns for traders in stock markets. Nonetheless, there have been no studies investigating technical trading rules in renewable energy stocks by amalgamating fractal geometry with technical indicators that focus on different market phases. In this paper, we explore the profitability of technical analysis using a portfolio of 20 component stocks from the NASDAQ OMX Renewable Energy Generation Index using fractal dimension together with trend-reinforcing and mean-reverting (contrarian) indicators. Using daily prices for the period 1 July 2012 to 30 June 2022, we apply several tests to measure trading performance and risk-return dynamics of each form of technical trading system—both in isolation and simultaneously. Overall, trend (contrarian) trading system outperforms (underperforms) the naïve buy-and-hold policy on a risk-adjusted basis, while the outcome is further enhanced (reduced) by the fractal-reinforced strategy. Simultaneous use of both trend-reinforcing and mean-reverting indicators strengthened by fractal geometry generates the best risk-return trade-off, significantly outperforming the benchmark. Our findings suggest that renewable energy stock prices do not fully capture historical price patterns, allowing traders to earn significant profits from the weak form market inefficiency.

Finding Optimal Parameter Values for the MACD Indicator: Evidence From the Japanese Nikkei 225 Futures Market Using a New Methodology

This paper explores: (1) what parameter values are most often used to optimize the Moving Average Convergence Divergence (MACD) trading system for the Japanese Nikkei 225 futures market; and, (2) the characteristics of good-performing models with the optimized parameter values. To accomplish this purpose, this paper presents a new methodology to find the three optimal parameter values of the MACD trading system; this approach systematically examines specific ranges of optimal parameter values. Evidence from the Japanese futures market demonstrates the validity of this new methodological approach. From this, we find that for the Japanese market the technical trading system is most often optimized by three parameter values within three specific ranges over the last 11 years (2011–2021). These optimal value combinations have a unique characteristic form. These findings give insightful and broader perspectives about the market. This issue, methodology and the results have not been discussed in the existing literature. This paper also considers how the models with optimal parameter values performed during the pandemic period (2020–2021).

Profitability of alternative methods of combining the signals from technical trading systems

SummaryPast efforts determining the profitability of technical analysis reached varied conclusions. We test the profitability of a composite prediction that uses buy and sell signals from technical indicators as inputs. Both machine learning methods, like neural networks, and statistical methods, like logistic regression, are used to get predictions. Inputs are signals from trend‐following and mean‐reversal technical indicators in addition to the variance of prices. Four representative commodities from agricultural, livestock, financial, and foreign exchange futures markets are selected to determine profitability. Special care is taken to avoid data snooping error. Both neural networks and statistical methods did not show consistent profitability.

AN EMPIRICAL ANALYSIS OF TRADING STRATEGY BASED ON SIMPLE MOVING AVERAGE CROSSOVERS

Technical analysis is based on the assumption that the future price of a stock can be predicted from its history. Several technical trading systems exist for generating buy and sell signals in stock prices. Simple moving average crossovers are popular tools for trading. In this study, simple moving average crossovers with different periods are analyzed empirically on historical daily data of NIFTY 50 index. The profit and loss distribution in these trades are studied to identify profitable and stable crossover periods. The choppy price action known as whipsaws incur large number of small losses in the crossover based trading system. The phenomenon of rare trending price movements and its impact on the trading system are demonstrated.

Momentum Investing & Asset Allocation

This paper highlights the use of a new strategic approach within a quantitative investment methodology in the context of making prudent asset allocation decisions. Three asset classes will frame the dynamic asset allocation discussion: Equities, Fixed Income, and Hedge Funds. The quantitative methodology used is an evolution of J. Welles Wilder’s Relative Strength Index (RSI) first published in New Concepts in Technical Trading Systems . The sample portfolio that was analyzed over several market cycles has demonstrated greater compound returns with less volatility. The result is a set of strategies that yield better risk-adjusted returns to the broad equity markets, broad bond markets, and broad returns of hedge funds. In fact, the portfolios we analyzed delivered significantly higher risk adjusted returns across multiple market cycles.

Building Technical Trading System with Genetic Programming: A New Method to Test the Efficiency of Chinese Stock Markets

Testing whether technical trading rules can beat buy-and-hold strategy is a common approach to study the efficiency of stock markets. Noticing that the common approach of evaluating popular technical trading rules' profitability would result in the biases of data snooping and incomplete test, we build a technical trading system with genetic programming to test the efficiency of Chinese stock markets. This system takes historical prices and volumes as inputs, randomly generates treelike structured technical trading rules composed of basic functions, and optimizes the rules using genetic programming according to the inputs. Using daily prices and volumes of Shenzhen Stock Exchange 100 index from January 2, 2004 to March 12, 2010, we find out that the optimal technical trading rules generated by our technical trading system have statistically significant out-of-sample excess returns compared with buy-and-hold strategy considering realistic transaction costs. Therefore, we conclude that Chinese stock markets have not achieved weak-form efficiency.

Reducing the Risk of Investing in Stocks

Although financial literature presents ambiguous evidence about the predicting value of fundamental and technical variables in stock markets, we find that evolving trading models based on fundamental variables substantially reduce the risk of investing in stocks. This reduction is so generous that the risk-adjusted return obtained following these fundamental variables to trade individual stocks is superior to that obtained by the passive investing in the same individual stocks. However the technical indicators we analyze do not show any predicting value neither in terms of return or risk. We observe the dynamics of individual stock prices’ return and risk in a new framework, the Adaptive Market Hypothesis (AMH) proposed recently by Lo (2004). Using this framework, we examine if there is room to improve investment strategies when adapting them to the potential changing conditions of financial markets or to the investors’ learning process. This adaptation is carried out by quantitative adaptive models driven by evolutionary algorithms (genetic algorithms) that update, over time, the threshold values for fundamental and technical indicators. We find that adaptation improves the risk-adjusted return of investment strategies. We test our trading models using a large sample of companies: non-financial firms with data available in Compustat database which have been listed in the S&P 500 for at least two quarters during the period 1976 - 2006. Our sample consists of 332,700 firm-quarterly observations for fundamental trading systems and 7,157,320 firm-daily observations for technical trading systems. Our models are run using parallel computation executed on 81 computers with a global capacity of 225 GFLOPS or (225x109) FLOPS (floating point operations per second) at the Computational Laboratory of the IT School of Madrid’s Complutense University.

Technical Trading Systems as Crystal Balls in Reducing Risk: The Malaysian Stock Market

This study investigates the advantage of technical analysis in reducing risk and generates profits and generates greater return than a passive strategy. Researcher examine the mean returns of 13 technical trading systems against the returns from a buy and hold strategy for the 7 year period from 1996-2009 for Malaysian stocks. The 13 technical trading systems are 1-30 dual simple moving average crossover, 5-20 dual simple moving average crossover, 3-7 exponential moving average crossover, Relative Strength Index (RSI), momentum, stochastic, Moving Average Convergence Divergence (MACD), five Channel Breakout Systems (CBO 20-20, CBO 20-10, CBO 20-5, CBO 10-5 and CBO 15-5) and the Directional Movement Index (DMI). The findings reveal that 12 out of 13 trading systems produced significantly positive gross returns when no transaction costs were involved. These findings refute the assertion that Malaysian stock prices are weak-form efficient suggesting that technical trading systems can be exploited to make abnormal profits.

Genetic Algorithm: An Application to Technical Trading System Design

Recent studies have shown that in the context of financial markets, technical analysis is a very useful tool for predicting trends. Moving Average rules are usually used to make “buy” or “sell” decisions on a daily basis. Due their ability to cover large search spaces with relatively low computational effort, Genetic Algorithms (GA) could be effective in optimization of technical trading systems. This paper studies the problem: how can GA be used to improve the performance of a particular trading rule by optimizing its parameters, and how changes in the design of the GA itself can affect the solution quality obtained in context of technical trading system. In our study, we have concentrated on exploiting the power of genetic algorithms to adjust technical trading rules parameters in background of financial markets. The results of experiments based on real timeseries data demonstrate that the optimized rule obtained using the GA can increase the profit generated significantly as compare to traditional moving average lengths trading rules taken from financial literature.

Performance of Technical Trading Systems in the Yen/Dollar Market

The study investigates the profitability of 1024 moving average and momentum models and their components in the yen/dollar market. It turns out that all models would have been profitable between 1976 and 1999. The pattern of profitability is as follows. The models produce more single losses than single profits, however, the size of the single profits is on average much higher than the size of single losses. Hence, the profitability of technical currency trading is exclusively due to the exploitation of persistent exchange rate trends. These results hold also when technical trading is examined over subperiods. The models which perform best over the most recent subperiod are in most cases significantly profitable also ex ante. However, the profitability of technical currency trading based on daily data has declined since the late 1980s and has disappeared over the out-of-sample period between 2000 and 2004.

Trend Following Algorithms for Technical Trading in Stock Market

Trend following (TF) is a rule-based trading mechanism that taps on the movements of long-term market trend instead of relying on any forecast or external information to decide when to buy and when to sell a stock. Its simple operation is in contrast to complicated prediction methods which typically would try to predict a future trend by analyzing the historical data and may be other factors. TF makes no prediction and it is well known for its simplicity. Although TF is a popular strategy in finance and was implemented in some commercial trading system decades ago, there have not been many studies of TF in computer science. Hence the objective of this paper is to develop a computer simulator in which TF is implemented as a variety of algorithms. Through the algorithms, readers will see how different parameters are chosen, and how these TF strategies perform in a simulation with real-life data. The simulation results show that TF algorithm can gain an average profit of 75.63% of return-of-investment monthly. However, we observed that TF degrades in performance in proportion to the amount of fluctuation of the market trend. This finding is important to the design of technical trading systems. It implies that the fluctuation of market trend should be monitored; when it exceeds a certain threshold the TF trading should be paused to prevent loss.

Applying genetic algorithms to Wall Street

Genetic algorithms (GAs) can be applied to a wide range of problems in the field of finance. The purpose of this paper is to make GAs accessible to practitioners, academicians and students who are interested in financial markets. By describing a simple application consisting in tuning a technical trading system for the Dow Jones we illustrate step by step how the reader can implement its own trading system with the help of the powerful tool, the GA. To show how this technique can easily be extended to other type of applications in the financial domain, some examples are brought up at the end of the paper.

Investment using evolutionary learning methods and technical rules

In this paper, I propose a genetic learning approach to generate technical trading systems for stock timing. The most informative technical indicators are selected from a set of almost 5000 signals by a multi-objective genetic algorithm with variable string length. Successively, these signals are combined into a unique trading signal by a learning method. I test the expert weighting solution obtained by the plurality voting committee, the Bayesian model averaging and Boosting procedures with data from the S&P 500 Composite Index, in three market phases, up-trend, down-trend and sideways-movements, covering the period 2000–2006. Computational results indicate that the near-optimal set of rules varies among market phases but presents stable results and is able to reduce or eliminate losses in down-trend periods.

The Interaction between Technical Currency Trading and Exchange Rate Fluctuations

This paper examines the mutually reinforcing interactions between exchange rate dynamics and technical trading strategies. I first show that technical trading systems have been quite profitable during the floating rate period. This profitability stems from the successful exploitation of exchange-rate trends and not from taking winning positions relatively frequently. I then show that technical models exert an excess demand pressure on currency markets. When these models produce trading signals, almost all signals are on the same side of the market, either buying or selling. When technical models maintain open positions they are either long or short. Initial exchange rate movements triggered by news or by stop-loss orders are strengthened by technical trading and are often transformed into a trend. This multiplier effect is reflected by the close relationship between technical trading signals and order flows. Hence, order flows are not only driven by (fundamental) news but also by technical trading, which reinforces exchange rate trends to which it responds.

The Interaction between the Aggregate Behaviour of Technical Trading Systems and Stock Price Dynamics

This study analyzes the interaction between the aggregate trading behavior of technical models and stock price fluctuations in the S&P 500 futures market. It examines 2580 widely used trading systems based on 30-minutes-prices. The sample comprises trend-following as well as contrarian models. I show that technical trading exerts an excess demand pressure on the stock market. This is because technical models produce clusters of trading signals that are on the same side of the market, either buying or selling. Initial stock price changes triggered by news are strengthened by a sequence of trading signals produced by trend-following models. Once 90% of the models have signaled a particular position, stock prices tend to move in the direction congruent with the position-holding of the models. This phenomenon has to be attributed to the transactions of non-technical traders, perhaps amateurs. Once price movements lose their momentum, contrarian technical models contribute to reversals of the trend.

The Profitability of Technical Stock Trading Has Moved from Daily To Intraday Data

This paper investigates how technical trading systems exploit the momentum and reversal effects in the S&P 500 spot and futures market. When based on daily data, the profitability of 2,580 technical models has steadily declined since 1960, and has been unprofitable since the early 1990s. However, when based on 30-minutes data the same models produce an average gross return of 7.2 percent per year between 1983 and 2007. These results do not change substantially when trading is tested over eight subperiods. In particular, there is no clear trend of a declining profitability of technical stock trading based on 30-minutes data. Those 25 models which performed best over the most recent subperiod produce a significantly higher gross return over the subsequent subperiod than all models. Between 2001 and 2007 the 2,580 models perform worse than over the 1980s and 1990s. This result could be due to stock markets becoming more efficient recently or to stock price trends shifting from 30-minutes prices to prices of higher frequencies.

Profitability of technical stock trading: Has it moved from daily to intraday data?

This paper investigates how technical trading systems exploit the momentum and reversal effects in the S&P 500 spot and futures market. When based on daily data, the profitability of 2580 technical models has steadily declined since 1960, and has been unprofitable since the early 1990s. However, when based on 30-minutes-data the same models produce an average gross return of 7.2% per year between 1983 and 2007. These results do not change substantially when trading is tested over eight subperiods. In particular, there is no clear trend of a declining profitability of technical stock trading based on 30-minutes-data. Those 25 models which performed best over the most recent subperiod produce a significantly higher gross return over the subsequent subperiod than all models. Between 2001 and 2007 the 2580 models perform worse than over the 1980s and 1990s. This result could be due to stock markets becoming recently more efficient or to stock price trends shifting from 30-minutes-prices to prices of higher frequencies.

Fitting the control parameters of a genetic algorithm: An application to technical trading systems design

This paper studies the problem of how changes in the design of the genetic algorithm (GA) have an effect on the results obtained in real-life applications. In this study, focused on the application of a GA to the tuning of technical trading rules in the context of financial markets, our tentative thesis is that the GA is robust with respect to design changes. The optimization of technical trading systems is a suitable area for the application of the GA metaheuristic, as the complexity of the problem grows exponentially as new technical rules are added to the system and as the answer time is crucial when applying the system to real-time data. Up to now, most of GAs applications to this subject obviated the question of possible “design dependence” in their results. The data we report, based on our experiments, do not allow us to refute the hypothesis of robustness of the GA to design implementation, when applying to technical trading systems tuning.

Improving technical trading systems by using a new MATLAB-based genetic algorithm procedure

Recent studies in financial markets suggest that technical analysis can be a very useful tool in predicting the trend. Trading systems are widely used for market assessment; however, parameter optimization of these systems has attracted little interest. In this paper, to explore the potential power of digital trading, we present a new MATLAB tool based on genetic algorithms; the tool specializes in parameter optimization of technical rules. It uses the power of genetic algorithms to generate fast and efficient solutions in real trading terms. Our tool was tested extensively on historical data of a UBS fund investing in emerging stock markets through our specific technical system. Results show that our proposed GATradeTool outperforms commonly used, non-adaptive, software tools with respect to the stability of return and time saving over the whole sample period. However, we provided evidence of a possible population size effect in quality of solutions.