No full-text available
To read the full-text of this research,
you can request a copy directly from the author.
New Concepts in Technical Trading Systems
... Many technical indicators have long been used by financial market traders and investors who must quickly decide whether to buy or sell financial products, such as stocks, bonds, currencies, commodities, and options, while those prices fluctuate 17 . In this study, we used three common indicators: Moving Average Deviation Rate (MAD), Moving Average Convergence/Divergence (MACD) 18 , and Relative Strength Index (RSI) 19 (Table 1). Our purpose here is not to discuss whether price trends exist in the financial market 20,21 . ...
... Subsequently, we employed financial technical indicators to identify turning points in the trends. We selected three widely used indicators: Moving Average Deviation Rate (MAD), Moving Average Convergence/Divergence (MACD), and Relative Strength Index (RSI) 18,19 . The calculation formulas for these indicators are outlined in Table 1. ...
... MAD calculates the deviation ratio between the current price and SMA, which is the average price of past prices, while MACD is the difference between short-term (default 12 periods, i.e., 6 h in this study) and long-term EMAs (default 26 periods, 13 h), with recent prices receiving more weight than older ones 18 . RSI is a momentum oscillator that gauges momentum (short trend) strength based on the ratio of upward to downward price changes over the past 14 days 19 . RSI values range from 0 to 100, with a value of 50 indicating equal total changes. ...
In dairy farming, the uncertainty of cow calving date often imposes waiting costs for days on farmers. Improving the accuracy of calving date prediction would mitigate these costs, specifically before a few days of the event. We monitored and analyzed the heart rate patterns of eight pregnant cows in the days leading up to calving using a dedicated monitoring device. We decomposed the heart rate data into three distinct components: trend, daily cycle, and the remainder, and discovered that the heart rate trend exhibited a sharp decline more than 40 h before the calving event via the trend turning point. To detect the turning point, we applied common financial technical indicators traditionally used to identify turning points of asset prices in trading markets for the extracted heart rate trend. This study remains a feasibility study because of the limited observations, but it indicates that these indicators can effectively capture the trend’s turning point in real time, offering a promising approach for enhanced calving prediction. In addition to discussing the practical implications for cow management, we also contemplate the broader utility of these technical indicators in the context of various dynamic scientific data analyses.
... The range from 30 to 70 points is called neutral. It is allowed to modify the ranges at any time, depending on the market on which the indicator is used (Wilder, 1978). The formula for calculating RSI indicator is as follows: ...
... This sequence repeats for the next period using the updated SAR and increment values. This allows the SAR indicator to accurately reflect trend momentum -the dots accelerate rapidly as the trend extends but slow down and eventually reverse when the trend shows weakness, signalling a trend change (Wilder, 1978). The Parabolic SAR indicator is calculated according to an algorithm using two formulas. ...
... • K -price change step, which defaults to 0.02 (Wilder, 1978). ...
Aim: The aim of the study was to determine the trend of wheat prices using technical analysis indicators. Methodology: Selected technical analysis indicators were used to determine price trends. The parameters of two technical analysis indicators, modified from their default settings, were used to forecast price trends. The Parabolic Stop and Reversal (SAR) indicator, which is a valued trend indicator, was chosen. The second indicator used was the Relative Strength Index (RSI) oscillator, which is also popular with proponents of technical analysis. The data source used to forecast wheat price trends was information from the MetaTrader5 trading platform. Results: The research analysis of the applied strategies shows that it is possible to realistically predict price trends on the wheat quotation market. There were two forecasts of the future price movement of wheat based on the indications of the indicators: (1) an indication to go long (in which case the investor should not expect a change in the trend) and (2) an indication to go short (both the SAR indicator and the RSI indicated a possible change in the trend to the downside). Implications and recommendations: Based on the analysis conducted in the article, it was concluded that technical analysis tools are useful in predicting prices in the wheat futures market. The conducted analysis indicated that the application of technical analysis in predicting wheat futures prices is effective. Therefore, technical analysis indicators can be considered by investors as a tool to assist in making investment decisions in various markets, including the agricultural products market, and the use of technical analysis in price forecasting seems to be justified in the context of economic and geopolitical changes. Originality/value: Due to the development of research methods and tools, it can be assumed that today's investors are looking for alternatives that allow them to reduce the time needed to gather and analyse market data. The presented approach to forecasting market prices based on technical analysis indicators showed that it can be used by a wider range of market participants than fundamental analysis, which requires more extensive econometric knowledge.
... They are explained in detail in the subsections below. Wilder (1978) developed the parabolic SAR indicator to improve the fact that many technical indicators' trading signals are based on lagging. The indicator is normally used by traders to determine trend direction and potential reversals in price, and it uses a trailing "SAR" method to detect suitable exits and entry points. ...
... The stop level increases speed based on α (acceleration variable). Following Wilder (1978), we assume that α starts with 0.02, increasing by 0.02 whenever the new or high new low price is updated, with 0.2 being the maximum. Extreme Point (EP) is a local maximum or minimum price. ...
... In general, the CCI indicator has the disadvantage of being weak in sideways direction. Wilder (1978) also developed the RSI indicator that evaluates the strength of a trend as a percentage by quantifying the width when a price rises or falls. The indicator tracks market momentum through the speed and change in price movements. ...
The authors test the weak-form efficiency in cryptocurrency markets using the most recent and comprehensive data as of 2021. The authors apply various technical indicators to take a long or short position on 99 cryptocurrencies and compare the 10-day returns based on the technical trading strategies to the simple buy-and-hold returns. The authors find that the trading strategies based on single indicators or the combination of two indicators do not generate higher returns than buy-and-hold returns among cryptos. These findings suggest that cryptocurrency markets are weak-form efficient in general.
... where EM A t -exponential moving average for t days -Relative strength index (RSI) (Wilder, 1978) ...
... where p t = p high +p low +p close 3 -typical price, M A -moving average and M D -mean absolute deviation -Average directional movement index (ADX) (Wilder, 1978) • Current regime prediction Generally, the regimes w i,t are represented as three variables with the following constraints: ...
There are many ways to model complex time series. The simplest approach is to increase the complexity, and thus, the flexibility of the model, for the entire time series. As an example, one could use a neural network. Another solution would be to change the parameters of a model dependent on the "state" or "regime" of the time series. A typical example here would be the Hidden Markov model (HMM). This paper combines the two concepts to create a Reinforcement Learning (RL) model that adds variables that depend on the state of the time series. To test the concept, the RL model is used with cryptocurrency data to determine the share to invest into the cryptocurrency index CRIX in order to maximize wealth. The results have shown that cryptocurrency metadata is useful as supplementary data for analysis of the respective prices. The Reinforcement learning model with regimes shows potential for investment management, but comes with some caveats.
... It should also be noted that specifically for cryptocurrency, there can be several technical indicators that can be incorporated into the model [16,17]. These indicators are derived from historical price, volume, or open interest data and provide insights into potential future price movements or trends. ...
... When applied specifically to cryptocurrency datasets, machine learning algorithms such as decision trees and XGBoost deliver promising results and lower values of root mean squared error (RMSE) [16][17][18][19]. As seen in [7], RF models give better results than LSTM, which suggests the potential for LSTM models to become overly complex and necessitate regularization. ...
Cryptocurrency has the potential to reshape financial systems and introduce financial investments that are inclusive in nature, which has led to significant research in the prediction of cryptocurrency prices by employing artificial neural networks and machine learning models. Accurate short-term predictions are essential for optimizing investment strategies, minimizing risks, and ensuring market stability. Prior studies in time-series forecasting have successfully employed statistical methods like Auto-Regressive Integrated Moving Average (ARIMA) and machine learning algorithms such as Long Short-Term Memory (LSTM). The research results presented in this paper evaluate various statistical and machine learning algorithms, assessing their accuracy and effectiveness in modeling volatile cryptocurrency data for short-term forecasting. Additionally, the study explores diverse hyperparameter settings to enhance the performance of machine learning models. The highest performance is achieved by a hybrid model combining LSTM and Deep Neural Network (DNN), showcasing its effectiveness in forecasting cryptocurrency prices with improved accuracy and capability.
... The Relative Strength Index (RSI) serves as a momentum oscillator extensively utilized in technical analysis, providing insights into the velocity and extent of price movements within financial markets. Developed by J. Welles Wilder, RSI is instrumental in identifying potential overbought and oversold conditions, offering insights into potential reversals or corrections [10]. ...
... Starting with the common parameters indicated in previous iterations, we systematically adjusted one parameter at a time. For instance, the common setting for the Moving Average Convergence Divergence (MACD) is (12,26,9), we explored variations like MACD (10-14, 26, 9), MACD (12,(24)(25)(26)(27)(28)9), and MACD (12,26,(7)(8)(9)(10)(11). ...
... The RSI was developed by Welles [30] and defined as ...
... In this study, we consider n=14 days. RSI ranges from 0 to 100 after calculating RSI, and the buy and sells signals are generated as recommended in the original work by Wells [30] or as shown in Henderson [29] and the trading signal explains as follows: ...
In the dynamic realm of financial markets, developing effective strategies for stock exchange transactions is paramount. This research addresses this critical need by introducing a pioneering indicator for daily stock trading, leveraging a robust fuzzy inference system (FIS). The indicator ingeniously integrates key technical indicators including Moving Average Convergence and Divergence (MACD), Relative Strength Index (RSI), Stochastic Oscillator (SO), and On-Balance-Volume (OBV). The FIS is meticulously constructed based on expert opinions and gleaned fuzzy rules. The fuzzified values then serve as inputs to the FIS, which in turn generates signals indicating optimal actions: buy, hold, or sell stocks. To validate the importance of the FIS, a carefully curated selection of stocks from the NASDAQ stock exchange is employed for experimentation. To prove the efficiency of the FIS, the technical indicators and the fuzzy risk-adjusted returns are considered as alternatives and criteria, respectively. A novel Z-number-based technique for order preference by similarity to the ideal solution (TOPSIS) method is used to rank the technical indicators and the FIS. The comparative results unequivocally demonstrate that the developed FIS surpasses existing indicators, yielding superior returns.
... The RSI was developed by Welles [45] and defined as ...
... In this study, we consider n=14 days. RSI ranges from 0 to 100 after calculating RSI, and the buy and sells signals are generated as recommended in the original work by Wells [45] or as shown in Henderson [17] and the trading signal explains as follows: ...
... After testing numerous data pre-processing techniques accepted from various disciplines such as engineering, economics, and social sciences, we have identified a suitable method that meets the needs of reformulating a time series data into a new data form that is constrained to a limited range. Specifically, the method relies on the Relative Strength Index (RSI) developed by Wilder [1978]. RSI is a momentum oscillator index that is widely used in the field of economics to measure the speed and change of price shifts. ...
... Specifically, the RSI calculation for streamflow can be carried out in the following manner. To simplify its application, RSI is broken down into its basic components: average rise (AR), average fall (AF), and a duration of period (N RSI ) that contains the averaging intervals for AR and AF [Wilder, 1978]. The RSI is calculated as: ...
... One of the tools of technical analysis for accurate price forecasting are indicators that allow precise timing of the opening and closing of trades. Among the most popular technical analysis indicators is the RSI, first presented by Wilder [1978]. ...
Accurate forecasting of the level of volatility of financial instrument prices is important from the point of view of stock exchange investors. The aim of this paper is to measure the value relevance of transaction signals (buy/sell) by the relative strength index (RSI) in the case of State Treasury companies listed on the Warsaw Stock Exchange (WSE). The research covered the two hypotheses stating that stock buy (sell) transaction signals generated by the RSI indicator cause the occurrence of statistically significant positive (negative) abnormal returns (AR). These, in turn, support that RSI generates value-relevant signals, which are valuable investment tools and can be used to earn money on the stock exchanges. Based on the final research sample, including 75 buy signals and 88 sell signals, generated by the RSI indicator on the shares of State Treasury companies listed on WSE, an event study methodology was carried out. In 7-day event windows, calculations were made of AR, which is the difference between the realized and the expected return (estimated on the basis of the market model). The averaged ARs did not differ statistically significantly from zero on any of the tested days for both buy and sell signals. Therefore, research results do not indicate that share purchase (sell) transaction signals generated by the RSI indicator result in the occurrence of statistically significant positive (negative) average abnormal returns (AAR).
... The Average True Range (ATR) is a measure of market volatility. It calculates the average of the true range over a specified period (e.g., 14 days) [20]. The mathematical formula for the ATR indicator is given by: ...
Thanks to the high potential for profit, trading has become increasingly attractive to investors as the cryptocurrency and stock markets rapidly expand. However, because financial markets are intricate and dynamic, accurately predicting prices remains a significant challenge. The volatile nature of the cryptocurrency market makes it even harder for traders and investors to make decisions. This study presents a machine learning model based on classification to forecast the direction of the cryptocurrency market, i.e., whether prices will increase or decrease. The model is trained using historical data and important technical indicators such as the Moving Average Convergence Divergence, the Relative Strength Index, and Bollinger Bands. We illustrate our approach with an empirical study of the closing price of Bitcoin. Several simulations, including a confusion matrix and Receiver Operating Characteristic curve, are used to assess the model's performance, and the results show a buy/sell signal accuracy of over 92%. These findings demonstrate how machine learning models can assist investors and traders of cryptocurrencies in making wise/informed decisions in a very volatile market.
... The indicator was developed by J. Welles Wilder Jr. and introduced in his seminal 1978 book, New Concepts in Technical Trading Systems. [6] Mathematically, it is a bullish sign when RSI bypass 30, as well as it is a bearish sign bearish sign. In other words, it indicates the assets are overvalued if RSI is equal or above 70 which states a sell sign and undervalue if RSI is equal or below 30 which states a buy sign. ...
This study investigates three commonly used methods for timing stock trades and assesses their performance over a decade. The advent of new technologies has sparked a surge in the development of diverse trading strategies tailored for investment portfolio management. Nevertheless, the suitability of these strategies for portfolio integration varies, and some may yield adverse outcomes. For instance, a speculative trading approach might lead to significant losses. Using data spanning ten years, we evaluate the effectiveness of three main trading strategies that identify when stocks are likely to rise or fall, considering metrics such as return rate, Sharpe ratio, and maximum drawdown. Additionally, we explore potential improvements and the optimal scenarios for applying each strategy. Through this comprehensive analysis, our goal is to offer insights into how these strategies perform and when they're most effective. This information can be valuable for undergraduate-level investors in making informed decisions about managing their investment portfolios.
... Description of technical indicators. Source:[39][40][41][42][43][44].SMA (simple moving average) Average of prices over periods SMA = ∑ prices Rate of rise or fall in prices MOM = P t − P t−n BOP (balance of power) Volume to price change BOP =Table A2. Raw vs. clean 10-K and 10-Q document file sizes in megabytes. ...
In this work, we explore the application of deep reinforcement learning (DRL) to algorithmic trading. While algorithmic trading is focused on using computer algorithms to automate a predefined trading strategy, in this work, we train a Double Deep Q-Network (DDQN) agent to learn its own optimal trading policy, with the goal of maximising returns whilst managing risk. In this study, we extended our approach by augmenting the Markov Decision Process (MDP) states with sentiment analysis of financial statements, through which the agent achieved up to a 70% increase in the cumulative reward over the testing period and an increase in the Calmar ratio from 0.9 to 1.3. The experimental results also showed that the DDQN agent’s trading strategy was able to consistently outperform the benchmark set by the buy-and-hold strategy. Additionally, we further investigated the impact of the length of the window of past market data that the agent considers when deciding on the best trading action to take. The results of this study have validated DRL’s ability to find effective solutions and its importance in studying the behaviour of agents in markets. This work serves to provide future researchers with a foundation to develop more advanced and adaptive DRL-based trading systems.
... The default RSI setting is usually 14. The RSI formula defined by Tinghino (2008) and Wilder (1978), is expressed by the following equation: ...
This study aimed to apply the algorithmic trading strategy on major foreign exchange pairs and compare the performances of machine learning-based strategies and traditional trendfollowing strategies with benchmark strategies. It differs from other studies in that it considered a wide variety of cases including different foreign exchange pairs, return methods, data frequency, and individual and integrated trading strategies. Ridge regression, KNN, RF, XGBoost, GBDT, ANN, LSTM, and GRU models were used for the machine learning-based strategy, while the MA cross strategy was employed for the trend-following strategy. Backtests were performed on 6 major pairs in the period from January 1, 2000, to June 30, 2023, and daily, and intraday data were used. The Sharpe ratio was considered as a metric used to refer to economic significance, and the independent t-test was used to determine statistical significance. The general findings of the study suggested that the currency market has become more efficient. The rise in efficiency is probably caused by the fact that more algorithms are being used in this market, and information spreads much faster. Instead of finding one trading strategy that works well on all major foreign exchange pairs, our study showed it’s possible to find an effective algorithmic trading strategy that generates a more effective trading signal in each specific case.
... The technical indicators' detailed explanation is included in the research articles; [41,42]. Active traders extensively use them in the market as they are primarily designed to analyze short-term price movements [43][44][45][46][47][48][49][50]. ...
Real estate significantly contributes to the broader stock market and garners substantial attention from individual households to the overall country’s economy. Predicting real estate trends holds great importance for investors, policymakers, and stakeholders to make informed decisions. However, accurate forecasting remains challenging due to it’s complex, volatile, and nonlinear behavior. This study develops a unified computational framework for implementing state-of-the-art deep learning model architectures the long short-term memory (LSTM), the gated recurrent unit (GRU), the convolutional neural network (CNN), their variants, and hybridizations, to predict the next day’s closing price of the real estate index S &P500-60. We incorporate diverse data sources by integrating real estate-specific indicators on top of fundamental data, macroeconomic factors, and technical indicators, capturing multifaceted features. Several models with varying degrees of complexity are constructed using different architectures and configurations. Model performance is evaluated using standard regression metrics, and statistical analysis is employed for model selection and validation to ensure robustness. The experimental results illustrate that the base GRU model, followed by the bidirectional GRU model, offers a superior fit with high accuracy in predicting the closing price of the index. We additionally tested the constructed models on the Vanguard Real Estate Index Fund ETF and the Dow Jones U.S. Real Estate Index for robustness and obtained consistent outcomes. The proposed framework can easily be generalized to model sequential data in various other domains.
... Recently, a study was done on effective tactics in the Bitcoin market. Wilder (1978) analyzed the success rates of various trading methods, such as buy-and-hold strategies, moving average crossovers, and momentum-based approaches within cryptocurrency markets. The study states that momentum-driven approaches provide higher return alternatives, regardless of market conditions. ...
Introduction
The cryptocurrency market is captivating the attention of both retail and institutional investors. While this highly volatile market offers investors substantial profit opportunities, it also entails risks due to its sensitivity to speculative news and the erratic behavior of major investors, both of which can provoke unexpected price fluctuations.
Methods
In this study, we contend that extreme and sudden price changes and atypical patterns might compromise the performance of technical signals utilized as the basis for feature extraction in a machine learning-based trading system by either augmenting or diminishing the model's generalization capability. To address this issue, this research uses a bagged tree (BT) model to forecast the buy signal for the cryptocurrency market. To achieve this, traders must acquire knowledge about the cryptocurrency market and modify their strategies accordingly.
Results and discussion
To make an informed decision, we depended on the most prevalently utilized oscillators, namely, the buy signal in the cryptocurrency market, comprising the Relative Strength Index (RSI), Bollinger Bands (BB), and the Moving Average Convergence/Divergence (MACD) indicator. Also, the research evaluates how accurately a model can predict the performance of different cryptocurrencies such as Bitcoin (BTC), Ethereum (ETH), Cardano (ADA), and Binance Coin (BNB). Furthermore, the efficacy of the most popular machine learning model in precisely forecasting outcomes within the cryptocurrency market is examined. Notably, predicting buy signal values using a BT model provides promising results.
... Historicamente, dois métodos têm sido empregados para orientar decisões no (Wilder, 1978). ...
... The four indicators are listed and explained below: i. Relative strength indicator (RSI)This was introduced byWilder (1978) and is one of the most popular technical indicators. The values for RSI were obtained directly from Bloomberg. ...
Volatility is often used as a key input into several financial models, yet there is still no consensus on the best-performing model in forecasting stock market returns volatility. Conventional time series models such as GARCH are the preferred models in the literature. However, this project aims to first adopt two novel non-linear machine learning algorithms, namely the Random Forest and Artificial Neural Network (ANN). The project then compares the performance of these two models in predicting stock market realized volatility for the JSE Basic Material Index (JBIND) and the JSE Financials Index (JFIN) over a period of five years. Based on the results of the project, the Random Forest model outperformed the ANN model for both the JFIN and JBIND index. Lastly, the COVID effect on the model’s performance was also considered and the results show that the negative impact of COVID on the model’s performance is ambiguous.
... RSI pokazuje, czy na rynku panuje nadmierny optymizm czy pesymizm. Jak podaje Wilder (1978) oblicza się go następująco: ...
... O RSIé um indicador formulado por Wilder [1978]. Ele mede a relação entre forças compradoras e vendedoras do mercado para um determinado ativo.É calculado por: ...
... A stochastic oscillator (STOCH) is a momentum indicator that compares a close price of security to its price range over a specified period and indicates how highest or lowers security's closing price was in comparison to the preceding n periods [1]. Finally, the Average Directional Movement Index (ADX) was constructed by Wilder Jr. [25] and it is used to measure the strength of the trend. After obtaining all data and calculating each of the previously mentioned technical indicators, the initial dataset can be defined in the form of supervised dataset ...
The paper examines the factors that influence Bitcoin price direction from the perspective of machine learning (ML) models. The observed factors cover Bitcoin market data, technical indicators, blockchain variables, sentiment analysis, and other macro-financial variables. Logistic Regression (LR), Random Forest (RF), and Support Vector Machine (SVM) classifiers are employed. Three train-test ratios are considered. Grid search and blocking time series cross-validation are used to adjust the hyperparameters of the proposed ML algorithms resulting in the three most accurate models for each train-test ratio. Variables that affect the next-day price direction are ranked using LR and RF best models. For each method and train-test ratio, the smallest subsets of independent variables with the highest test set accuracy were chosen to reduce dimensionality. Models show that technical indicators influence daily Bitcoin price direction the most, followed by blockchain and Bitcoin market variables. Contrarily, models disagree on the importance of Tweets and macro-financial variables. Finally, SVM performed better on the test set when the LR optimal sets of independent variables were considered, indicating that the analysis of individual factors' influence on the Bitcoin price is not important only for corresponding model. Combining only influential independent variables and 90:10 train-test ratio yielded the greatest accuracy of 58.18 % achieved by RF model.
... İndikatör, hisse senedinin kapanış değerlerinin yukarı ve aşağı yönlü hareketlerini kıyaslayarak, fiyatların hangi yöne gideceğini belirlemeye çalışır. RSI hesaplanmasında kullanılan formül aşağıdaki gibidir (Wilder 1978). ...
Bu çalışmanın amacı; yatırımcılar tarafından yaygın şekilde kullanılan RSI, MACD, Stokastik ve Bollinger Bandı indikatörlerinin Borsa İstanbul Turizm Sektöründe işlem görmekte olan hisse senetleri üzerindeki performanslarını karşılaştırmaktır. Bu bağlamda, hisse senetlerinin günlük kapanış değerleri Matriks Veri Tabanı ile analiz edilmiştir. Teknik indikatörlerin alım satım kararları dikkate alınarak karlı işlem yüzdeleri, ortalama kazanç/ ortalama kayıp oranları ve elde ettikleri getiri oranları analiz edilmiştir. Geçmişe yönelik yapılan testler sonucunda, RSI(50) indikatörü al ve tut stratejisine göre daha iyi performans gösterirken diğer indikatörler al ve tut stratejisine göre daha düşük performans göstermiştir. Çalışma sonucunda, RSI(50) indikatörü alım satım sinyalleri ile oluşturulan sistemlerde etkin piyasalar hipotezi ve rassal yürüyüş teorisi varsayımları reddedilirken, RSI(30-70), MACD, Stokastik ve Bollinger Bandı indikatörleri ile oluşturulan sistemlerde etkin piyasalar hipotezi ve rassal yürüyüş teorisinin varsayımlarının geçerli olduğu sonucuna ulaşılmıştır.
... The RSI values vary from 0 to 100. Usually, an RSI exceeding 70 implies that stocks are overbought, while an RSI falling below 30 implies that stocks are oversold [32]. We used the RSI to assess stock trends and trading directions. ...
Efficient stock status analysis and forecasting are important for stock market participants to be able to improve returns and reduce associated risks. However, stock market data are replete with noise and randomness, rendering the task of attaining precise price predictions arduous. Moreover, the lagging phenomenon of price prediction makes it hard for the corresponding trading strategy to capture the turning points, resulting in lower investment returns. To address this issue, we propose a framework for Important Trading Point (ITP) prediction based on Return-Adaptive Piecewise Linear Representation (RA-PLR) and a Batch Attention Multi-Scale Convolution Recurrent Neural Network (Batch-MCRNN) with the starting point of improving stock investment returns. Firstly, a novel RA-PLR method is adopted to detect historical ITPs in the stock market. Then, we apply the Batch-MCRNN model to integrate the information of the data across space, time, and sample dimensions for predicting future ITPs. Finally, we design a trading strategy that combines the Relative Strength Index (RSI) and the Double Check (DC) method to match ITP predictions. We conducted a comprehensive and systematic comparison with several state-of-the-art benchmark models on real-world datasets regarding prediction accuracy, risk, return, and other indicators. Our proposed method significantly outperformed the comparative methods on all indicators and has significant reference value for stock investment.
Crafting a lucrative stock trading strategy is pivotal in the realm of investments. However, the task of devising such a strategy becomes challenging task the intricate and ever-changing situation of the stock market. In recent years, with the development of artificial intelligence (AI), some AI technologies have been proven to be successfully applied in stock price and asset management. For example, long short-term memory networks (LSTM) can be used for predicting stock price variation, reinforcement learning (RL) can be used for control stock trading, however, they are generally used separately and cannot achieve simultaneous prediction and trading. In this study, we propose a hybrid deep learning model to predict stock prices and control stock trading to manage assets. LSTM is responsible for predicting stock prices, while RL is responsible for stock trading based on the predicted price trends. Meanwhile, to reduce uncertainty in the stock market and maximize stock assets, the proposed LSTM model can predict the average directional index (ADX) to comprehend the stock trends in advance and we also propose several constraints to assist assets management, thereby reducing the risk and maximizing the stock assets. In our results, the hybrid model yields an average R ² value of 0.94 when predicting price variations. Moreover, employing the proposed approach, which integrates ADX and constraints, the hybrid model augments stock assets to 1.05 times than initial assets.
The efficacy of Long Short-Term Memory (LSTM) neural networks and attention-based models in predicting next-day closing prices of the MSFT 500index is meticulously examined. A comprehensive suite of nine carefully chosen predictors spanning fundamental market data, macroeconomic indicators, and technical metrics is amalgamated, fostering a holistic comprehension of market behavior. Through rigorous analysis, the research evaluates single-layer and multilayer LSTM architectures alongside attention- based LSTM variants, juxtaposed against traditional ARIMA models. Surprisingly, the single-layer LSTM consistently outperforms its multilayer counterpart, demonstrating superior accuracy and model fit. The integration of corporate accounting statistics augments predictive capabilities, enriching the models' efficacy. Notably, attention-based LSTM models, particularly the Attention-LSTM variant, exhibit markedly lower prediction errors and higherreturns in trading strategies compared to other methodologies. However, the heightened complexity of stacked-LSTM structures fails to surpass the predictive acumen of simpler LSTM architectures.This inquiry underscores the paramount importance of leveraging advanced AI techniques and comprehensive datasets in navigating the intricate nuances of modern financialmarkets, offering invaluable insights for both researchers and practitioners engaged in stock priceforecasting endeavors.
This study aims to examine the impact of financial reporting quality on the returns realized for investors, who use value and momentum strategies for trading in the stock market, and its implications on the stock market performance.Thus, stock portfolios are formed on a quarterly basis Based on the book-to-market ratio of the share as a proxy for value strategy portfolios, and according to (Jegadeesh, et al., 1993) methodology for momentum strategy portfolios. The study sample consists of 112 companies listed in the Egyptian stock market that yield 5,100 (Firm-Quarter) observations during 2008-2020. To test the study hypotheses, the Multiple Linear Regression model and the Path Analysis method are employed. The results showed a positive association between the financial reporting quality and the returns of value strategy portfolios. Additionally, the findings revealed that there is no significant association between the quality of financial reports and the returns of momentum strategy portfolios. Furthermore, the results showed that there is a significant direct association between the returns of value strategy portfolios and the market performance indicators. However, the association between the returns of the momentum strategies portfolios and market performance indicators were varied, and there is no direct association between the financial reporting quality and market performance indicators. Nevertheless, the return of value strategy totally mediate relationship between the financial reporting quality and market performance indicators.
Keywords: Financial Reporting Quality, Value Strategy, Momentum Strategy, Stock Market Performance indicators.
Understanding the past, current, and future dynamics of dengue epidemics is challenging yet increasingly
important. To date, many techniques across statistics, mathematics, and machine learning have provided
us with quantitative tools for studying dengue epidemics. Here, using data from provinces in northern
Peru across 2010 to 2021, we provide a new interdisciplinary pipeline that draws on a new and existing
techniques to provide comprehensive understanding and robust prediction of dengue epidemic dynamics.
Wavelet analyses can unveil spatiotemporal patterns in epidemic dynamics across annual and multi-
annual time periods. Here, these included climatic forcing and greater spatial similarity in large outbreak
years. Space-varying epidemic drivers included climatic influences and shorter pairwise distances driv-
ing greater epidemic similarity in more northerly coastal provinces. Then, using a Bayesian model,
we can probabilistically quantify the timing, structure, and intensity of such climatic influences on
Dengue Incidence Rates (DIRs), while simultaneously considering other influences. Recognising that
a single model is generally sub-optimal for any forecasting task, we demonstrate how to form trained
and untrained probabilistic ensembles for forecasting dengue cases in settings reflective of real-world
conditions. We introduce a suite of climate-informed and covariate-free deep learning approaches that
leverage big data and foundational time series, temporal convolutional networks, and conformal infer-
ence. We complement these modern techniques with statistically principled training and assessment of
ensemble frameworks, while explicitly considering strong benchmark models, computational costs, pub-
lic health priorities, and data availability limitations. In doing so, we show how ensemble frameworks
consistently outperform individual models across space and time, and produce sharp and accurate fore-
casts with robust, reliable descriptions of uncertainty. We report interpretable classification metrics for
detection of outbreaks to communicate our outputs with the wider public and public health authorities.
Looking forward, whether the objective is to understand and/or to predict epidemic dynamics, our
modelling pipeline can be used in any dengue setting to robustly inform the decision-making and
planning of public health authorities.
This study presents a decision support system for stock market investors that combines technical analysis with fuzzy logic. The system utilizes four essential technical indicators—Moving Average Convergence/Divergence (MACD), Relative Strength Index (RSI), Stochastic Oscillator (SO), and On-Balance Volume (OBV)—to predict future price movements. These indicators are mapped as inputs into a fuzzy inference system, where fuzzy rules and membership functions are applied to generate trading recommendations, categorized as Bullish, Neutral, or Bearish. Experiments using MATLAB with data from 10 Indian banks demonstrate that the system effectively predicts stock movements and improves investment decisions when integrated with additional market information and investor insights
Financial forecasting involves predicting the future financial states and performance of companies and investors. Recent technological advancements have demonstrated that machine learning-based models can outperform traditional financial forecasting techniques. In particular, hybrid approaches that integrate diverse methods to leverage their strengths have yielded superior results in financial prediction. This study introduces a novel hybrid model, entitled EMD-TI-LSTM, consisting of empirical mode decomposition (EMD), technical indicators (TI), and long short-term memory (LSTM). The proposed model delivered more accurate predictions than those generated by the conventional LSTM approach on the same well-known financial datasets, achieving average enhancements of 39.56%, 36.86%, and 39.90% based on the MAPE, RMSE, and MAE metrics, respectively. Furthermore, the results show that the proposed model has a lower average MAPE rate of 42.91% compared to its state-of-the-art counterparts. These findings highlight the potential of hybrid models and mathematical innovations to advance the field of financial forecasting.
The currency market is one of the main markets of the world's modern financial and economic systems. With respect to the availability of information, this market is the most data-rich and public. These two features allow it to be viewed as volatile. This study aims to assess the dependence of the currency market's volatility on the conditions and factors that formed during the COVID-19 pandemic. The research used statistical and correlation analysis and general scientific methods. Correlation analysis revealed an insignificant effect of the dollar index on the change in currency market volatility during the COVID-19 pandemic (r = 0.09). The outcomes indicated the impact of the disease factor on currency trading at the 0.8% level (r2 = 0.0081). The research conclusions suggest that the effects of information on the currency market differed during 2015-2019 and deviated in response to various political and economic events. The study highlights that the COVID-19 pandemic and its aftermath did not significantly influence the currency pairs' volatility. In the future, if crisis trends re-emerge, the findings of this study may influence the behavior of investors and participants in global trade. This could affect their investment decisions, currency reserve diversification, insurance strategies, and capital migration.
The consideration of environmental, social, and governance (ESG) aspects has become an integral part of investment decisions for individual and institutional investors. Most recently, corporate leaders recognized the core value of the ESG framework in fulfilling their environmental and social responsibility efforts. While stock market prediction is a complex and challenging task, several factors associated with developing an ESG framework further increase the complexity and volatility of ESG portfolios compared with broad market indices. To address this challenge, we propose an integrated computational framework to implement deep learning model architectures, specifically long short-term memory (LSTM), gated recurrent unit, and convolutional neural network, to predict the volatility of the ESG index in an identical environment. A comprehensive analysis was performed to identify a balanced combination of input features from fundamental data, technical indicators, and macroeconomic factors to delineate the cone of uncertainty in market volatility prediction. The performance of the constructed models was evaluated using standard assessment metrics. Rigorous hyperparameter tuning and model-selection strategies were implemented to identify the best model. Furthermore, a series of statistical analyses was conducted to validate the robustness and reliability of the model. Experimental results showed that a single-layer LSTM model with a relatively small number of neurons provides a superior fit with high prediction accuracy relative to more complex models.
The rapid evolution of cryptocurrency markets and the increasing complexity of trading strategies necessitate a comprehensive understanding of price-prediction models and their direct impact on trading efficacy. While extensive research has been conducted separately on price prediction methods and trading strategies, there remains a significant gap in studies explicitly correlating precise price forecasts with successful trading outcomes. This review paper addresses this gap by critically examining the role of accurate cryptocurrency price predictions in enhancing trading strategies. We conducted a systematic review of sufficient scholarly articles and web resources, focusing on the methodologies and effectiveness of various predictive models and their integration into cryptocurrency trading strategies. Our selection criteria ensured the inclusion of papers that demonstrate methodological rigor, relevance, and recent contributions to the field, spanning from economic theories and statistical models to advanced machine learning techniques. The findings reveal that precise price predictions significantly contribute to the development of adaptive and risk-managed trading strategies, which are crucial in the highly volatile cryptocurrency market. The review also identifies current challenges and proposes directions for future research, emphasizing the need for interdisciplinary approaches and ethical considerations in predictive modeling. This synthesis aims to bridge the existing research gap and guide future studies, thereby fostering more sophisticated and profitable trading strategies in the cryptocurrency domain.
We analyze return predictability for U.S. sectors based on fundamental, macroeconomic, and technical indicators and analyze whether return predictions improve tactical asset allocation decisions. We study the out-of-sample predictive power of individual variables for forecasting sector returns and analyze multivariate predictive regression models, including OLS, regularized regressions, principal component regressions, the three-pass regression filter, and forecast combinations. Using an out-of-sample Black–Litterman portfolio optimization framework and employing predicted returns as investors’ ‘views’, we evaluate the benefits of sector return forecasts for investors. We find that portfolio optimization with sector return prediction models significantly outperforms portfolios using historical averages as well as passive benchmark portfolios.
The shipping industry transports nearly 80% of the goods worldwide and requires large funding. The shipping industry shifted from debt to equity as the source of funding in the last decade. Because most shipping companies already had their initial public offering before 2013, these companies tend to engage in follow-on equity offerings (FPO). However, the challenge faced by the shipping companies is the lack of knowledge on successful FPO. The purpose of this study is to identify the most influential factors affecting shipping companies’ FPO from the investor perspective. This research applies a hybrid multiple-criteria decision-making model integrating the fuzzy-Delphi method and Decision-Making Trial and Evaluation Laboratory, processing survey responses covering four dimensions and 16 criteria from 33 investment experts. The results show that financial indicator is the primary cause affecting offering condition, technical indicators. An increase in earnings per share would help the financial performance of the shipping companies to appear most attractive to investors.
Algorithmic trading, a widespread practice in the financial industry, is based on the automatic signal generation based on trading rules of one or more technical analysis indicators. Generally, the parameters for computing the indicators (such as the time windows), the trading rules (converting the indicator into a trading signal) and the weights for signal aggregation (for combining the signals from a plurality of indicators) are established by the trader based on her experience and are treated as fixed inputs of the trading algorithm. In recent literature, simple optimization systems are introduced by varying only one category of parameters at a time, that is only the indicators setting, only the trading rules definition, or only the signal aggregation while keeping the remaining parameters fixed. Our research goes further and proposes an automated trading system based on simultaneous optimization of the three categories of parameters. More precisely, we consider four technical indicators widely used in financial practice, the Exponential Moving Average, the Relative Strength Index, the Moving Average Convergence/Divergence, and the Bollinger Bands and we determine the optimal signal aggregation, trading rule definition and indicator setting using the Particle Swarm Optimization metaheuristic over a commonly used fitness function, that is the net capital at the end of the trading period. We apply our trading system to the Italian index FTSE MIB and to a set of financial stocks belonging to the FTSE MIB over a multi-year period for training and testing. We generally achieve superior performance both in sample and out of sample, using a standard technical analysis system as a benchmark. Furthermore, we successfully verify the ability of the optimized trading system to accurately classify the stock price trends.
This method explores the application of the Prophet model to forecasting Bitcoin prices, emphasising the integration of technical indicators such as RSI and MACD, along with other pivotal market factors such as Volume, Market Cap, Percent Change on multi-timeframes from 1 hour to 7 days, Halving Event, and Mining Reward. The paper delves into the mathematical formulations of these indicators and elucidates their relevance within the predictive model, providing a comprehensive understanding of their impact on forecasting precision.
Recently, a substantial body of literature in finance has implemented deep learning algorithms as predicting approaches. The principal merit of these methods is the ability to approximate any nonlinear and linear behaviors without understanding the data generation process, making them suitable for predicting stock market movement. This paper explores deep learning approaches to forecast stock price movement in the Hong Kong stock market. The forecasting performance of a temporal convolutional network (TCN) approach and several recurrent neural network (RNN) models is compared. The results show that the TCN can outperform all compared RNN models. Further parameter tuning results also show the superiority of the TCN approach. In addition, we demonstrate that a profitable strategy can be built based on the forecasting results of the proposed model.
Dollar-cost averaging (DCA) is a popular investment strategy for retail investors, but its performance is generally inferior to lump-sum investing. In this study, we test modifications to improve the performance of DCA while keeping its simplicity, based on the Relative Strength Index (RSI) and CBOE Volatility Index (VIX). We define varying upper and lower bounds for RSI and VIX values, increasing investment to varying degrees in the asset when below the lower bound and vice versa when above the upper bound. We tested these strategies on 5 assets: Bitcoin, the S &P500, Gold, Crude oil, and the NASDAQ. We tested 300 variations of DCA strategies, based on price data from 2 January 2017 to 27 December 2021. To evaluate performance, we calculated 5-year Sharpe ratios for each tested strategy. The best performing RSI-weighted strategies outperformed pure DCA by statistically significant margins (p < 0.05) for 3 assets: Bitcoin (Sharpe = 1.984 vs 1.424, p = 0.0330), Crude oil (Sharpe = 1.570 vs 0.4174, p = 0.0223) and the NASDAQ (Sharpe = 1.923 vs 0.0491, p = 0.0034). This suggests that RSI-weighted strategies are viable regardless of asset class. Although all VIX-weighed strategies underpeformed pure DCA, an opposite version of our tested strategy could produce profits. Our results show that RSI-weighted DCA is a viable way to improve the profitability of DCA while keeping it simple enough for retail investors to execute.
In the context of education, people are looking for more ways to facilitate the teaching and learning of young adults. As a result, they see technology as a way to help in these activities. This paper presents a mobile software application called QUIMAPP. This tool provides chemistry content schematically to support teaching and learning in Adult Education. Potential users evaluated the tool's usability using the Technology Acceptance Model (TAM), with positive results indicating great potential for its goals.
Borsa analizi, geleceğe yönelik tahminler yapmak için finansal, politik ve sosyal göstergeleri göz önünde bulundurarak borsayı inceler ve değerlendirir. Büyük veri ve derin öğrenme teknolojilerindeki gelişmelerin çığır açan sonuçları, araştırmacıların ve endüstrinin dikkatini bilgisayar destekli borsa analizine çekmektedir. Geleneksel makine öğrenimi ve derin öğrenme modellerini kullanarak borsa analizi konusunda çeşitli çalışmalar bulunmaktadır. Bu çalışmada, temel model olarak Otoregresif Entegre Hareketli Ortalama (ARIMA) yöntemini tekrarlayan sinir ağlarının üç farklı modeliyle karşılaştırılmıştır; Uzun Kısa Süreli Bellek (Long Short Term Memory- LSTM) ağları, Geçitli Tekrarlayan Birim (Gated Recurrent Unit- GRU), dikkat katmanlı LSTM modeli. Bu çalışmada literatürdeki diğer çalışmalardan farklı olarak 28 tane finansal indikatör kullanılarak Borsa İstanbul verileri üzerinde gün içi tahminler yaparken dört farklı modelin sonuçları karşılaştırılmıştır. İstatistiksel ve doğrusal bir model olan ARIMA, zaman serileri tahmini için doğrusal olmayan RNN modelleri ile karşılaştırılmıştır ancak 3 sinir ağı modelinden de yüksek ortalama hata oranına sahip olduğu görülmüştür. LSTM sonuçları GRU modeline çok yakın olsa da GRU diğerlerinden biraz daha iyi performans göstermektedir. Dikkat mekanizmalı sinir ağı diğer temel sinir ağlarından daha iyi sonuç vermemektedir.
ResearchGate has not been able to resolve any references for this publication.