Hybrid Forex prediction model using multiple regression, simulated annealing, reinforcement learning and technical analysis

Jamali, Hana; Chihab, Younes; García‐Magariño, Iván; Bencharef, Omar

doi:10.11591/ijai.v12.i2.pp892-911

Cited by 6 publications

(3 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When we look at the work done on the algorithms used for FTSERF, we can see that researchers in both public and private institutions have tried out all the machine learning tools that are available. Those tools may be supervised, such as classification [1], regression [2], recommender systems [3], and reinforement learning [4]. They also include unsupervised algorithms, such as clustering and association analysis, ranking, and anomaly detection techniques [5].…”

Section: Introductionmentioning

confidence: 99%

Financial Time Series Forecasting: A Data Stream Mining-Based System

2023

View full text Add to dashboard Cite

Data stream mining (DSM) represents a promising process to forecast financial time series exchange rate. Financial historical data generate several types of cyclical patterns that evolve, grow, decrease, and end up dying. Within historical data, we can notice long-term, seasonal, and irregular trends. All these changes make traditional static machine learning models not relevant to those study cases. The statistically unstable evolution of financial market behavior yields a progressive deterioration in any trained static model. Those models do not provide the required characteristics to evolve continuously and sustain good forecasting performance as the data distribution changes. Online learning without DSM mechanisms can also miss sudden or quick changes. In this paper, we propose a possible DSM methodology, trying to cope with that instability by implementing an incremental and adaptive strategy. The proposed algorithm includes the online Stochastic Gradient Descent algorithm (SGD), whose weights are optimized using the Particle Swarm Optimization Metaheuristic (PSO) to identify repetitive chart patterns in the FOREX historical data by forecasting the EUR/USD pair’s future values. The data trend change is detected using a statistical technique that studies if the received time series instances are stationary or not. Therefore, the sliding window size is minimized as changes are detected and maximized as the distribution becomes more stable. Results, though preliminary, show that the model prediction is better using flexible sliding windows that adapt according to the detected distribution changes using stationarity compared to learning using a fixed window size that does not incorporate any techniques for detecting and responding to pattern shifts.

show abstract

Section: Introductionmentioning

confidence: 99%

Financial Time Series Forecasting: A Data Stream Mining-Based System

2023

View full text Add to dashboard Cite

show abstract

“…Both technical analysis and fundamental analysis can be used to forecast FOREX prices. While technical analysis only uses historical time series data to make FOREX market predictions, the fundamental analysis considers various variables, including the company's and the nation's economic and industrial conditions [5]. Algorithmic trading refers to trading in which automated programmed algorithms implement orders instead of human traders.…”

Section: Introductionmentioning

confidence: 99%

FOREX Prices Prediction Using Deep Neural Network and FNF

Moustafa,

Fakhr,

Maghraby

2023

IJACSA

View full text Add to dashboard Cite

One of the largest financial markets on the planet is the foreign exchange (FOREX) market. Banks, retail traders, businesses, and individuals trade more than $5.1 trillion in FOREX daily. It is very challenging to predict prices in advance due to the market's complex, volatile, and highly fluctuating nature. In this study, the new FOREX Normalization Function (FNF) is proposed and used with different models to predict the prices of the AUD/USD, EUR/USD, USD/JPY, CHF/INR, USD/CHF, AUD/JPY, USD/CAD, and GBP/USD. Two models are proposed in this study. The first model contains FNF as a normalization and feature extractor, followed by a Convolutional Neural Network (CNN). The second model utilizes FNF and a Support Vector Regressor(SVR). The forecasts are set for a oneday timeframe, with predictions made for 1, 3, 7, and 15 days ahead. The efficient ability of the proposed method to solve the FOREX prediction problem is proven by performing experiments on nine real-world datasets from different currencies. Additionally, the models are evaluated using Mean Absolute Error (MAE) and Mean Squared Error (MSE). Applying the presented models to 9 different datasets improved the results by an average between 0.5% and 58% of MAE.

show abstract

“…Existing research and journals primarily focus on technical indicators in Forex trading, with limited studies specifically addressing money management. For instance, studies such as [10] and [11] only examined trading strategies without incorporating money management strategies. Therefore, this study tries to give more contributions to money management analysis for forex trading.…”

Section: Introductionmentioning

confidence: 99%

Comparative Analysis of Reverse Martingale And Cumulative Win Strategies Using Ichimoku Kinko Hyo Indicator

Wendy,

Sunardi Oetama

2023

International Journal of Science, Technology & Management

View full text Add to dashboard Cite

Given the dearth of prior research on the practical implementation of money management strategies in the foreign exchange market, making it arduous to ascertain profitable money management comparisons, this study places its focus on the amalgamation of money management strategies and technical indicators. The research specifically explores the utilization of two money management strategies, namely reverse martingale, and cumulative win strategy, in conjunction with Ichimoku Kinko Hyo serving as the chosen technical indicator. The primary aim of this research endeavor is to identify the most lucrative money management combination within a three-year timeframe. The study centers on the EURUSD currency pair, employing the H1 timeframe for analysis. The research methodology encompasses four essential stages: data collection, data processing, strategy testing, and result analysis. Subsequently, the acquired EURUSD data will undergo amalgamation utilizing the One-Way ANOVA method to determine the presence of statistically significant disparities between the two combinations. The outcomes of this investigation underscore the supremacy of the cumulative win strategy and Ichimoku Kinko Hyo combination, exhibiting a remarkable Return on Investment (ROI) surpassing alternative combinations, soaring to an impressive figure exceeding 2860%.

show abstract

Hybrid Forex prediction model using multiple regression, simulated annealing, reinforcement learning and technical analysis

Cited by 6 publications

References 19 publications

Financial Time Series Forecasting: A Data Stream Mining-Based System

Financial Time Series Forecasting: A Data Stream Mining-Based System

FOREX Prices Prediction Using Deep Neural Network and FNF

Comparative Analysis of Reverse Martingale And Cumulative Win Strategies Using Ichimoku Kinko Hyo Indicator

Contact Info

Product

Resources

About