AUTOMATED FOREX CHART PATTERN RECOGNITION SYSTEM USING MACHINE LEARNING
Abstract
ABSTRACT
The Automated Forex Chart Pattern Recognition System Using Machine Learning is designed to automate the detection and classification of common chart patterns used in the technical analysis of foreign exchange (forex) markets. Traditional manual identification of chart patterns such as head and shoulders, double tops, triangles, and flags is often time-consuming and prone to human error, especially in fast-moving markets. This project leverages machine learning algorithms and computer vision techniques to analyze forex price data, recognize visual trends, and generate reliable trading signals in real time. The system processes both historical and live forex data, converting price movements into structured visual representations. A trained model then identifies recurring chart formations and provides traders with potential entry and exit points. Through testing and evaluation, the model achieved an average accuracy above 85%, demonstrating strong performance in detecting key reversal and continuation patterns across multiple currency pairs. Overall, this project highlights how artificial intelligence can enhance technical analysis by improving speed, consistency, and decision-making accuracy. The system serves as a practical tool for traders, researchers, and developers seeking to integrate intelligent automation into modern forex trading strategies.
Full-Text Access Notice
In accordance with the NERD Policy on promoting peer-reviewed publication, public access to the full text of a project, thesis or dissertation is restricted for three years, allowing the author and supervisors sufficient time to pursue peer-reviewed publication.
During this period, researchers with legitimate academic or research purposes may request authorisation directly from the author to enable NERD to release the indexed full texts of the work using the form below.