Object Detection Approach for Stock Chart Patterns Recognition in Financial Markets

Abstract

Technical analysis is a chart-based method, from price movements and trading volume of stocks to analyze movements to make trend predictions and make real buying and selling decisions. Pattern-based technical analysis is one of the most effective for stock market volatility. The problem analysts often face is that looking for patterns wastes time and effort with thousands of stock symbols. This research aims to apply object detection techniques to analyze and recognize chart patterns, thus evaluating the accuracy of price action candlesticks. However, image data of the patterns on the candlestick chart is too scarce. We built an image dataset consisting of four patterns: Head and Shoulder, reverse Head and Shoulders, Double Top, and Double Bottom. Candlestick charts' distinctive shape makes it challenging to discern precise patterns, and segmentation has been used in the data processing section to reduce candlestick chart noise. Moreover, data collection also encountered the problem of time and effort. So the method to generate variable data uses possible patterns to enrich the data set. The experiments reveal that performance in detecting patterns is described later in this article.