An Intelligent System for Determination of Stop – Loss and Take – Profit Limits: A Dynamic Decision Learning Approach

Stock market prices are notoriously difficult to predict for traders and investors alike. However, accurate stock market price predictions can result in high returns and substantial percentages of returns for investors and traders. Unfortunately, stock price data is inherently complex, noisy, and nonlinear, making it a challenging task. As technology continues to advance, trading strategies are beginning to adapt to automated systems instead of relying on manual analysis. Dynamically determining buying and selling levels in automated systems has become increasingly important. Many traders and investors seek to minimize losses and maximize profits by utilizing technical analysis methods and implementing stop-loss and take-profit strategies. Technical analysis methods are commonly used by traders and investors to determine and set predetermined thresholds for existing positions, as well as enter positions with stop-loss and take-profit orders. In this study, the main objective is to determine stop-loss and take-profit levels dynamically by analysing historical data using standard deviation and Sharp Ratios. To decide on the selling (short) or buying (long) position, TP\SL levels have been divided into two separate parts with different approaches. The approaches in this study aim to compare the end-of-day Open to Close returns with TP\SL level returns to determine the best course of action. Overall, this study aims to develop effective trading strategies that can minimize losses and maximize profits in the volatile world of stock market trading.