Prediction of Technical Indicators for Stock Markets using HPO-CCOA Based Machine Learning Algorithm

Predicting the Stock Market's behaviour has become an enormous requirement, making it one of the most active study fields. Stock market forecasting is notoriously difficult and calls for a deep dive into the facts. To address this problem and provide a workable solution, we need to employ targeted statistical models and AI-powered algorithms. Several different deep learning and machine learning algorithms can generate a reliable forecast with little room for mistake. Due to the significant degree of uncertainty surrounding technical indicators, they tend to have a disproportionate impact on stock market forecasts. When compared to other methods created for financial market prediction, AI methods demonstrate superior prediction efficiency. In order to forecast the stock market index, this study employs a Machine Learning-based Hyper-parameter tuning optimisation procedure (HPO). During pre-processing, data is first cleaned and normalised to improve classification precision. The Crisscross Optimisation Algorithm (CCOA) is then used to fine-tune the HPO once K-Nearest Neighbour (KNN) has been applied. Using three publicly accessible datasets, this study presents a thorough analysis of the methods used to forecast stock prices, discusses the difficulties encountered, and looks ahead to the potential for further research in this area.