Predicting Stock Market Trends Using Machine Learning and Deep Learning Algorithms via Continuous Binary Data

• Python
• Machine Learning

The nature of stock market movement has always been ambiguous for investors because of various influential factors. This project aims to significantly reduce the risk of trend prediction with machine learning and deep learning algorithms. In this project, we concentrate on comparing predicting performance of different machine learning models and deep learning approaches to prognosticate stock market movement. Numerous specialized indicators are applied as inputs to our models. Our project includes two different approaches for inputs, continuous data and binary data, the effect of pre-processing; the former uses stock trading data (open, close, high and low values) while the latter employs pre-processing step to convert continuous data to binary one. Each specialized indicator has its specific possibility of upward or down movement predicated on market integral properties. The performance of the mentioned models is compared for the both approaches with classification metrics, and the best tuning parameter for each is reported. All experimental tests are done with old times of historical data of four stock market groups that are completely pivotal for investors. The future up or down trend is associated and when binary data is given as the input values to the predictors, we enter data with a recognized trend based on each feature's property.