Predictive Model of Publicly Traded Stocks, using Python

Abstract

This article presents a predictive model for analyzing the behavior of stocks traded on the stock exchange using the Python programming language. Stock price prediction is a crucial area for investors seeking to maximize returns and minimize risks. Through advanced machine learning techniques and data analysis, the model is trained with historical data to predict future stock behavior. The process includes data cleaning and transformation, the selection and application of appropriate analysis methods, and the evaluation of model performance. The results show high accuracy in predictions, with a coefficient of determination R2 of 0.999513, indicating a strong correlation between predicted values and actual data. This level of precision can be very useful for investors and financial analysts, providing a reliable tool for informed decision-making. The article also discusses the practical implications of these findings, including the importance of data quality and model selection in prediction success. Future research directions are proposed, such as integrating sentiment analysis and other external factors to further enhance model accuracy and robustness. This study contributes to the field of financial prediction and offers a practical and effective methodology for stock market analysis using Python.