Stock price prediction of PayPal by Linear Regression, SVM, Random Forest and LSTM

Abstract

This research paper undertakes an extensive and detailed examination of four distinct machine learning models, specifically Linear Regression, Support Vector Machine (SVM), Random Forest, and Long Short-Term Memory (LSTM). The stock values of PayPal are forecast employing these techniques, and Python serves as the fundamental tool in facilitating a comprehensive and thorough evaluation of their efficacy in predicting trends in the financial market. In the realm of methodology, this study encompasses a multifaceted approach. Python forms the cornerstone for data analysis, model development, and testing. The data collection process encompasses historical stock price data for PayPal, alongside an array of relevant economic indicators. The core of the study lies in the comparative analysis of the four machine learning models. Each model is rigorously tested against historical data, allowing for a nuanced understanding of their strengths and weaknesses. Linear Regression, remarkably, emerges as the standout performer in terms of predictive accuracy and consistency. This firmly establishes Linear Regression as the optimal choice for forecasting stock prices. The significance distinction of this research extends beyond its findings. It advances the discipline of financial forecasting by illuminating the comparative effectiveness of different models, offering valuable insights for guiding future research initiatives within this domain. The integration of advanced methodologies and the clear-cut conclusion regarding Linear Regression's superiority underscore the pivotal role of this study in enhancing the precision of financial market trend forecasting.