Stock Price Prediction using Machine Learning

• Published in: 2024 3rd International Conference on Artificial Intelligence For Internet of Things (AIIoT) pp. 1 - 5
• Main Authors: Vardhan, Marepalli Vishnu, Jaffino, G
• Format: Conference Proceeding
• Language: English
• Published: IEEE 03.05.2024
• Subjects: Adaptation models; AutoTS; Costs; Estimation; Libraries; LSTM; Machine learning; Regression; Reliability; Stock Price Forecasting; Technological innovation
• DOI: 10.1109/AIIoT58432.2024.10574730

Within the domain of budgetary markets, stock price forecasting has continuously been a challenging but noteworthy undertaking for both pros and financial specialists. The energetic nature of stock markets, which are impacted by a wide range of variables counting financial specialist estimation, geopolitical occasions, and financial figures, makes anticipating more challenging. Through the use of the AutoTS library, a cutting-edge mechanized time arrangement estimating innovation, we aim to improve and speed up the method of stock cost estimation. In contrast to customary machine learning strategies, AutoTS chooses models and adapts to hyperparameters naturally, altering the always moving money related markets. Our investigation, which made use of Yahoo Finance's chronicled stock showcase information, involved meticulous preprocessing of the information to ensure its quality and worldly consistency. The benefits of AutoTS, its adaptability in taking care of complicated designs, and a nitty gritty appraisal of the model's rightness by broad testing on various time periods are secured in detail within the parts that take after. This comprehensive analysis aims to provide insight into the reliability and validity of the AutoTS-based stock cost forecasting system.