A Comparative Review on Stock Market Prediction Using Artificial Intelligence

Abstract

The global financial landscape has undergone unprecedented transformations in recent decades, characterized by increased complexity, volatility, and interconnectivity. In this dynamic environment, the ability to anticipate stock market trends has become a paramount concern for investors, financial analysts, and policymakers alike. This research aims to distil insights and contribute to advanced predictive models for the dynamic global financial landscape. The exploration encompasses diverse approaches, including artificial neural networks, convolutional neural networks, LSTM, and traditional machine learning algorithms. Emphasis is placed on data pre-processing, numerical analyses, and the efficacy of LSTM models. The significance of this research lies in its synthesis of existing knowledge, offering a holistic view of methodologies and outcomes in Share Market Prediction. The model signifies a foundation for further innovation in predictive modeling, addressing real-time data challenges and dynamic market conditions. This work advances the understanding and forecasting of stock market trends.

Keywords

• Artificial Neural Network
• Long-Short-Term Memory (LSTM)
• Predictive Modelling Data