Exploiting Artificial Intelligence to enhance average individual investment performance: a comparative analysis of combined models

Abstract

This research explores the enrichment of individual investment performance through artificial intelligence. It focuses on trading strategies for financial instruements, leveraging sentiment analysis, genetic programming, and various machine learning models. A literature review provides context for the strategies employed. The study tests sentiment-based trading as a standalone approach and combines it with alpha generation via genetic programming. Additionally, models such as “LSTM Neural Networks”, “Random Forests”, and “XGBoost” are evaluated to assess their effectiveness. Comparative analysis are performed to identify optimal strategies for maximizing returns, improving investment decisions, and mitigating risks for individual investors.