Answers are grounded in this paper and cite their sources.
This paper aims to understand if machine learning models can enhance stock price predictions compared to that of traditional financial models. The paper covers traditional financial models such as Stochastic Discount Factor models, factor-based models, option pricing models, and behavioural models, and machine learning techniques like supervised learning, deep learning, and hybrid models. By summarizing the results of various papers, this review compares the predictive accuracy of these models. The review found that machine learning methods, deep learning and hybrid models, outperformed traditional models as they captured nonlinear relationships between factors and stock price however found that some machine learning models were prone to overlearning. Through this review, financial analyst can understand if machine learning models should be used, which models to use specifically and can lead to enhanced stock price prediction.
No takes yet. Share an insight, caveat, or question.
Arav Agarwalla (2024) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: