Journal of Recent Trends in Computer Science and Engineering (JRTCSE) Vol. 12, No.5, November - December 2024, PP. 60-72. ISSN: 2322-0872 DOI: https://doi.org/10.70589/JRTCSE.2024.5.9 https://jrtcse.com 60 Quantitative Methods in Business Intelligence: A Systematic Review of Machine Learning Algorithms for Financial Forecasting Hanza Parayil Salim, Staff Engineer, Neiman Marcus, Texas, USA. Abstract Financial forecasting is one of the key subcategories of BI that employs ML to improve the reliability and precision of the forecast. This paper reviews various quantitative methods applied to business intelligence, particularly in using machine learning algorithms to forecast financial data. The study focuses on regression models, time-series analysis, deep learning, and ensemble learning as ML techniques. The paper reviews the various advantages and drawbacks of these methods, compares the results from the performance of the benchmark-based approach, and talks about the use of those approaches in financial markets. Moreover, the work outlines this domain's major issues and important research perspectives. In the paper, we identified the effectiveness of the machine learning models in forecasting stock prices, risk and portfolio using literature reviews, case studies, or experimental results. Thus, hybrid models, deep learning strategies, and other enhanced varieties of ensemble algorithms reduce disparities and enhance the accuracy level of the forecast. Moreover, it highlights the significance of cleaning, transforming and validating characteristics and assessing a model's performance. The conclusion made from this review will be relevant to the understanding and development of the current business intelligence system and serve as a guide to practice for financial analysts and researchers in this line of study. Keywords: Machine Learning, Business Intelligence, Financial Forecasting, Quantitative Methods, Time-Series Analysis, Deep Learning, Ensemble Learning, Risk Management Citation: Hanza Parayil Salim. (2024). Quantitative Methods in Business Intelligence: A Systematic Review of Machine Learning Algorithms for Financial Forecasting. Journal of Recent Trends in Computer Science and Engineering (JRTCSE), 12(5), 60–72. https://doi.org/10.70589/JRTCSE.2024.5.9 1. Introduction Predicting these markets is necessary as they become more complicated due to factors such as electronic trading and globalization. However, linear regression and Autoregressive Integrated Moving Average (ARIMA) models are ineffective in analyzing big data. [1-3] Machine learning techniques, on the other hand, can be used to forecast financial data more accurately and efficiently and can be adjusted to the prevailing circumstances in the market.