Application of Machine Learning Algorithms in Predicting Financial Market Trends: A Comparative Analysis
Article PDF

Keywords

Machine Learning, Random Forest, Financial Forecasting, Predictive Analytics, Financial Data Analysis.

How to Cite

Mkpedem, K. A., Etefia, I. E., & Oluwafemi, R. O. (2025). Application of Machine Learning Algorithms in Predicting Financial Market Trends: A Comparative Analysis. American Research Journal of Contemporary Issues, 3(4), 74-94. https://doi.org/10.46654/na5khe24

Abstract

This study investigates the use of machine learning algorithms for predicting financial market trends through a comparative analysis of the Prophet model and the Random Forest Classifier. Historical stock market data for Apple Inc. (AAPL), including Open, High, Low, Close prices, and Volume, were collected and pre-processed using exploratory data analysis, feature engineering, and normalization techniques to improve model reliability. A quantitative comparative methodology was adopted to evaluate predictive performance. The Prophet model was implemented as a time-series forecasting approach, while the Random Forest Classifier was applied as a supervised learning model for multi-class trend classification. Performance was assessed using accuracy, precision, recall, F1-score, and confusion matrices. Results showed that Prophet achieved 52% accuracy, highlighting limitations in modelling complex financial market behaviours and minority classes. In contrast, the Random Forest Classifier achieved 100% accuracy, precision, recall, and F1-score. The findings suggest that ensemble-based machine learning models outperform traditional time-series forecasting methods in financial market trend prediction.

Article PDF
Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

Copyright (c) 2025 American Research Journal of Contemporary Issues

271 139