Comparative Analysis of Stock Market Prediction System using SVM and ANN

Abstract

Support vector machines (SVM) and artificial neural networks (ANN) are machine learning methods that find a wide range of applications both in the field of engineering and social sciences. Here, Artificial Neural Networks (ANN) and Support vector machines (SVM) are employed to predict stock market daily trends: ups and downs. The purpose is to study the variation in certain parameters like accuracy, time efficiency of both classifiers (ANN and SVM) on similar datasets in predicting stock market daily trends. In this study, different SVM and ANN models for the problem of stocks prediction which provide maximum accurate results have been applied on different combinations of data sets which obtained from the historical data of various companies and comparative analysis has been presented. The findings show that SVM and ANN models give meaningful performance results for the stock investment.

Stock Prediction Web-App based on Python-Streamlit Using Data Analysis and Machine Learning

“…The experimental results of Madhu, B. et al (2021) [6] depict how ANN outperforms SVM in predicting option price and is a promising technique and can be adopted as an alternative of the SVM model in predicting option price. Talekar, S. (2020) [7] also gives a somewhat similar result but the amount of difference in accuracy here is negligible and the authors balance SVM's lack of inaccuracy with the amount of time consumed to train the ANN model. Di Persio, L., & Honchar, O.…”