Comparative Analysis of Machine Learning Models for Predicting Stock Prices in High-Volatility Scenarios

DOI

10.2991/978-94-6463-512-6_46How to use a DOI?

Keywords

Stock Price Prediction; Machine Learning; High-Volatility Markets; Financial Forecasting; Comparative Model Analysis

Abstract

This work aimed at predicting Tesla’s stock price with focus on high volatility environments by the aid of machine learning algorithms. The research work covered the period between January 2019 to April 2024, the dataset sourced from Yahoo Finance and contained historical stock prices of the selected company, which was Tesla. Data preparation steps included date to ordinal transformation, calculating technical indicators using TA-Lib such as SMA20, RSI14, and many more, and ordering missing observations. The time series was divided into training and testing series from January 1, 2019 to January 1, 2024 and April 29, 2024, respectively. Three machine learning models were implemented using scikit-learn: Linear Regression, Random Forest and Support Vector Machine (SVM) it is type of machine learning techniques. Linear regression uses a straight line to model the variables, Random Forest builds many numbers of decision trees and provides average value, SVM identifies a hyper plane in a higher dimensional space such that the distance between the closest data points is maximized. Model effectiveness was assessed through the MSE and R2 coefficient, which gave an indication of how well each model was performing in predicting the stock prices of Tesla in a highly volatile market. The results also indicated that SVM had a higher accuracy and sensitivity in the high volatility environment than both Linear Regression and Random Forest in predicting Tesla’s stock prices. This shows the need to apply enhanced machine learning method for ANS for efficient financial forecasting in volatile environment.

Copyright

© 2024 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Jiashuo Xing
PY  - 2024
DA  - 2024/09/23
TI  - Comparative Analysis of Machine Learning Models for Predicting Stock Prices in High-Volatility Scenarios
BT  - Proceedings of the 2024 International Conference on Artificial Intelligence and Communication (ICAIC 2024)
PB  - Atlantis Press
SP  - 433
EP  - 440
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-512-6_46
DO  - 10.2991/978-94-6463-512-6_46
ID  - Xing2024
ER  -