Research on Microsoft Stock Prediction Based on Machine Learning Methods

Shengyang Xu

2024

Abstract

This research delves into the dynamic realm of forecasting Microsoft stock trends, utilizing a dataset spanning from November 2019 to 2023, accessible via Kaggle. The data undergoes meticulous preprocessing, including temporal filtering and weekly resampling, to ensure relevance and consistency. Key features – ’Open,’ ’High,’ ’Low,’ and ’Volume’ – identified as pivotal in prior studies, form the basis for constructing training and testing datasets. Our methodology integrates diverse machine learning models, namely k-Nearest Neighbors (k-NN), Random Forest, and Support Vector Regression (SVR). The k-NN model captures local patterns, leveraging proximity within the data. Random Forest, known for robustness, interprets high-dimensional financial data through an ensemble of decision trees. SVR, designed for nonlinearity, addresses intricate relationships within the stock dataset. Training and evaluation on distinct datasets reveal nuanced performances. While k-NN encounters challenges, Random Forest emerges as a robust choice, excelling in capturing diverse features. SVR, despite its nonlinear focus, faces limitations in the specific dynamics of stock data. This study contributes to the evolving landscape of stock price prediction, emphasizing the effectiveness of a diversified machine learning approach.

Paper Citation

in Harvard Style

Xu S. (2024). Research on Microsoft Stock Prediction Based on Machine Learning Methods. In Proceedings of the 1st International Conference on Data Science and Engineering - Volume 1: ICDSE; ISBN 978-989-758-690-3, SciTePress, pages 47-51. DOI: 10.5220/0012818700004547

in Bibtex Style

@conference{icdse24,
author={Shengyang Xu},
title={Research on Microsoft Stock Prediction Based on Machine Learning Methods},
booktitle={Proceedings of the 1st International Conference on Data Science and Engineering - Volume 1: ICDSE},
year={2024},
pages={47-51},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012818700004547},
isbn={978-989-758-690-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on Data Science and Engineering - Volume 1: ICDSE
TI - Research on Microsoft Stock Prediction Based on Machine Learning Methods
SN - 978-989-758-690-3
AU - Xu S.
PY - 2024
SP - 47
EP - 51
DO - 10.5220/0012818700004547
PB - SciTePress