Location

Presentation- College of Science and Mathematics

Document Type and Release Option

Thesis Presentation (Restricted to Georgia Southern)

Faculty Mentor

Dr. Kyle Bradford

Faculty Mentor Email

kbradford@georgiasouthern.edu

Presentation Year

2021

Start Date

26-4-2021 12:00 AM

End Date

30-4-2021 12:00 AM

Keywords

Georgia Southern University, Honors Symposium, Presentation

Description

Predicting stock prices is perhaps one of the most tantalizing applications of mathematical statistics. Despite the Efficient Market Hypothesis’ (EMH) assertion that consistent predictions of stock price movements are impossible, it has done little in the way of deterring people’s efforts. One area of growing interest is the use of various Machine Learning (ML) techniques to forecast stock price direction. In that spirit, this study aims to refute the EMH through the implementation of a Support Vector Regression (SVR) model. Using optimized hyperparameters and k-fold cross validation to assess the model’s overall performance, the results suggest that our model does have a certain predictive power.

Academic Unit

College of Science and Mathematics

Comments

This work is archived and distributed under the repository's standard copyright and reuse license, available here. Under this license, end-users may copy, store, and distribute this work without restriction. For questions related to additional reuse of this work, please contact the copyright owner.

Files over 10MB may be slow to open. For best results, right-click and select "Save as..."

Share

COinS
 
Apr 26th, 12:00 AM Apr 30th, 12:00 AM

Stock Price Prediction Using Support Vector Regression

Presentation- College of Science and Mathematics

Predicting stock prices is perhaps one of the most tantalizing applications of mathematical statistics. Despite the Efficient Market Hypothesis’ (EMH) assertion that consistent predictions of stock price movements are impossible, it has done little in the way of deterring people’s efforts. One area of growing interest is the use of various Machine Learning (ML) techniques to forecast stock price direction. In that spirit, this study aims to refute the EMH through the implementation of a Support Vector Regression (SVR) model. Using optimized hyperparameters and k-fold cross validation to assess the model’s overall performance, the results suggest that our model does have a certain predictive power.