svr-rf-stock-price-prediction

Stock price prediction using Support Vector Regression (SVR) and Random Forest Regressor (RF).

https://github.com/not-jess/svr-rf-stock-price-prediction

Science Score: 44.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
    Found CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
    Found .zenodo.json file
  • DOI references
  • Academic publication links
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (8.4%) to scientific vocabulary
Last synced: 6 months ago · JSON representation ·

Repository

Stock price prediction using Support Vector Regression (SVR) and Random Forest Regressor (RF).

Basic Info
  • Host: GitHub
  • Owner: not-jess
  • Language: Python
  • Default Branch: main
  • Homepage:
  • Size: 86.9 KB
Statistics
  • Stars: 0
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created over 1 year ago · Last pushed over 1 year ago
Metadata Files
Readme Citation

README.md

svr-rf-stock-price-prediction

A project I did for my research course in Binus University (COMP6696001 – Research Methodology in Computer Science). This repository contains the source code and datasets used in the research.

The paper's title was "Evaluating the Performance of Support Vector Regression and Random Forest for Stock Price Prediction in the IDX", with the primary objective being to evaluate the performance of SVR and RF in predicting stock prices within the IDX. Afterwards, I compared the accuracy and effectiveness of both models in capturing future stock price movements. Link to the paper can be found here and there is also a research trailer uploaded to Youtube.

The results indicate that the Random Forest model generally outperforms the Support Vector Regression model for most of the stocks, especially in cases where the data exhibits complex, non-linear patterns. However, the SVR model also showed competitive performance for some stocks, highlighting its strength in handling specific types of data patterns.

Going forward, expanding the sample size by including more company stock indexes would provide a more comprehensive evaluation of the models' performance. A larger and more diverse dataset would help better assess the generalizability of both the Support Vector Regression and Random Forest models across different sectors and market conditions. This would also allow for a more robust comparison of the models, as certain patterns or behaviors may only emerge with a broader range of stock data.

Owner

  • Login: not-jess
  • Kind: user
  • Location: Jakarta, Indonesia

hai hello

Citation (CITATION.cff)

cff-version: 1.2.0
message: "If you use this software, please cite it as below."
authors:
- family-names: "Effendi"
  given-names: "Jessee"
- given-names: "Albert"
title: "svr-rf-stock-price-prediction"
version: 1.0.0
date-released: 2024-06-23
url: "https://github.com/not-jess/svr-rf-stock-price-prediction"

GitHub Events

Total
Last Year

Dependencies

requirements.txt pypi
  • datetime *
  • matplotlib *
  • numpy *
  • pandas *
  • plotly *
  • scikit-learn *
  • seaborn *
  • warnings *