This repository contains the research paper titled "Survey of Regression-Driven Stock Market Price Predictors," presented at the 2nd National Conference on Engineering Applications of Emerging Technology in association with the International Journal of Scientific Research in Science, Engineering, and Technology. The paper investigates various regression algorithms for stock market price prediction, focusing on their accuracy and performance metrics. The code and analysis provided here demonstrate the efficacy of various regression models, including linear regression, robust regression, ridge regression, and lasso regression. Additionally, the implementation of a neural network for predictive analysis is showcased to provide a comprehensive understanding of the application of machine learning in financial markets.
The repository contains Python code that imports, preprocesses, and analyzes stock market data. It includes exploratory data analysis techniques to gain insights into the dataset. The code demonstrates the step-by-step implementation of each regression model, along with the necessary evaluation metrics to assess their predictive accuracy. Furthermore, the utilization of a neural network for predictive analysis is highlighted, providing an additional perspective on the application of advanced machine learning techniques.
The research delves into the application of machine learning techniques, particularly regression algorithms, to predict stock market prices. It emphasizes the significance of factors such as company earnings, market competition, demand, and stability in making accurate predictions. The paper analyzes the performance of regression models, including Linear Regression, Robust Regression, Ridge Regression, and Lasso Regression, using a dataset obtained from Kaggle. The study measures their accuracy based on metrics such as Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and R-squared (R2).
- Detailed analysis of Regression algorithms in stock market prediction
- Explanation of various performance metrics used in the analysis
- Implementation of Python and Scikit-learn for the regression models
- Insightful data representation through graphs and charts
- Data Import and Preprocessing
- Exploratory Data Analysis
- Linear Regression Implementation
- Robust Regression Analysis
- Ridge Regression Application
- Lasso Regression Utilization
- Neural Network Implementation for Predictive Analysis
- Data Visualization and Analysis
The results showcase the efficacy of different regression models, as illustrated in the table below:
| Model | MAE | MSE | RMSE | R2 Square | Cross Validation |
|---|---|---|---|---|---|
| Linear | 3.845779 | 30.11601 | 5.487806 | 0.997035 | 0.925135 |
| Robust | 3.845779 | 30.11601 | 5.487806 | 0.997035 | 0.925135 |
| Ridge | 6.633434 | 64.82109 | 8.051155 | 0.993619 | 0.925135 |
| Lasso | 3.850596 | 30.12317 | 5.488458 | 0.997035 | 0.92513 |
The repository contains Python code snippets that demonstrate the implementation of the various regression models. Users can refer to the code to understand the practical application of these algorithms in stock market price prediction.
Please refer to the paper for a comprehensive understanding of the survey and its implications research paper
This project is licensed under the MIT License - see the LICENSE file for details.
