https://github.com/akashkg03/concrete-strength-prediction

Predictive model using machine learning to forecast concrete strength based on constituent materials.
https://github.com/akashkg03/concrete-strength-prediction

exploratory-data-analysis jupiter-notebook matplotlib pandas python3 regression seaborn supervised-learning

Last synced: 8 days ago
JSON representation

Predictive model using machine learning to forecast concrete strength based on constituent materials.

• Host: GitHub
• URL: https://github.com/akashkg03/concrete-strength-prediction
• Owner: Akashkg03
• Created: 2024-02-12T01:22:48.000Z (9 months ago)
• Default Branch: main
• Last Pushed: 2024-02-23T04:34:38.000Z (9 months ago)
• Last Synced: 2024-02-23T05:27:54.020Z (9 months ago)
• Topics: exploratory-data-analysis, jupiter-notebook, matplotlib, pandas, python3, regression, seaborn, supervised-learning
• Language: Jupyter Notebook
• Homepage:
• Size: 2.17 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
## Concrete-Strength-Prediction

### Problem Statement:

- In the project, the objective was to develop a machine learning model capable of accurately predicting the compressive strength of concrete based on its constituent materials.

### Methodology:

- Utilized a regression-based machine learning approach to predict strength of concrete.

- Implemented data preprocessing techniques such as feature scaling and feature extraction.

- Explored various regression algorithms including linear regression, decision trees, knn, svr, random forests, adaptive boosting, gradient boosting and XG boost.

### Results:

- The Gradient Boosting Regressor outperformed other algorithms, achieving a RMSE of 4.56 N/mm2 and accuracy of 92.5% on the test data.

- Identified important features influencing concrete strength through feature importance analysis.

### Skills Demonstrated:

- Data preprocessing, data visualization, regression modeling, hyperparameter tuning, model evaluation.

### Technologies Used:

- Python, pandas, scikit-learn, matplotlib, seaborn, Jupyter Notebook.