A curated collection of beginner-to-intermediate level machine learning projects built using Scikit-learn, XGBoost, and other essential ML tools. Each project explores a different real-world use case, complete with preprocessing, training, and evaluation steps.
| Project Name | Algorithm / Library | Description |
|---|---|---|
| California Housing Value Prediction | XGBoost | Predicts housing prices based on California census data. |
| Car Price Prediction | Scikit-learn (Regression) | Predicts car resale value using various numerical and categorical features. |
| Diabetes Prediction | Scikit-learn (Classification) | Predicts the likelihood of diabetes using medical parameters. |
| Heart Disease Prediction | Logistic Regression | Classifies heart disease presence using clinical data. |
| Loan Approval Prediction | Scikit-learn + EDA | Determines loan eligibility based on applicant information. |
| Rock vs Mine Prediction | Scikit-learn (Binary Classifier) | Classifies sonar signals as either rocks or mines. |
| Spam Mail Detection | Scikit-learn (NLP) | Detects spam emails using text processing and Naive Bayes. |
| Wine Quality Predictor | Scikit-learn (Regression) | Predicts wine quality from chemical properties. |
| Heart Failure Prediction | Logistic Regression | Predicts risk of heart failure from medical data. |
- Languages: Python
- Libraries: scikit-learn, pandas, NumPy, matplotlib, seaborn, XGBoost
- Tools: Jupyter Notebook, Google Colab, VS Code
Each project typically follows this pipeline:
- Data Cleaning & Exploration
- Feature Engineering & Scaling
- Model Selection & Training
- Model Evaluation (Accuracy, Confusion Matrix, etc.)
- Final Inference / Deployment-Ready Notebook
This repository is ideal for:
- Beginners exploring classic ML problems.
- Students preparing for ML interviews.
- Showcasing end-to-end workflows in various domains: healthcare, real estate, finance, and more.
Clone the repo:
git clone https://github.com/architasaha21/Machine-Learning.git