🤖 Machine Learning Projects

A collection of Machine Learning projects built using Python and industry-standard ML libraries. This repository showcases end-to-end machine learning workflows, including data preprocessing, exploratory data analysis (EDA), feature engineering, model development, evaluation, and business insights.

---

👨‍💻 About Me

Hi, I'm Harsh Poonia.

🎓 MCA Student at Thapar Institute of Engineering & Technology

I am passionate about Machine Learning, Data Analytics, and Software Development. This repository documents my journey of building real-world machine learning projects while strengthening my understanding of data-driven problem solving.

---

🛠️ Tech Stack

Programming

• Python

Data Manipulation

• Pandas
• NumPy

Data Visualization

• Matplotlib
• Seaborn

Machine Learning

• Scikit-Learn

Development Tools

• Jupyter Notebook
• VS Code
• Git
• GitHub

---

📚 Machine Learning Workflow

Projects in this repository typically follow:

1. Data Collection
2. Data Cleaning
3. Exploratory Data Analysis (EDA)
4. Feature Engineering
5. Data Preprocessing
6. Model Training
7. Model Evaluation
8. Performance Comparison
9. Business Insights
10. Model Persistence

---

🚀 Projects

No.	Project	ML Type	Status
1	Customer Churn Analysis & Prediction	Classification	✅ Completed
2	House Price Prediction	Regression	🔄 Planned
3	Loan Approval Prediction	Classification	🔄 Planned
4	Credit Risk Prediction	Classification	🔄 Planned
5	Customer Segmentation	Clustering	🔄 Planned
6	Recommendation System	Recommendation	🔄 Planned
7	Email Spam Detection	NLP	🔄 Planned
8	Movie Review Sentiment Analysis	NLP	🔄 Planned
9	Sales Forecasting	Time Series	🔄 Planned
10	Medical Diagnosis Prediction	Classification	🔄 Planned

---

📌 Featured Project

Customer Churn Analysis & Prediction

Objective

Predict whether a telecom customer is likely to churn based on demographic information, account details, and service usage patterns.

Project Highlights

• ✅ Data Cleaning & Preprocessing
• ✅ Exploratory Data Analysis (EDA)
• ✅ Feature Engineering
• ✅ Model Training
• ✅ Model Evaluation
• ✅ Model Comparison
• ✅ Feature Importance Analysis
• ✅ Model Saving

Models Evaluated

Model	Accuracy	Precision	Recall	F1 Score
Logistic Regression	0.807	0.647	0.607	0.626
Decision Tree	0.743	0.517	0.521	0.519
Random Forest	0.796	0.642	0.527	0.579

Best Model

🏆 Logistic Regression

• Accuracy: 80.74%
• Precision: 64.67%
• Recall: 60.70%
• F1 Score: 62.62%

Key Findings

• Customers with shorter tenure are more likely to churn.
• Higher monthly charges increase churn risk.
• Long-term contracts improve customer retention.
• Fiber optic customers exhibit higher churn rates.
• Electronic check users are more likely to churn.

---

🎯 Learning Goals

• Build 10+ Machine Learning Projects
• Strengthen Statistical Thinking
• Master Scikit-Learn
• Learn Model Optimization Techniques
• Explore NLP and Deep Learning
• Develop Industry-Ready ML Workflows
• Build a Placement-Ready Portfolio

---

📈 Skills Demonstrated

• Data Cleaning
• Data Preprocessing
• Exploratory Data Analysis
• Feature Engineering
• Data Visualization
• Classification Modeling
• Regression Modeling
• Clustering
• Model Evaluation
• Feature Scaling
• Machine Learning Pipelines
• Business Insight Generation

---

📂 Repository Structure

Machine-Learning-Projects/
│
├── Customer_Churn_Analysis/
│
├── README.md
│
└── Future Projects...

---

📈 Current Progress

• ✅ 1 Machine Learning Project Completed
• 🔄 9 Planned Projects Remaining
• 🎯 Building a diverse portfolio covering Classification, Regression, Clustering, NLP, Recommendation Systems, and Time Series Forecasting

---

📫 Connect With Me

GitHub

https://github.com/Harshpoonia

---

⭐ This repository is continuously updated as I build and document new Machine Learning projects.