HMEQ

🧠 HMEQ Credit Risk Modeling

This project analyzes and models the HMEQ dataset to predict whether a loan applicant will default.
It combines data cleaning, visualization, and machine learning classification using Python’s top data science libraries.

---

🚀 Project Overview

The HMEQ (Home Equity) dataset contains information on loan applicants, their credit history, and default status.
Our goal: build a robust ML model to predict loan default and identify the key factors influencing credit risk.

---

📊 Workflow

1. Data Preprocessing

• Handling missing values with SimpleImputer
• Encoding categorical variables using LabelEncoder
• Splitting the dataset into train/test sets

2. Exploratory Data Analysis (EDA)

• Visualizing distributions and correlations with seaborn and matplotlib
• Detecting outliers and understanding feature importance

3. Model Building

Implemented and tuned several ML models:

• 🌳 Decision Tree Classifier
• 🌲 Random Forest Classifier
• 🚀 Gradient Boosting Classifier

Used GridSearchCV for hyperparameter optimization.

4. Model Evaluation

• ✅ Accuracy score
• 📈 ROC & Precision-Recall Curves
• 🔍 Confusion Matrix
• 📜 Classification Report

---

🧠 Key Insights

• Gradient Boosting delivered the highest accuracy and AUC
• Feature importance analysis reveals the top predictors of default
• Missing value treatment and encoding significantly improved performance

---

🧰 Tech Stack

Category	Tools
Language	Python 🐍
Data	Pandas, NumPy
Visualization	Matplotlib, Seaborn
ML Models	scikit-learn
Optimization	GridSearchCV
Metrics	ROC, AUC, Confusion Matrix

---

💻 How to Run

1. Clone the repository

   git clone https://github.com/<your-username>/hmeq-ml.git
   cd hmeq-ml