Bank Customers Classification using MLP

This project focuses on classifying bank customers using a Multilayer Perceptron (MLP) neural network built with PySpark and MLlib.

🧠 Objective

The aim is to build an efficient classification model to predict customer behavior based on various banking features. This helps in identifying potential customers for targeted marketing or risk assessment.

📁 File

• bank-customers-classification-using-mlp.ipynb – Main Jupyter notebook containing the entire pipeline:
  • Data preprocessing
  • Feature engineering
  • MLP model training
  • Evaluation using accuracy and other metrics

🛠️ Tech Stack

• PySpark
• MLlib
• Python
• Matplotlib (for visualization)

📊 Workflow

1. Data Loading and Exploration
2. Data Cleaning and Feature Selection
3. Categorical Encoding using StringIndexer
4. Vectorization using VectorAssembler
5. MLP Model Building and Training
6. Model Evaluation

📈 Evaluation Metrics

• Accuracy Score
• Multiclass Classification Evaluator (Precision, Recall, F1-score)

🚀 How to Run

1. Clone the repo:

   git clone https://github.com/ArPaN-DS/Bank-Customer-Classification-MLP.git
   cd Bank-Customer-Classification-MLP