This repository contains a machine learning project focused on predicting diabetes risk. The project involves training various machine learning models, including Random Forest, SVM, and deep learning models. The best-performing model, Random Forest, achieved the highest F1 score and was identified as the optimal model for predicting diabetes risk.

• Data Preprocessing: Handling class imbalance, and splitting the dataset.
• Model Training: Multiple ML models including Logistic Regression, Random Forest, SVM, KNN, Naive Bayes, and XGBoost.
• Deep Learning: A custom-built Artificial Neural Network (ANN) model.
• Model Evaluation: Metrics include F1 score, accuracy, confusion matrix, and classification report.
• Model Compression: The best model is saved as a compressed file using the bz2file library to reduce its size for easy deployment and sharing.

1. Clone the repository:

   git clone https://github.com/ajitmane36/Diabetes-Prediction-Deep-Learning-Model.git