Emergency Hospital Finder using Machine Learning & XGBoost Optimization

Emergency Hospital Finder Using Machine Learning and XGBoost

This project is an AI-powered emergency hospital recommendation system designed to help users quickly identify the most suitable hospital during emergency situations.

The system takes several inputs, including the emergency type, governorate, district, and number of injured people. Based on these inputs, it analyzes hospital data and recommends the most appropriate hospital while displaying its emergency contact number and estimated travel time.

The project was developed using Python and several machine learning techniques. Data preprocessing was performed using Pandas, NumPy, and Scikit-learn, including data encoding, feature scaling, and handling class imbalance with SMOTE. An XGBoost classifier was trained and optimized to improve prediction accuracy and provide reliable hospital recommendations.

Key Features

Intelligent hospital recommendation based on emergency information.

Fast prediction using a trained XGBoost model.

Data preprocessing and feature engineering for improved performance.

Class imbalance handling using SMOTE.

Hospital recommendation within the selected governorate.

Estimated travel time calculation.

Clean and scalable machine learning pipeline.

Technologies Used

Python

Pandas

NumPy

Scikit-learn

XGBoost

SMOTE

Google Colab

Machine Learning

Data Analysis

Model Evaluation