Flight Price Prediction

Project Overview

This project implements a machine learning model to predict flight prices using Random Forest Regressor. The system analyzes various factors including airline, departure time, stops, class, and duration to provide accurate price predictions for domestic flights. The model achieves high accuracy through careful feature engineering and advanced preprocessing techniques.

Technical Highlights

• Implemented using Python with scikit-learn, pandas, and numpy
• Feature engineering incorporating both numerical and categorical variables
• Comprehensive data preprocessing
• Model evaluation using R2 score and mean squared error
• Comparison with algorithms including Randomforest, XGBoost, AdaBoost, and Gradient Boosting

Purpose and Applications

• Assists travelers in planning their trips by providing price estimates
• Helps travel agencies optimize their pricing strategies
• Enables airlines to analyze pricing patterns and market trends
• Supports revenue management systems with data-driven insights
• Provides a foundation for building automated pricing recommendation systems

Installation

# Clone the repository
git clone https://github.com/BhaveshBhakta/Flight-Price-Prediction-Using-ML.git
cd Flight-Price-Prediction-Using-ML

# Create and activate virtual environment
python -m venv venv
 venv\Scripts\activate

# Install required packages
pip install -r requirements.txt
# Required packages:
# - pandas
# - numpy
# - scikit-learn
# - seaborn
# - matplotlib
# - plotly
# - xgboost
# - pandas-profiling

Collaboration

Feel free to fork this repository, contribute, or open issues for suggestions and improvements!