Developed a Machine Learning regression model to predict flight ticket prices using historical flight booking data. The project applies data preprocessing, feature engineering, and regression algorithms to estimate airfare accurately.
Build a regression model to accurately predict flight ticket prices based on airline, source, destination, journey date, duration, total stops, and additional flight information.
- Domain: Aviation
- Records: 10,683
- Target Variable: Price
- Python
- Pandas
- NumPy
- Matplotlib
- Seaborn
- Scikit-learn
- Data Collection
- Exploratory Data Analysis (EDA)
- Data Cleaning
- Feature Engineering
- Data Preprocessing
- Model Training
- Model Evaluation
| Model | R² Score |
|---|---|
| Linear Regression | 0.43 |
| Random Forest Regressor | 0.79 |
| Gradient Boosting Regressor | 0.78 |
Random Forest Regressor
- R² Score: 0.79
The Random Forest Regressor achieved the highest R² score of 0.79, demonstrating strong predictive performance for estimating flight ticket prices through feature engineering and ensemble learning techniques.
Prasanth G