Overview
Flight Fare Predictor is a machine learning project that estimates airline ticket prices based on various travel parameters such as source, destination, duration, and timing.
The project combines data preprocessing, feature engineering, and a trained regression model, exposed through a lightweight Flask API for real-time predictions.
Key Features
-
Price Prediction Model
Uses Random Forest Regression to predict flight fares with strong performance on structured data. -
Feature Engineering Pipeline
Handles date-time extraction, categorical encoding, and data cleaning to improve model accuracy. -
Flask API Integration
Exposes the trained model through REST endpoints for real-time predictions. -
End-to-End ML Workflow
Covers data preprocessing → model training → evaluation → deployment. -
Lightweight & Deployable
Designed to be easily deployed and integrated into other applications.
Tech Stack
- Python — Core programming language
- Pandas — Data preprocessing and manipulation
- Scikit-learn — Model training and evaluation
- Flask — API layer for serving predictions
Use Case
This project is useful for:
- Understanding regression-based ML problems
- Learning practical feature engineering techniques
- Building and deploying ML models via APIs
- Demonstrating end-to-end ML project workflow
Model Approach
- Algorithm: Random Forest Regressor
- Handles non-linearity and feature interactions effectively
- Robust against overfitting compared to single decision trees
Getting Started
git clone https://github.com/viveek-sh/flight-fare-predictor
cd flight-fare-predictor
pip install -r requirements.txt
python app.py
Repository
- Explore the full project here: 👉 https://github.com/viveek-sh/flight-fare-predictor