Skip to content

shruti-cpp/ML_Project

Repository files navigation

ML_Project

✈️ Flight Price & Demand Prediction A machine learning and time series analysis project aimed at predicting flight ticket prices and passenger demand using real-world aviation data. This project showcases end-to-end data science workflow — from data cleaning and EDA to model building, evaluation, and forecasting.

🔍 Project Objectives Predict flight ticket prices based on airline, route, stops, timings, etc.

Forecast passenger demand using time series models.

Identify key patterns and trends in flight data through visualizations.

🧠 Techniques Used Data Preprocessing: Handling nulls, feature extraction (date, time, stops), encoding

Exploratory Data Analysis (EDA): Price trends, demand fluctuations, correlation insights

Machine Learning Models:

Random Forest Regressor

XGBoost Regressor

Linear Regression (baseline)

Time Series Forecasting:

Forecasted both price and demand over time using decomposition and forecasting techniques

📁 Files Overview

File Name Description eda.ipynb Initial data exploration and visualization Price_Prediction.ipynb ML models for predicting flight ticket prices demandprediction.ipynb ML models to predict passenger demand Price_timeseries.ipynb Time series forecasting of prices Demand_timeseries.ipynb Time series forecasting of demand datasetcsv.zip Raw dataset (compressed) README.md You’re reading it :) 🧰 Tech Stack Python

Pandas, NumPy

Scikit-learn, XGBoost

Matplotlib, Seaborn

Statsmodels, TimeSeries tools

Jupyter Notebook

📈 Key Results Achieved high accuracy in price prediction with Random Forest and XGBoost

Discovered peak pricing times, demand spikes, and seasonal fluctuations

Time series models gave reliable short-term demand forecasts

🚀 Applications Can be adapted for railway demand forecasting, fare optimization, and resource planning

Useful for airlines, railways, or any transport sector dealing with large-scale passenger data

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published