Flight-Fare-Prediction_ML

✈️A Machine Learning Model that can predict the prices of flight tickets.

Image Source

Problem Statement

A flight fare prediction machine learning model is needed to help travelers and airlines make informed decisions about pricing and booking flights based on historical data and real-time information.

Datasets

Find the datasets used at - Kaggle

In this scenario, we have two sets of data: the training set and the test set. The training set comprises 10 input features and 1 output column, which is the price of flights, and has a total of 10683 records. The test set includes 10 input features and 2671 records. The objective is to predict the output column, which is the price of flights, using regression techniques because it is a continuous value. The available columns in the dataset are Airline, Date_of_Journey, Source, Destination, Route, Dep_Time, Arrival_Time, Duration, Total_Stops, Additional_Info, and Price.

Steps

1. Exploratory Data Analysis
2. Data Visualization
3. Feature Engineering
4. Model Building

Future Scope

Model Deployment - Designing a User Interface using the Python Flask Framework or Streamlit which will take the user's input preferences and calculate the fare. The model can then be deployed on Heroku through the GitHub link.

References

Link1 Link2 Link3 Link4