Flight Price Prediction using Machine Learning, Flask, Docker, Azure Cloud

Flight Fare Prediction - a Classic Time Series Project

  • Flight fare prediction is a classical problem of time series forecasting that finds trends in past observations to outline the future
  • Many popular flight booking websites today, including Google Flights, showcase important insights on:
    • Current fair status: high, low or fair
    • Past fare trends, upcoming future trends and
    • Helps decide the right time to book a flight ticket.

Project Overview

I built a Flight Fare Prediction App, that takes travel details as input, like: the departure date, arrival date, departure city, arrival city, stoppages, airline carrier; to predict flight ticket price. With this understanding, users may have a better idea of what the cost would be on their upcoming travel

The dataset can be found here

The steps involved in my Project

  1. Data Ingestion using Python

  2. Model Training using Random Forest Regressor

  3. Model Deployment using Flask Web Application

  4. Containerization using Docker.

  5. Deploying Conatinersed model to Azure Cloud

Project - Plan of Action

image

High Level Project Flow

image

Below are some of the screenshots for Flask Application

Flight Price Prediction Web App image

Flight Price Prediction Web App image

Built Docker image of the Source Code and Pushed Image to Docker Hub image

Pushed Docker image to Container Registry and Deployed the Web App Server in Azure image

You can find the Project code here