Predicting Total Fare based on Booking Method and Airline - Project

Completion Date:

03-03-2024

Project Overview

The travel industry demonstrated significant growth and efficiency, as evidenced by the performance metrics. The sector successfully served 20,000 passengers, showcasing a robust week-over-week (WoW) growth rate of 4.38%. This increase in passenger volume reflects the industry’s effective marketing and service strategies aimed at boosting customer engagement. During the same period, total revenue reached $16 million, with a WoW increase of 3.97%, underscoring the sector\\\\\\\'s strong revenue generation capabilities.
Despite this upward trend in passengers and revenue, the average fare experienced a slight decrease of 0.08%, settling at $787. This marginal reduction in fare suggests a strategic pricing adjustment to stay competitive in the market. Additionally, the industry maintained a stable saving rate of 19%, indicating no significant change in cost-saving measures. These figures highlight the travel industry\\\\\\\'s successful balance between growth in service demand and financial sustainability during January 2019, setting a positive outlook for future performance.

Role:

I was a lead data scientist and specializing in data visualization.

Problem Statement

In today\\\\\\\'s highly competitive air travel market, airlines and travel agencies face the challenge of setting optimal prices to maximize revenue without deterring potential customers. With the industry experiencing a fluctuation where over 20% of travelers select flights based on price alone, there\\\\\\\'s a critical need for a robust solution that can predict airfare prices with high accuracy. This project proposes the use of advanced regression models, including Linear Regression, Random Forest Regression, and Gradient Boosting Regression, to tackle this problem. By analyzing variables such as booking method, airline code, and journey routes, we aim to develop a predictive model that will revolutionize fare pricing strategies, catering specifically to the needs of pricing analysts and revenue managers in the aviation sector.

Executive Summary

Data Dictionary

Key Takeaways

Next Steps

Deployment