What Drives Travel Costs? A Data Analysis Project Using Python & Tableau

Over the past few weeks, I completed a data analysis project focused on a simple but practical question:

What factors drive the total cost of travel the most?

Travel is something almost everyone relates to, which made it a great opportunity to practice turning raw data into insights that are easy to understand and useful for decision-making.

Project Overview

The goal of this project was to identify which factors contribute most to travel expenses, with a focus on:

• Accommodation type
• Transportation type
• Trip duration

I approached this as a real-world analytics problem: clean the data, engineer meaningful metrics, analyze cost drivers, and clearly communicate the results.

Tools Used

• Python (pandas, numpy) for data cleaning and feature engineering
• Tableau for interactive data visualization and storytelling

Key Steps in the Analysis

1. Cleaned and standardized raw travel data
2. Engineered new metrics such as:
3. Aggregated and compared costs across accommodation types and transportation methods
4. Built an interactive Tableau dashboard to communicate findings

Key Insights

• Accommodation type is the primary driver of total travel cost. Resorts and hotels were significantly more expensive than budget-friendly options such as hostels or vacation rentals.
• Transportation type is a secondary cost driver. Flights and long-distance travel increased total cost, but the impact was less consistent than accommodation choice.
• Trip duration alone does not explain cost differences. Longer trips were not always more expensive, highlighting the importance of how money is spent rather than how long a trip lasts.

Why This Project Matters

This project reinforced an important lesson in data analytics: The value of analysis comes from clear insights, not complex models.

By focusing on clean data, simple metrics, and clear storytelling, I was able to answer a real-world question in a way that non-technical stakeholders can understand.

What I Learned

• How messy real-world data can be — and how important proper data cleaning is
• The importance of feature engineering in uncovering insights
• How to use Tableau to communicate results visually and interactively

View the Dashboard

You can explore the interactive Tableau dashboard (link in the comments)

I’m continuing to build projects as I transition into a data-focused role, and I’m always open to feedback, suggestions, and conversations around analytics and data storytelling.

If you’re working on similar projects or have advice to share, I’d love to connect.