Airline-Booking-Data-Analysis

Table of Contents

• Project Objective
• Data Analysis
• Limitations

Project Objective

This repository contains airline booking datasets (Flights, Bookings, and Passengers) that have been cleaned, transformed, and joined for exploratory data analysis and dashboard visualization.

Tools

• MySQL - Data Cleaning
• Tableau - Data Visualisation

Data Cleaning

• Duplicate Removal
• Handling Missing Values
• Standardizing Data Types
• Categorical Data Cleaning
• Blank & Null Handling
• Joined Final Dataset

Exploratory Data Analysis

• Total number of bookings across all flights?
• Sum of all booking prices?
• Unique passenger count?
• Total Revenue ÷ Total Bookings?
• Breakdown by age, gender, nationality?

Data Analysis

SELECT 
  b.booking_id,
  b.booking_date,
  b.seat_class,
  b.price,

  p.passenger_id,
  p.name AS passenger_name,
  p.gender,
  p.age,
  p.nationality,

  f.flight_id,
  f.airline,
  f.flight_number,
  f.origin_airport,
  f.destination_airport,
  f.departure_time,
  f.arrival_time,
  f.status
FROM bookings2 b
JOIN passengers2 p ON b.passenger_id = p.passenger_id
JOIN flights2 f    ON b.flight_id = f.flight_id;

Results

• Majority of passengers are between 25–40 years old, showing higher travel activity among working-age adults.
• A small number of airlines account for the majority of bookings (market share concentration).

Recommendations

• Focus marketing campaigns on the 25–40 age group, as they represent the largest passenger base.
• Increase dynamic pricing strategies during high-demand months to maximize revenue.
• Use demographic insights (age, nationality) to tailor in-flight services and amenities.
• Monitor on-time performance closely (if delay data available) and prioritize punctuality to increase customer satisfaction.

Limitations

• Some rows contained NULL or blank values (e.g., missing passenger age, flight times), which were replaced with placeholders or estimates. This may affect accuracy.
• Even after cleaning duplicates and blanks, there may still be hidden inconsistencies (e.g., name spelling variations, nationality codes).