Conducted a complete operational analysis of U.S. domestic flight data to identify delay patterns for Frontier Airlines, aiming to optimize scheduling, improve on-time performance, and enhance operational efficiency. Leveraged Python and Tableau to visualize bottlenecks, pinpoint delay causes, and propose data-driven solutions
Frontier Airlines exhibited significant delays compared to peers, especially at key hubs and during peak seasons.
Contributing factors included weather-related disruptions, late aircraft turnovers, and carrier-specific scheduling inefficiencies.
Solution / Approach
1. Airport and Traffic Analysis
Objective: Identify Frontier’s busiest operational hubs and traffic concentration.
Action:
A bubble chart was used to visualize flight volume distribution across major airports.
Key Insight:
ATL (Atlanta) and DEN (Denver) emerged as significant traffic hubs.
High congestion at these hubs correlates with operational bottlenecks and peak-time delays.
Objective: Detect geographic hotspots with the highest departure and arrival delays.
Action:
Created heatmaps mapping average delays by city.
Key Insight:
Providence, RI, Houston, TX, and Hartford, CT recorded the highest average delays for both departures and arrivals.
Frontier operations in these regions require focused delay mitigation strategies.
Objective: Compare Frontier Airlines’ operational efficiency against competitors.
Action:
Plotted comparative bar charts for key metrics across airlines (flights operated, total delays, cancellations, air time, and distances flown).
Key Insight:
Frontier Airlines (F9) shows higher total delay averages than major competitors like Delta (DL) and American Airlines (AA).
Average air time is competitive, but higher delays and cancellations negatively impact customer satisfaction.
Objective: Analyze how delay reasons fluctuate across different quarters of the year.
Action:
Built a quarterly trend line chart tracking key delay causes (Carrier Delay, Weather Delay, Late Aircraft Delay, Security Delay).
Key Insight:
Carrier Delay and Late Aircraft Delay peak sharply in Q2 and Q3, aligning with seasonal traffic surges.
Weather and security-related delays are minor in comparison.
Pinpointed peak delay periods (Q2 and Q3) and major delay contributors (carrier operations, late aircraft).
Identified operational hubs and timeframes responsible for 60%+ of Frontier’s total delays.
Proposed scheduling optimization and operational buffers projected to improve on-time performance by 15–20%.
Laid the foundation for future machine learning delay prediction models.