✈️ Airline Operations Disruption Analysis

MBA Business Analytics | Python Analytics Project

📌 Project Overview

• Airline operations are highly sensitive to disruptions such as delays and cancellations, which significantly impact passenger experience and operational efficiency.
• This project presents a data-driven analysis of airline operational disruptions, focusing on delay severity, cancellation patterns, airport-level impact, and passenger disruption.
• The objective is to transform raw flight operations data into actionable business insights that support operational decision-making and recovery planning.

---

🎯 Business Objectives

• Analyze flight delays and cancellations during disruption events
• Quantify disruption impact using a Disruption Severity Index (DSI)
• Identify high-impact airports contributing most to network-wide disruption
• Estimate passenger impact across disruption phases
• Translate analytical findings into business recommendations

---

📊 Dataset Description

• Total Records: 500 flights

• Airline: IndiGo (case study – simulated data)

• Airports Covered: DEL, BOM, BLR, HYD, CCU

• Time Phases:

  • Pre-disruption
  • Disruption
  • Recovery

Key Features

• Departure delay (minutes)
• Flight status (On-Time, Delayed, Cancelled)
• Estimated passenger count
• Disruption phase

---

🛠 Tools & Technologies Used

• Python
• Pandas – data manipulation & analysis
• NumPy – numerical computations
• Matplotlib & Seaborn – data visualization
• Jupyter Notebook – analysis workflow

---

🔍 Methodology

• Data cleaning and preprocessing
• Feature engineering for delay severity and cancellation flags
• Creation of Disruption Severity Index (DSI)
• Passenger impact estimation based on delay thresholds
• KPI analysis across disruption phases
• Visualization of trends and operational insights

---

📈 Key Insights

• 55.4% of flights experienced delays during the analysis period
• 9.4% of flights were cancelled, significantly increasing passenger impact
• Disruption Severity Index showed sharp spikes during incident days
• A small number of hub airports contributed disproportionately to total disruption
• Recovery from disruption was gradual and uneven, indicating operational strain

---

💡 Business Impact

This analysis helps airlines to:

• Detect early signs of operational disruption
• Prioritize recovery efforts at high-impact hub airports
• Reduce passenger dissatisfaction during irregular operations
• Improve data-driven decision-making in operations management

---

🚀 Future Enhancements

• Integration of real-time flight data
• Predictive disruption alerts using machine learning
• Interactive dashboards using Power BI / Tableau
• Route-level and fleet-level disruption analysis

---

👤 Author

Kushal Roy MBA (Business Analytics) IBM