1 of 16

Raghav Arun, Suhan Asaigoli, Daniel Li, Nithi Salian

OPTIMIZING

AIRLINE PROFITS

2 of 16

OVERVIEW

Dataset Overview

01

SWOT

02

04

Actionable Items

05

Flysight

03

FlySight

06

Analyses

3 of 16

DATASET OVERVIEW

CARRIER

FARES

AIRPORTS

4 of 16

AIRLINE INDUSTRY SWOT

    • Strengths: Speed, Safety
    • Weaknesses: Limits in destinations with airlines
    • Opportunities: Hotel Partnerships, Price Elasticity Optimization
    • Threats: COVID-19, Weather

5 of 16

6 of 16

Price Elasticity Factors

Current Price

Costs &

Revenue

Historical Pricing Patterns

7 of 16

PROFIT ANALYSIS

01

02

03

04

RPM: Revenue per Passenger Mile

CPM: Cost per Passenger Mile

Profit

Actionable Items

8 of 16

Random Forest Algorithm

Fare and Passenger Volume Projection

One-hot encoding source and destination airports to Booleans

Quarter Year variable calculated from Year + (Quarter * 0.25 - 0.25)

9 of 16

Fare and Passenger Volume Projection

​

Training Group of ~400,000 routes

Test Group of ~50,000 routes

Algorithm tested with 67.8% R2 value

​

Flight fares and Passengers per day

predicted for all routes for 2024 Q2 to

2029 Q1 (next 20 Qs after dataset)

10 of 16

Competitive Landscape Analysis

11 of 16

Competitive Landscape Analysis

12 of 16

Competitive Landscape Analysis

13 of 16

Competitive Landscape Analysis

14 of 16

Business Strategy

15 of 16

Conclusion

16 of 16

Citations | External Data Information

    • Bloomberg Terminal: Financial Projections
    • ChatGPT: Development of Visualizations, Supplement of Hotel Dataset
    • Google Places API
    • Folium PyViz and GeoData
    • External Data
      • lists of hotel collective groups - self curated
      • airports.csv - supplementing given dataset with geolocation information of airports