Case StudySouthwest Airlines

Southwest Airlines improves safety and preventes flight anomalies with machine learning

Southwest Airlines leverages machine learning techniques like time series analysis and pattern recognition to identify flight anomalies patterns in historical data. With enhanced data mining capabilities the company is able to avoid and prevent potential future safety issues. The airline has successfully managed to communicate with Las Vegas'' and Denver''s air traffic control to resolve arrival issues.

The Project

"According to Jeff Hamlet, former Director of Air Operations Assurance using machine-learning algorithms to identify patterns has enabled Southwest Airlines to identify potential flight anomalies found in pilots’ data reports. The issues that pilots report allow them to mine the flight data (from FDAP) to get a better idea of where those problems may be occurring and to what extent. The collection of time-ordered data helps locate glitches in flight patterns to report to air traffic control upon arrival."

AI Usage

Time series analysis

Data

time-ordered data, flight reports

Results

The company has been successful in communicating with air traffic control in Las Vegas and in Denver about arrival issues and how their instructions impact operations.

Related Use Cases

Use Case

Augment traffic control processes at (air)ports

→

Use Case

Identify performance and risk for pilots through flying patterns and other data

→

←Back to Case Studies