Public Transport Authorities worldwide manage one or more contracts with different Operators. These contracts typically outline the compensation structure for Operators based on deviations between planned and actual service.

This includes scenarios such as planned services with more trips than agreed upon, actual services with canceled trips, or services performed at a lower quality level than specified in the contract.

At the heart of this contract management process lies the “Cause Codes Review,” where Operator personnel manually analyze discrepancies between planned and actual service trips, determined by real-time CAD/AVL data of vehicle passing times at bus stops.

Trips are typically categorized as Operated, Lost-Deductible, or Lost-Not-Deductible. Only trips with a Lost-Deductible cause code affect Operator compensation, deducting from the Authority payment.

The Contract and Performance Management module of the MAIOR Suite helps to monitor and improve your service quality delivered to the passengers, improving decision making and ease your service accountability with clear performance indicators reports.

This is where artificial intelligence comes into play for public transport.

While this process is crucial for determining Operator compensation, it is also labor-intensive, involving the manual analysis of thousands of trips. Recognizing the importance of streamlining this task, MAIOR has developed a Machine Learning algorithm.

This algorithm helps Operator end users in accurately associating cause code classes with undetected trips—whether they are operated, not operated deductible, or not operated not deductible.

The algorithm achieves up to an 85% classification accuracy, significantly reducing the workload on Operator personnel. This not only addresses the repetitiveness of the task but also serves as a pivotal element in the precise calculation of Operator compensation.