Time and cost optimization of the public transport network. Streamlining timetables by arranging vehicles to the assumed load in a proactive way - before it actually occurs. Adjustment of the system to a dynamically changing environment. Prediction of crowded areas using Machine Learning. Consideration of random situations affecting ground movement, such as weather, road works, accidents and mass events (like concerts or matches).
The system that enables analyzing and predicting load of the public transport network. For this purpose the system uses transaction data obtained from credit card payments (settled in Mass Transit Transaction). The solution is based on the travel data function, chosen tariff and place of purchasing tickets. This function is later combined with data prediction models based on Deep Learning algorithms. It is a combination of AI technology and the latest achievements in payments systems that are used in public transport.