A mathematical model for predicting traffic jams. Yandex Workshop

For the qualitative construction of routes in urban environments, it is necessary to estimate the travel time along the route as accurately as possible. It is desirable to take into account not only the current situation, but also how it can change. A couple of years ago we already published a post about predicting the situation on the roads. The text allows you to make a general idea about this topic. Mikhail Khokhlov addressed the issue of traffic jam forecasting in his report. He spoke about various mathematical approaches to predicting road difficulties for the near future, including the linear autoregression method used in Yandex.Probka. Since then, much has changed, but the main problems and methods of their solution remain the same and deserve attention.