Ensuring the effectiveness of the taxi order service by mathematical modeling and machine learning

Abstract

We can't imagine modern science without mathematical modeling. At the same time, ideas related to mathematical modeling find themselves in various fields. One of the interesting applications of mathematical modeling of random processes is the work of the taxi order service. The article describes the description of the operation of the taxi order service using autoregressive models with multiple roots of characteristic equations of different multiplicity. Also attempts were made to approximate and predict the time series of various important parameters of the taxi order service. Algorithms for identifying model parameters are proposed. Besides, we try to introduce machine learning methods to optimize work of taxi service.