This paper provides a systematic overview of machine learning methods applied to solve NP-hard Vehicle Routing Problems (VRPs). Recently, there has been a great interest from both machine learning and operations research communities to solve VRPs either by pure learning methods or by combining them with the traditional hand-crafted heuristics. We present the taxonomy of the studies for learning paradigms, solution structures, underlying models, and algorithms. We present in detail the results of the state-of-the-art methods demonstrating their competitiveness with the traditional methods. The paper outlines the future research directions to incorporate learning-based solutions to overcome the challenges of modern transportation systems.

No abstract

No abstract

Kazakh is an agglutinative language which has complex structure. In this work Apache Spark was used to specify the popularity of Kazakh words in 3 popular kazakh compositions. The main goal was to find the optimal number of data segments for a specific number of cores in order to find the best computational speed. To do so, the data was divided into several segments and ran on a cluster with a different number of cores each time. Results show that the amount of data segments directly affects the computing speed.