Machine Learning Methods Application in Logistics Chains

The Russian market of transport and logistics services is of key importance for modern society and the country's economy as a whole, the latest data demonstrates the active growth of this sector. These indicate a rapidly developing and unstable business environment where traditional methods of logistics chain optimisation are becoming ineffective in ensuring the competitiveness of enterprises as well as their development. Therefore, the introduction of modern solutions such as machine learning methods as the most promising business tool is becoming a necessity to monitor and improve the operation efficiency of transport and logistics companies' departments. Nevertheless, the field of analysing and applying machine learning techniques in logistics is quite new, rapidly expanding and, as a consequence, not comprehensively investigated. This graduate research paper on the topic «Machine learning methods application in logistics chains» is supposed to fill the gap of complex studies of the mentioned innovation implementation in the Russian market of transport and logistics services, based on the example of the 5 Post LLC's operations, as well as become the basis for future researches in the field of intelligent technologies in logistics. During the writing of this investigation, the theoretical foundations of modern logistics chain management and machine learning methods have been presented, the mentioned company's activities have been analysed and its experience of implementing the explored innovation in the process of handling customer requests has been reviewed. Furthermore, quantitative and qualitative analyses of the considered case of intellectualisation were conducted by highlighting KPIs and making a correlation SWOT-analysis. Finally, an algorithm for assessing the economic efficiency of machine learning methods in the field of order management was formed and presented, the potential result of their implementation was concretized as well as some future steps to maximise the benefits of the innovation and minimise the identified risks were recommended.