Machine Learning-Based Forecasting of LRU Demand and Implementation in Kazakhstan Base Airports

Abstract

This paper addresses the optimization of aviation spare parts logistics at base airports. Particular attention is given to Line Replaceable Units (LRUs), which play a critical role in ensuring aircraft operational readiness. The limitations of traditional inventory management methods are analyzed, and the need for the implementation of digital technologies is substantiated. An approach to forecasting LRU demand based on machine learning techniques is proposed. An example of economic impact assessment is presented. It is shown that the implementation of intelligent forecasting systems enables a reduction in inventory holding costs and minimizes aircraft-on-ground (AOG) events.