Predictive Analytics in Food Grain Logistics: Supervised Machine Learning Approach

Procurement, storage and distribution of food grains across the nation are a major challenge for any economy in the world. In India, both public and private sector organisations are involved in the food grains procurement, storage and distribution which completes the food grain supply chain for the whole country. This work focuses on the movement of food grains in the state of Kerala through the railway network. The research deals with the application of machine learning algorithms to predict the occurrence of demurrage cost due to the detention of wagons. In this work, popular classification algorithms such as support vector machine, k-nearest neighbour, decision tree and random forest are used to develop a model to predict the occurrence of demurrage cost. Various performance measures are used to evaluate the different models, and the best model is chosen. The classification models are presented with a case illustration at two warehouses.