Paper Title
DATA ANALYSIS AND LEARNING BASED APPROACH FOR LOGISTICS OPTIMIZATION

Abstract
Abstract - Every industry has been significantly impacted by developments in information and communication technology. Additionally, it affects how service industries like e-commerce carry out the process of satisfying consumer requests for goods. A major concern in e-commerce logistics is the optimization of order dispatch procedures and delivery time prediction. It is observed that the traditional mathematical modeling approach cannot deliver the intended results for route optimization as the problem becomes more and more complex. The objective of this paper is to take into account situations where the amount of available load is less than the permitted vehicle’s maximum capacity between two hubs in order to maximize the utilization of the vehicle’s capacity. The load factor of the vehicle has improved because to this hub-to-hub optimization scheme. With the ideal model, operational effectiveness has increased. The model’s estimations predict that using it will result in a cost reduction of 8–12 percent So, in terms of vehicle allocation and route optimization for transportation services, this hub-to-hub model delivers the optimum vehicle placement for available load at each hub. Keywords - Data Analytics, Logistics Optimization, Route Optimization, Transportation Problem, Hub To Hub Optimization