Optimizing logistics routes with advanced algorithms: comprehensive route prediction and efficiency enhancement
Authors
Wu,Zhilei
Issue Date
2024-09-20
Degree
MSc Data Analytics
Publisher
Rights holder
Rights
Items in eSource are protected by copyright. Previously published items are made available in accordance with the copyright policy of the publisher/copyright holder.
Abstract
This study leverages machine learning and data mining techniques to optimise logistics transportation routes, aiming to enhance efficiency in short-distance deliveries. The research aims to develop reliable predictive models, providing optimization solutions for shortdistance logistics routes by comparing the effectiveness of traditional machine learning algorithms and deep neural networks. The model training used historical data from Amazon Logistics in 2018, with key features including route efficiency, package density, and transit time. The study follows the CRISP-DM framework, evaluating the performance of different models in route prediction and optimization. The deep neural network model, combined with graph theory-based algorithms such as the Traveling Salesman Problem (TSP), significantly improves route optimization outcomes. The research concludes that integrating advanced deep learning models with traditional optimization techniques can lead to substantial cost savings and efficiency improvements for logistics companies, while also enhancing customer satisfaction. Future research is recommended to explore larger datasets, real-time data integration, and the impact of economic and social factors.