Show simple item record

dc.contributor.authorMueller, Christine M.
dc.contributor.authorYao, Lili
dc.date.accessioned2022-06-10T16:04:57Z
dc.date.available2022-06-10T16:04:57Z
dc.date.issued2022-06-10
dc.identifier.urihttps://hdl.handle.net/1721.1/142934
dc.description.abstractThe market for obtaining truckload capacity is becoming more dynamic as demand for truckload freight capacity in the US increases. Freight brokers form a vital connection between shippers and the hundreds of thousands of truckload transportation providers in the US and are critical to unlocking all available freight capacity. Previous research has focused on network and load optimization for freight brokerage firms, but not on optimizing the internal resources dedicated to booking and managing shipments. This study investigates commonalities in features between shipments that require similar amounts of resources to manage using feature engineering to quantify various shipment characteristics and unsupervised machine learning to cluster features. The results of this study found that there is overlap between the shipping cost per mile, the number of carrier cancellations, and the lead times between shipment request, shipment booking, and pickup time. Understanding how these shipment features relate to one another and contribute to overall shipment difficulty will help freight brokerages and third- party logistics providers better anticipate which types of shipments will require more the allocation of more internal resources in order to more effectively manage internal operations.en_US
dc.language.isoen_USen_US
dc.rightsCC0 1.0 Universal*
dc.rights.urihttp://creativecommons.org/publicdomain/zero/1.0/*
dc.subjectTransportationen_US
dc.subjectData Analyticsen_US
dc.subjectMachine Learningen_US
dc.titleA Shipment Difficulty Model for Third-Party Logistics Resource Allocationen_US
dc.typeThesisen_US


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record