USING VISUAL ANALYTICS AND K-MEANS CLUSTERING FOR MONETISING LOGISTICS DATA, A CASE STUDY WITH MULTIPLE E-COMMERCE COMPANIES

Abstract

Logistics companies possess and collect a large amount of data on the shipments they perform while at the same time facing a challenge to understand their complicated market better. Therefore, investigating whether large databases gathered by logistics companies on their e-commerce partners could be monetised as a business service and how this could eventually be achieved is an important research venture. In this paper we used visual analytics and k-means clustering to see whether the data could be structured and presented in a monetisable way, while at the same time adhering to the quality characteristics necessary for doing so: reliable, accurate, relevant, segmented, secured and anonymized. Results show that is clearly the case for the database we investigated and contained 85989 transactions. Using a semi-structured interview with several key managers of both the logistics company and its e-commerce partners, a business-model canvass was developed that indicates the necessary elements for this venture and the right mindset to manage the process. We can confidently conclude that all elements are present to answer the monetisability question positively and to pretend that given the right visualization and confidence between the companies the process could very well be profitable.