Possibilities in using big data to improve supply chain efficiency - A study in the inbound logistics of an automotive company

Abstract

The purpose of this thesis project was to investigate the possibilities of using big data for the material transport process (inbound logistics) of an automotive company. The study was performed in two stages: An exploratory phase and the development of a proof of concept. The first stage allowed the understanding of the material transport process at a strategic, tactical and operational level, as well as the identification of fourteen big data opportunities that support the drivers of the focal company. In the second stage, the CRISP-DM methodology was applied to develop a proof of concept that would transform the material forecast into a transport forecast. It was identified, that the development and implementation of this proof of concept would provide benefits in a tactical level, such as: improved volume optimization, better price negotiation with carriers, improved management of human resources in terminals and better cost control, among others. In order to get these benefits, the focal company may overcome three main gaps: the accuracy and reliability of information in the system, the level of detail and the quality of the data. It was concluded that the use of big data will have a significant positive impact for the focal company.