Risk Resilient Supply Chain Management Using IoT and Big Data Analytics

Abstract

We are one of the most fortunate generations comparing to others across several decades, who have been witnessing tremendous growth on both the industrial and technological front. This growth spills over to other sectors as well, including infrastructure, logistics and other supporting economy driving factors. The present research is based on novel opportunities presented by several cross domain technological sectors including development in the Internet of Things (IoT) which is primarily communication technology, the Analytics in Big Data (ABD) which deals with huge volumes of diverse types of data and its analysis, to provide solutions for the Supply Chain Logistics Management (SCLM) sector, catering to the movement of resources across various industrial processes. newlineThe SCLM industry in India has rapidly evolved in the last two decades and has seen unparalleled growth, but it still finds itself fraught with unsavory challenges including road accidents, unruly drivers, mismanagement of the economics of fuel, vehicle theft and consignment tracking to name a few. In the search of solution to these problems, the Global Positioning System (GPS) location tracking coupled with smart sensing devices have been found very effective to ensure basic fleet management services. The GPS coordinates and data generated by the location/event sensing trackers, however present new challenges of its own, owing largely to huge amounts of geolocation data being churned out at a fast pace. This real time data is a treasure trove, and our thesis uses Apache Hadoop platform to analyze the voluminous data. We have taken the fleet IoT sensor data from one of the biggest SCLM firms in India for our research study. The study presented interesting findings on individual driver behavior based on driving patterns and unusual event occurrences during trips. Risk analysis on the basis of the same has been applied on a large sample of 100 drivers to reveal the safest and the most risk prone drivers. The study also shed light on the reasons of mor