Predictive Analytics in Reverse Supply Chain Management Commodity Life Expectancy for Quality Engineering

As the competitive market becomes more customized and the customer becomes more educated, companies are striving to sell quality products. Moreover, customer relationships are significantly influenced by after product-purchase service quality. Reverse Logistics is one such area, where there is ample room for improvisation. It deals with the process of product return from the customer to the manufacturer. The product maybe returned due to reasons like failure, product lifetime etc. It is different from traditional logistics where processes are carried out from manufacturer to final user stage only. It can be optimized and made predictive in nature to forecast the reverse flow of commodities. Conventionally, the commodities are sent back to the manufacturer upon encounter of failure. The products, under warranty period, are immediately replaced by the manufacturer. However, the quality of the service provided is deteriorating. With the advent of information age, it is possible to be prepared for tomorrow, today. By predicting the time of failure of a commodity, the manufacturer can retain service quality levels and help avoid customer chum. In Supply Chain Management(SCM), there is a plethora of data from different sources and in different formats. Big Data, Machine to Machine(M2M), IOT etc. provide a lot of scope into drawing clairvoyant insights. The aim of this paper is to discuss the methodology to forecast failure of a commodity. Such a model can not only help take prescriptive measures but also improve the service quality and protect a company's loyal customers. The paper also covers the process in all respects like the data extraction, management and cognitive approaches.