Developing intelligent index for fuzzified inventory of supply chain by using neural computing

An intelligent index measures the performance of fuzzified inventory flowing in supply chain which involves various factors of storing cost, backorder cost, cost of placing an order, holding cost, transportation cost, penalty cost, total demand, order quantity, and shortage quantity as the triangular fuzzy numbers. Combined effect of these factors on optimal total cost of the system is a complex case of relationship between inputs and output to provide as an index of the system. To model the complex relationship between input and output of the system where relationship is not easily predictable on linearity or nonlinearity basis, mathematical modelling and techniques literally fail to help us, and then in such a situation, a neural computing method proves to be panacea to produce the decisive intelligent index. In various real life situations including inventory control system, it is a pressing demand to identify and measure the degree of complexity between input and output relationship and to produce some index for optimality of the system. In this paper, a fresh endeavour is made to develop and compute an intelligent index for a fuzzified inventory in supply chain in order to reach the optimality of total cost of the system. The computing algorithm is implemented on R.