A Review on Data Driven Models for Supply Chain Forecasting

Supply chain Management has remained an active area of research due to its widespread applications in several domains of manufacturing business. Supply Chain Management is a broad domain of business analytics with each sub-domain having its own importance. Off late, supply chain forecasting has emerged as a very effective tool which is useful in streamlining production, logistics and manpower thereby critically affecting the profit margin. Supply chain forecasting predominantly deals with forecasting of demands of the products and goods based on previously available data. The estimation of demands directly impacts the production, which in turn influences the supply. The current supply has a critical impact on the future demands. Due to the enormity of data to be analysed, supply chain forecasting is prone to errors in forecasting. Off late, machine learning based algorithms typically termed as evolutionary algorithms have been in the forefront for supply chain forecasting. This paper presents a review of latest evolutionary algorithms in the domain of supply chain forecasting with its salient features.