An Adaptive Neuro Fuzzy Inference System (ANFIS) Based Model for Supply Demand Forecasting

An Adaptive Neuro Fuzzy Inference System (ANFIS) Based Model for Supply Demand Forecasting

Abhishek Solanki1, Prof. Vaishali Upadhyay2

Abstract: Off late, the demand for pharmaceutical products and drugs has ramped up significantly due to the ongoing COVID-19 scenario. Several instances have been reported where large scarcity of drugs have led to fatalities in patients. Hence, the necessity for a holistic approach for demand forecasting for the pharmaceutical supply chain has become imperative. Recently, soft computing techniques are being used widely for demand forecasting due to relatively higher accuracy compared to conventional statistical techniques. This work proposes a wavelet transform-adaptive neuro fuzzy inference system (DWT-ANFIS) hybrid to forecast pharmaceutical products. The DWT has been used as a data cleaning and optimization tool whereas the ANFIS has been used for forecasting. The evaluation of the proposed work has been done based on the mean absolute percentage error, regression and iterations of the system. It has been shown that the proposed system outperforms the existing system in terms of the MAPE.

Keywords: Demand Forecasting, Pharmaceutical Supply Chain, Soft Computing, Adaptive Neuro Fuzzy Inference Systems (ANFIS), Discrete Wavelet Transform, Mean Absolute Percentage Error (MAPE).