Intelligent Sales Prediction for Pharmaceutical Distribution Companies: A Data Mining Based Approach

摘要: One of the problems pharmaceutical distribution companies (PDCs) is how to control inventory levels in order prevent costs excessive and losing customers due drug shortage. Consequently, purpose this study propose a novel method forecast sales PDCs. The presented combination network analysis tools time series forecasting methods. Due lack enough past records each drug, an explorative based conducted find clique sets group members use comembers’ data their prediction. Afterwards, models were built with three different approaches including ARIMA methodology, neural network, advanced hybrid approach. offered by applying its comembers facilitates capturing both linear nonlinear patterns accurately. performance proposed was evaluated real dataset provided one leading PDCs Iran. results indicated that able cope low number while it forecasts medicines