Customer Behaviour Forecasting in FMCG Retail Industry; Golpakhsh Avval Co. Case Study

Providing that data mining has been an effective solution of improving the efficiency and the effectiveness of the retail industry, this industry has been the subject of data mining science due to the nature of its data. In this study, the prediction of customer behavior in the retail industry of Fast Moving Consumer Goods is aimed at increasing the quantity and quality of sales in the study of Golpakhsh Avval Co.
The present study is applied in terms of purpose, using data survey to collect data. The research is based on the CRISP-DM process, which uses the RFMCL clustering model, regression classification and regression techniques as well. Eventually, a collaborative recommendation method has been applied for recommendation.
The result is a forecasting model recommended to the best customers goods that they have not bought on a particular date and to a certain amount, so that, the order-based sale is changed to hot sale method. The final solution involves three sub models of customer clustering, sale forecasting and a recommendation system. The five variables model –with MSE/Range accuracy of 2.24% – is solved for recommendation of sales amount.
By implementing the developed recommender system in Golpakhsh Avval Co., the proactive production master plan would be possible to execute. In addition, the marketing approach could be transformed from visiting sales to hot sales in the future which provides considerable savings in shipping and personnel costs.