Previsão de demanda em uma indústria do ramo alimentício

Abstract

Brazil stands out for being the fourth largest milk producer in the world, and the dairy industry, largely composed of small companies, represents an important increase in the country's GDP. In order for these companies to remain competitive in the market, with adequate levels of raw material stock and fully meeting their demand, the importance of using quantitative demand forecasting methods is highlighted to support purchase, production and stocks. In this context, the main objective of this work is to apply quantitative methods of demand forecasting in a small dairy industry, in order to maintain adequate levels of raw material stock and assist in the development of production strategies to avoid losses in sales. This work consists of an applied study, and with regard to the objectives, it is a quantitative research. A descriptive research was carried out, and a case study was developed through a semi-structured interview with the manager of a small dairy company located in São Paulo’s countryside. The data collected refer to the demand for three products from January 2020 to December 2021. From the analysis of the time series, the simple moving average, simple exponential smoothing and time series decomposition models were applied. The results showed that the time series decomposition model proved to be the most accurate for forecasting product demand, with error values for the products strawberry yogurt, açaí yogurt with strawberry and açaí yogurt with banana, of 9.8%, 14.3% and 15.0%, respectively.