(INSTITUTO DE TECNOLOGIA, 2015) LIMA, Orlem Pinheiro de; SANTIAGO, Sandro Breval; RODRÍGUEZ, Carlos Manuel Taboada; Jandecy Cabral Leite
The study presents a demand forecasting analysis for a plastic injection industry in the Manaus Industrial Pole (PIM), using the Holt-Winters exponential smoothing method. Monthly sales data over 36 months (2010-2012) were analyzed, identifying additive seasonality patterns. The model was evaluated using Mean Absolute Percentage Error (MAPE) and Theil's U coefficient, demonstrating forecasting efficacy and emphasizing the importance of error analysis for continuous improvements.
