Supporting an Expert-centric Process of New Product Introduction With Statistical Machine Learning

Industries that sell products with short-term or seasonal life cycles must regularly introduce new products. Forecasting the demand for New Product Introduction (NPI) can be challenging due to fluctuations of many factors such as trend, seasonality, other external and unpredictable phenomena (e.g., COVID-19 pandemic). Traditionally, NPI is an expertcentric process. This paper presents a study on automating forecast demands using statistical Machine Learning (namely, Gradient Boosting XGBoost). We show how overcome shortcomings traditional data preparation underpins manual Moreover, we illustrate role cross-validation techniques hyper-parameter tuning validation models. Finally, provide empirical evidence better than experts.