Answers To Your Forecasting Questions

Answers to Your Forecasting Questions [ Q ] What is the difference between outlier and seasonality? [ A ] An outlier is an unusual value that occurs once in a while. Sales of a certain department store went up signifi cantly in one month because of the Olympic games in town, or dropped sharply because of heavy snow. These are outliers that occur, but not at any set time. Seasonality, on the other hand, occurs every year regularly and at a set time. For example, sales in department stores go up in the month of December because of Christmas. This happens every year and at the same time. Sales of winter sport goods increase during winter, again this happens every year at the same time. [ Q ] How do we determine the seasonality of a product that has a life span of just one year? [ A ] Certainly, we need data of more than one year to make sure seasonality reflected in the data is true seasonality. If in one year in January, sales went up sharply, but in other year in the same month it did not, then it is an outlier, not seasonality. If a product has seasonality it should consistently, year after year, do well or poorly in the same months. One way to tackle this problem is to look ...