Question

You are hired by a Danish distributor of consumer goods, Dicgø, to improve their forecasting capabilities. You are tasked with coming up with quarterly forecasts for an item that appears to have level, seasonality, and trend. While the company does have an existing Holt-Winter forecasting model, no one knows what the parameters (Alpha, Beta, or Gamma) are.

You do have some information. For example, you know that historically, the demand in each quarter follows this distribution:

- Q1 (January through March) = 60% of average quarterly demand

- Q2 (April through June) = 80% of average quarterly demand

- Q3 (July through September) = 140% of average quarterly demand

- Q4 (October through December) = 120% of average quarterly demand.

You just ran the forecast at the end of September (end of 2014Q3) and you have the following estimates:

For level:  = 1048 units

For trend: = 40.9 units per quarter

Suppose the actual demand in 2014Q4 is 1050 units. What is the lowest possible value for your estimate for level For a^2014Q4 ?

Answer 1

Seasonal Factors

Quarter 1 = 0.6
Quarter 2 = 0.8
Quarter 3 = 1.4
Quarter 4 = 1.2

Forecast in a multiplicative seasonal method can be calculated using the following formula:

Forecast =[Level + n*Trend]*Seasonal Factor
=[1048+4*40.9]*1.2
=1211.6*1.2
=1453.92