Suppose I have 20 years of monthly data on revenue for my firm. This is the only

Question

Suppose I have 20 years of monthly data on revenue for my firm. This is the only variable I have data for on my firm. It looks like my revenue grows over time. The growth trend doesn’t seem to be constant over time, instead the growth trend seems to drift slightly. In other words, it grows but at a decaying rate of sorts. There might be a seasonal component, since it appears that the firm brings in much more revenue on November and December than any other months. Which two (very specific) forecasting methods would you recommend as the best two options to use to forecast future revenue for my firm? Explain why you choose these.

Explanation / Answer

We will use naïve methods to forecast future trends since data is time series. The two methods apt for the problem statement are:

1. Seasonal naïve method {Quick and Dirty Method] - We set forecast to be equal to the last observed value from the same season of the year (Roll forward mechanism)

Formally, the forecast for time T+h is written as:

yT+hkm where m= seasonal period, k=(h1)/m+1,

2. Drift method - It allows the forecasts to change over time, where the amount of change over time (called the drift) is set to be the average change seen in the historical data. So the forecast for time T+h is given by

yT+h/T1(ytyt1)=yT+h(yTy1/T1).

Related Questions

Navigate

• Browse (All)
• Browse S
• Subjects

Integrity-first tutoring: explanations and feedback only — we do not complete graded work. Learn more.