2 - Simple Exponential Smoothing

Question 1

What does a forecast algorithm do?

Answer 1

Predicts y(t+1) given y (1:t)

Question 2

How does the simple exponential smoothing works to provide a forecast of y(t+1)?

Answer 2

geometrical decreasing weights

Question 3

Why can we say that if t is large, the weights’ sum in the average is approximately one?

Answer 3

Question 4

If j increases, what happens to c?

Answer 4

it becomes smaller

Question 5

Classic form of the simple exponential smoothing algorithm

Answer 5

Question 6

Recursive form of the simple exponential smoothing algorithm

Answer 6

Question 7

What does the alpha parameter tell us in the recursive form?

Answer 7

Question 8

Forecast error correction form of the simple exponential smoothing algorithm

Answer 8

• It is another way to write it.
• Ho moltiplicato (1-α) con y(t|t−1) e poi ho messo in evidenza α

Question 9

How is the forecast function in the simple exponential smoothing?

Answer 9

In simple exponential smoothing, the forecast function at time t is assumed to be a constant function of h.
- Praticamente il forecast in t per t+1, t+2 e così via è sempre lo stesso, cioè è flat.

Question 10

How do we tune (choose) the smoothing parameters α?

Answer 10

• consider a (fine) grid of values of α in (0, 1)
• for each α, use the algorithm to recursively compute the one-step-ahead forecasts, for t = 1, … , T
• “Score” the forecasts and choose the value α that gives the best predictive performance.

Question 11

What are the popular measure of predictive performance? That are also the most known scores for the forecast error

Answer 11

Scale dependent:
- Mean Absolute Value (MAE)
- Mean Square Error (MSE)

Non scale dependent:
- Mean Absolute Percentage Value (MAPE)

Question 12

Are trend and seasonal behavior envised in simple exponential smoothing?

Answer 12

Simple exponential smoothing does not envisage a trend nor a seasonal behavior.