Scribd
Upload
95 views3 pages

Exponential Smoothing: Mean Absolute Error (Mad)

The document provides demand data for Krispy Doughnuts over the past 6 weeks and asks to forecast week 7 using 3 methods: 3-month moving average, exponential smoothing, and linear trend. Using 3-month moving average, the forecast for week 7 is 260.33 dozens. Using exponential smoothing with alpha of 0.10, the forecast is 226.09 dozens. The 3-month moving average method has a lower mean absolute error and is thus the better forecasting technique for this data.

Uploaded by

Ednelyn Cura
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
95 views3 pages

Exponential Smoothing: Mean Absolute Error (Mad)

The document provides demand data for Krispy Doughnuts over the past 6 weeks and asks to forecast week 7 using 3 methods: 3-month moving average, exponential smoothing, and linear trend. Using 3-month moving average, the forecast for week 7 is 260.33 dozens. Using exponential smoothing with alpha of 0.10, the forecast is 226.09 dozens. The 3-month moving average method has a lower mean absolute error and is thus the better forecasting technique for this data.

Uploaded by

Ednelyn Cura
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

CURA, EDNELYN JOY S.

(A-332)

The data on the tables below are the demand in dozens of doughnuts of Krispy Doughnuts for the past
six weeks, make a forecast for week 7 using 3-month moving average, exponential smoothing with an
alpha of 0.10, and linear trend.

EXPONENTIAL SMOOTHING
ABSOLUTE
PERIOD ACTUAL DEMAND FORECAST
ERROR
Jan 200
Feb 256 200 256 - 200 56
March 287 200 + .10(256-200) 205.60 287 – 205.60 81.40

April 282 205.6 + .10(287-205.60) 213.74 282 – 213.74 68.26

May 247 213.74 + .10(282-213.74) 220.57 247 – 220.57 26.43

June 252 220.57 + .10(247-220.57) 223.21 252 – 223.21 28.79

July 223.21 + .10(252-223.21) 226.09


TOTAL 260.88
MEAN ABSOLUTE ERROR (MAD) 52.18

3-MONTH MOVING AVERAGE


ABSOLUTE
PERIOD ACTUAL DEMAND FORECAST
ERROR
Jan 200
Feb 256
March 287
April 282 (200+256+287)/3 247.67 282 – 247.67 34.33
May 247 (256+287+282)/3 275 247 - 275 28

June 252 (287+282+247)/3 272 252 - 272 20

July (282+247+252)/3 260.33


TOTAL 82.33

MEAN ABSOLUTE ERROR (MAD) 27.44


CURA, EDNELYN JOY S. (A-332)

1. What is your forecast for week 7 using 3 month moving average?

(282+247+252)/3 = 260.33

2. What is your forecast for week 7 using exponential smoothing?

223.21 + 0.10 (252 – 223.21) = 226.09

3. Which is the better forecasting technique for the data, moving average or exponential
smoothing?

The moving average method is a better technique because it has a lower MAD than the
exponential smoothing method. (27.44 < 52.18)

4. Using the 3-month moving average, what period did your forecast start?

The forecast started in the month of April.

5. If 4 month moving average is used, what period must you start your forecast?

The forecast should start in May.

6. In exponential smoothing, to what did you multiply the alpha of 0.10, actual demand or
forecast?

It was multiplied by the difference between actual demand and forecast.


CURA, EDNELYN JOY S. (A-332)

7. Given weights of 0.40 (most recent), 0.20,0.20 and 0.20 for the preceding periods
respectively, what is the forecast for week 7 using weighted moving average?

252(0.40) + 247(0.20) + 282(0.20) + 287(0.20) = 264

You might also like