BUSI 405 HW Moving Averages and Exponential Smoothing Assignment
xlsx
keyboard_arrow_up
School
Liberty University *
*We aren’t endorsed by this school
Course
405
Subject
Industrial Engineering
Date
Feb 20, 2024
Type
xlsx
Pages
4
Uploaded by MagistrateProtonHorse17
4)
Weight, a=0.3
0.1029
6)
Month
Inventory
16-Apr
1,544
16-May
1,913
16-Jun
2,028
16-Jul
1,178
16-Aug
1,554
16-Sep
1,910
16-Oct
1,208
16-Nov
2,467
16-Dec
2,101
17-Jan
1,662
17-Feb
2,432
17-Mar
2,443
Month
Inventory
16-Apr
1,544
16-May
1,913
16-Jun
2,028
16-Jul
1,178
16-Aug
1,554
16-Sep
1,910
16-Oct
1,208
16-Nov
2,467
16-Dec
2,101
17-Jan
1,662
17-Feb
2,432
17-Mar
2,443
10)
Month
Number of Service Calls
Apr-00
19
May-00
31
Jun-00
27
Jul-00
29
If the smoothing factor is high, more weig
August
15)
16)
19)
20)
22)
The term moving average is a statistical t
used to analyze data points by creating a
averages of different subsets of the full d
moving average would be an appropriate
method when the number of observations
the periods in the moving average, the forecast
horizon is very short, and the da
stationary. That is, when the series show
positive or negative trend.
Simple moving average models weigh all equally within a set window, resulting in but slower reaction to change. Exponenti
models
give more weight to
recent data, more sensitive to change but more difficu
calculate. Simple moving average models
appropriate for stationary data, but expo
smoothing is preferable for data with tre
changing patterns.
A Holt's exponential smoothing model is appropriate when the data exhibits a line
with little or no seasonality.
A data pattern exhibiting both trend and would suggest the use of a Winters' expo
smoothing model.
An event model is a feature found in expo
smoothing programs enabling the user to
timing of one or more special events, suc
irregular promotions and natural catastro
calibrating data. ForecastX is one of thes
programs.
3 month Avg. Forecast Error Percentage Error Absolute Value 1828
-650.33
-55.21%
55.21%
1706
-152.33
-9.80%
9.80%
1587
323.33
16.93%
16.93%
1547
-339.33
-28.09%
28.09%
1557
909.67
36.87%
36.87%
1862
239.33
11.39%
11.39%
1925
-263.33
-15.84%
15.84%
2077
355.33
14.61%
14.61%
2065
378.00
15.47%
15.47%
MAPE =
22.69%
5 month Avg. Forecast Error Percentage Error Absolute Value 1643
266.60
13.96%
13.96%
1717
-508.60
-42.10%
42.10%
1576
891.40
36.13%
36.13%
1663
437.60
20.83%
20.83%
1848
-186.00
-11.19%
11.19%
1870
562.40
23.13%
23.13%
1974
469.00
19.20%
19.20%
MAPE =
23.79%
Forecast
21
20.8
21.82
22.338
ght is given to recent observations.
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
- Access to all documents
- Unlimited textbook solutions
- 24/7 expert homework help
23
technique a series of data set. A e forecast s is equal to ata is ws little or no l data points a smoother ial smoothing making them ult to s are onential ends or most ear trend seasonality onential onential o select the ch as ophes, when se kinds of