RISK: EXPONENTIAL SMOOTHING FORECASTING AND VALUE OF INFORMATION Risk: Simple Exponential Smoothing (SES) Assignment Overview Scenario: You are a consultant for the Excellent Consulting Group (ECG). You have completed the first assignment, developing and

attachment_22 xattachment_13.xlsxattachment_32.xlsx
 

RISK: EXPONENTIAL SMOOTHING FORECASTING AND VALUE OF INFORMATION

Risk: Simple Exponential Smoothing (SES)

Assignment Overview

Scenario: You are a consultant for the Excellent Consulting Group (ECG). You have completed the first assignment, developing and testing a forecasting method that uses Linear Regression (LR) techniques (Module 3 Case). However, the consulting manager at ECG wants to try a different forecasting method as well. Now you decide to try Single Exponential Smoothing (SES) to forecast sales.

Case Assignment

Using this Excel template: Data Chart For BUS520 Case 4 (see attached ) do the following:

1. Calculate the MAPE for Year 2 Linear Regression forecast (use the first spreadsheet tab labeled “Year 2 Forecast – MAPE”).
2. Calculate forecasted sales for Year 2 using SES (use the second spreadsheet tab labeled “SES – MAPE”). Use 0.15 and 0.90 alphas.
3. Compare the MAPE calculated for the LR forecast (#1 above) with the MAPEs calculated using SES.

Then write a report to your boss in which you discuss the results obtained above. Using calculated MAPE values, make a recommendation concerning which method appears to be more accurate for the Year 2 data: SES or Linear Regression.

Assignment Expectations

Analysis

• Accurate and complete SES analysis in Excel.

Written Report

• Length requirements: 4–5 pages minimum (not including Cover and Reference pages). NOTE: You must submit 4-5 pages of written discussion and analysis. This means that you should avoid use of tables and charts as “space fillers.”
• Provide a brief introduction to/background of the problem.
• Complete a written analysis that supports your Excel analysis, discussing the assumptions, rationale, and logic used to complete your SES forecast.
• Give complete, meaningful, and accurate recommendation(s) relating to whether LR or SES is more accurate in predicting sales.

Note: Please Read attached Chapter 3,4,5 and background Reading to be clear. Also Provide Heading for Each Section of Work.

Module 4 – Background

RISK: EXPONENTIAL SMOOTHING FORECASTING AND VALUE OF INFORMATION

Case Background

What if you cannot find another factor that has a high correlation with the forecasted factor? Are there other forecasting methods other than Linear Regression? How do you determine which method is actually the best one?

Chase, C. W., (2013). Demand-driven forecasting: A structured approach to forecasting. John Wiley & Sons. Somerset, NJ. Retrieved from Ebrary.

From the source above, read: SEE ATTACHED

· Chapter 3, pp. 91–93 (the section Some Causes of Forecast Error)

· Chapter 4, pp. 103–113, which provides information on forecast error measures; pay special attention to the sections on the MAPE measurement

· Chapter 5, pp. 125–147; pay attention the sections on Simple Exponential Smoothing (SES)

Download the Excel file 
Case 4 Examples-Practice.xlsx
  (SEE ATTACHED ) that contains an example and a Practice Exercise.

Watch this video that shows how to do SES and calculate MAPE: 

http://permalink.fliqz.com/aspx/permalink.aspx?at=75d6cc75bbe742159e56ad8836531c1d&a=5fae3cf0f1624f39b0341263a6541ea0

PRACTICE: Do the Practice Exercise in the Excel file: 
Case 4 Examples – Practice
(SEE ATTACHED ). Check your work.

You are ready to do the Case 4 problem.

SLP Background

Consider that you may be pretty good sometimes at estimating future probabilities. But you also acknowledge that you might be biased, too. This is where experts are useful, although they do charge a fee for their services. What is the value of the information you could get from an expert? Is it worth paying this expert for his/her advice? Read the paper 
Deciding to Use an Expert
(SEE ATTACHED ) that explains how to make this decision.

Download the Excel file 
SLP 4 Examples-Practice.xlsx
 (SEE ATTACHED ) that provides examples and a Practice Exercise.

Watch this video showing how to determine the value of information: 

http://permalink.fliqz.com/aspx/permalink.aspx?at=f616909cae2d4d06834359502f672aff&a=5fae3cf0f1624f39b0341263a6541ea0

Practice determining the Value of Information; do the Practice Exercise in the Excel file.

You are ready for SLP 4.

Additional Required Reading

(For Discussions, Module 2, 3, and 4)

Download and read 
Subjective Assessments of Risk and Uncertainty
 (SEE ATTACHED ) on subjective probabilities in risk decisions. This paper will be useful for the discussion questions in Module 2, 3, and 4.

Get this journal article from the library. It is lengthy, but you only need to read Section 1.1, pp. 3-5. This section provides a very good review of three major biases that have been studied by the famous team of Kahneman and Tversky.

Laibson, D., & Zeckhauser, R. (1998). Amos Tversky and the ascent of behavioral economics. Journal of Risk & Uncertainty. Feb1998, Vol. 16 Issue 1, p7-47. 41p. Retrieved from Business Source Complete (EBSCO) in the Trident Online Library.

Year 2

Forecast MA

PE

Year 2

PE

= Mean error

= Mean percentage error

ME MPE

ABC Furniture Company

Sales

b1

Customers (x)

Actual Y(t)

Forecast

F(t)

Y(t) – F(t)

APE

b0

January

215

February

259

Y= b0+ b1x

March

325

April

354

May

258

June

199

July

254

August

299

September

264

October

198

November

223

December

261

ME

MPE

MAPE

MAPE = Mean absolute percentage error

SES – MAPE

ABC Furniture Company

Alpha

Year 2

F(t) Y(t) – F(t) PE APE F(t) Y(t) – F(t) PE APE

January
February
March
April
May
June
July
August

September

October MAPE = Mean absolute percentage error
November
December

ERROR:#DIV/0! ERROR:#DIV/0! ERROR:#DIV/0! ERROR:#DIV/0! ERROR:#DIV/0!

ME MPE MAPE ME MPE MAPE

	Alpha
0.15	0.9
Sales, Y(t)
ME = Mean error
MPE = Mean percentage error
					ERROR:#DIV/0!

2

>Example

Alpha

5

F(t) Y(t) – F(t) PE APE

5

1

8

1798

0.000 1798 0.0 0.000 0.000

25

2

66

0.226 1798.0 -332.0

0.226

06

3

18

0.534

0.356

4

.8

0.231

0.074

5

0.363

0.149

6

0.026

0.217

7

0.098

0.083

8

0.217 0.217

0.262

9

0.253

0.143

10

0.019

0.185

11

0.123

0.171

12

0.202

0.251

7.5

ME MPE MAPE

																																																																																																																																																																														Alpha
0.2			5	0.			8
		Mo			Sales, Y(t)						F(t)						Y(t) – F(t)						PE						APE
			1			3			6			1			7			9				0.0								0.000
			12	1			4		1798.0		-332.0	–		0.226	-0.226
			10				11	1715.0	-597.0	–	0.534	1515.8	-397.8	–	0.356
1132	1272	1565.8	–		293	–	0.231	1177.7	94.3		0.074
1090	1095	1492.3	-397.3	–	0.363	1257.9	-162.9	–	0.149
1722	1430	1393.0	37.0		0.026	1	119.4	310.6				0.217
1602	1277	1402.2	-125.2	–	0.098	1383.4	-106.4	–	0.083
1709	1751	137		0.9	380.1	1293.0	458.0		0.262
1547	1962	1465.9	496.1		0.253	1682.3	279.7		0.143
1227	1620	1590.0	30.0		0.019	1920.0	-300.0	–	0.185
1308	1422	159	7.5	-175.5	–	0.123	1665.0	-243.0	–	0.171
1536	1948	1553.6	394.4		0.202	1458.5	489.5		0.251
1513.25	-48.6	-0.072	0.1910	-0.019	0.1764
					ME						MPE						MAPE

Practice Problem

Alpha Alpha

0.9

Mo Sales, Y(t) F(t) Y(t) – F(t) PE APE F(t) Y(t) – F(t) PE APE

1

525 525

2 293
3

4

5

6

7

8

9

10

11

12

ME MPE MAPE ME MPE MAPE

	0.15
					525
	256
	425
	753
	596
	391
	563
	571
	633
	653
	811
	539.1666666667

Practice Problem-Solution

Alpha Alpha
0.15 0.9
Mo Sales, Y(t) F(t) Y(t) – F(t) PE APE F(t) Y(t) – F(t) PE APE

1 525 525 0.0 0.000 0.000 525 0.0 0.000 0.000
2 293

0.792 525.0 -232.0

0.792

3 256

0.915

0.235

4 425

0.071

0.383

5 753

0.402

0.457

6 596

0.168

0.206

7 391

0.307

0.556

8 563

0.124

0.267

9 571

0.118

0.040

10 633

119.4

0.189

0.102

11 653

0.186

0.040 0.040

12 811

0.322

0.198

539.1666666667

25.0

ME MPE MAPE ME MPE MAPE

	5	25.0		-232.0	–		0.792	-0.792
490.2	-234.2	–	0.915	316.2	-60.2	–	0.235
455.1	-30.1	–	0.071	262.0	163.0		0.383
450.6	302.4		0.402	408.7	344.3		0.457
495.9	100.1		0.168	718.6	-122.6	–	0.206
510.9	-119.9	–	0.307	608.3	-217.3	–	0.556
492.9	70.1		0.124	412.7	150.3		0.267
503.5	67.5		0.118	548.0	23.0				0.040
513.6		0.189	568.7	64.3		0.102
531.5	121.5		0.186	626.6	26.4
549.7	261.3		0.322	650.4	160.6		0.198
35.5	-0.048	0.2994	-0.025	0.2730