Technology and information management

R

TIM 125 HW#3

01/31/2019

TIM 125/225: MOT II: Homework #3

Day & Date Completed Assignment Friday (01/25/19) • Start on HW3, Problem 1

Saturday (01/26/19) • Finish up HW3, Problem 1

• Start on HW3, Problem 2

• Finish up HW3, Problem 2

Sunday (01/27/19) • Start on HW3, Problem 3

Tuesday (01/29/19) • Finish up HW3, Problem 3

• Start on HW3, Problem 4

Thursday (01/31/19) • Finish up HW3, Problem 4

• Check work to make sure everything was done correctly and followed through.

Problem 1: Seven-Eleven Japan

1. Define the Real Problem a. Answer the following questions as a group about the 7-11 case study:

• What has Seven-Eleven done in its choice of facility location, inventory

management, transportation, and information infrastructure to develop

capabilities that support its supply chain strategy in Japan?

• Seven-Eleven is attempting to duplicate the supply chain structure that

has succeeded in Japan and the United States with the introduction of CDCs.

What are the pros and cons of this approach? Keep in mind that stores are also

replenished by wholesalers and DSD by manufacturers.

2. Plan a. What information is available for solving the problem?

• Lecture Notes

• Textbook

• Internet

b. What assumptions need to be made to make the solution process manageable?

• I must assume that the documents provided are the correct documents

assigned by the professor.

c. What analysis needs to be performed to resolve the issues defined in Step 1?

• I need to execute my analysis in the form of a text-based report which answer

the questions 3 and 6 from the SCM textbook.

• Problem 1: What has Seven-Eleven done in its choice of facility location,

inventory management, transportation, and information infrastructure to

develop capabilities that support its supply chain strategy in Japan?

o Read the case study for 7-11 Japan in the textbook

o Define the different supply chain strategies listed above

• Problem 2: Seven-Eleven is attempting to duplicate the supply chain structure

that has succeeded in Japan and the United States with the introduction of

CDCs. What are the pros and cons of this approach? Keep in mind that stores

are also replenished by wholesalers and DSD by manufacturers.

o Explain the pros and cons of the CDC approach

3. Execute the Plan PART 1

a. Facility Location

• Convivence stores in Japan have historically been very successful. Even

during hard times, the convenience store was still growing. 7-11 sought

to enter the Japanese market for this very reason. Stores of this type are

so popular that the market has become oversaturated causing many

stores to close and leave. The top 10 stores account for 90% of the sales

and 7-11 is in that top 10.

• Entry into any new market was built around a cluster of 50 to 60 stores

that were to be supported by a distribution center. This clustering

strategy allowed 7-11 to have a high-density presence in an area and

allowed them to operate an efficient distribution system. For example,

the Aichi prefecture began opening stores in 2002, and by 2004 had 108

stores. The clusters of stores in the Aichi prefecture were all fed by the

same distribution center. By 2014, 7-11 owned stores in 42 or 27

prefectures in Japan, approximately 16,000 stores across Japan.

b. Inventory Management

• Through the help of the Graphic order terminal, the POS (point-of-sales)

system store, and the scanner terminal, helped managers have an much

easier time with their inventory management. Managers are able to view

a detailed analysis of the POS data on specific items and then follow up

with placing an order through the graphic order terminal. The

information of the order from the graphic terminal was then relayed to

the store computer of both the appropriate vendor and the seven-eleven

distribution center. The scanner terminal was used to receive products

coming in from a distribution center. Once an order was received the

scanner allowed the managers to easily enter their new supplies into the

system.

c. Transportation

• For transportation, there was two levels to it, one from suppliers to

distribution center and the other from distribution center to the 7-11

stores. Suppliers receive order from all stores, and they sent the order by

truck to distribution center. Each store order was separated so the DC

could easily assign it to the appropriate store truck using the order

information it already had. At the DCs, similar products are directed to a

single temperature-controlled truck and there are 4 different type. he

numbers of stores per truck depended on the sales volume. All deliveries

were made during off-peak hours and were received using the scanner

terminals. There are about 158 DCs in Japan that ensures rapid, reliable

delivery and none these carry any inventory; they just transfer inventory

from supplier trucks to 7-11 distribution trucks.

d. Information Infrastructure

• The managers of each seven-eleven store computer send data through

the POS (point-of sales) system. With the POS system every time a

customer purchased a product data was stored and sent to the

headquarters. Data of register sales, and other data was recorded

through the POS system. The data was then analyzed and updated and

sent back to each seven-eleven store. With this information the

managers of each store were able to better match their store’s supply

with demand. The store computer also gave information on store

inventory, sales, POS data, store equipment and placed orders.

Throughout the year about 70% of the items sold at a seven eleven store

changed according to the POS system.

Part 2 Explain the pros and cons of the CDC approach

CDC Combined Distribution Centers

DSD Direct Store Delivery

Pros • Lower operation costs o Rent or Utility expenditures

for different warehouses reduced.

• Efficient in Operating o Reduces the delivery time

spent at each store. o Reduces the number of

vehicles required for daily delivery service to each store.

• Known to work strategy o US stores currently use this

strategy o Able to put product on the

shelves • 7-11 can depend on other companies to

deliver their goods to the store o 7-11 does not need a

distribution network for products they do not make

• Fresh Products o No inventory is carried at the

DCs. o DCs is just used to transfer

inventory from supplier trucks to Seven-Eleven distribution trucks.

o This will cut down on costs and responsibilities of having to deliver and move goods

• Saved retailer hours o Item data is managed by

vendors and then communicated to retailers which means that retailers do not have to take as long to manage their item data.

Cons • Rush delivery is of high cost o If a mistake occurs in the

miscalculation of supplies additional fees must be paid for rush deliveries.

• Not good if customers are widespread.

o If customers are demanding different items in nearby areas CDCs would be the only distribution center and would only be able to supply what is being carried.

• 7-11 must depend on others to bring them their products

o Since they are not in charge of the delivery of their products they have to wait for other companies to do this

o This means that they cannot dictate when their products arrive

• Keeping track of products o With a DSD products are being

transported from multiple areas meaning that products must be tracked from multiple locations. With CDC all the products are being kept in one place.

4. Check your work

a. We went over our work as a team and talked about if it made sense or not. All of the work that was done was based off of the textbook. We looked over the question and

made sure that we answered all parts of the questions. To verify the popularity of

convenience stores in Japan we as a team took a trip to Tokyo and sampled a number of

the convenience stores available to the Japanese public. 5. Learn and Generalize

a. The case study for 7-11 Japan addressed some of the supply chain strategies that made

their convenience stores expand rapidly around the world. The seven-eleven

distribution system linked the entire supply chain together; its supply chain also has

many CDCs located throughout North America. Seven-Eleven understands the tricks in

supplying and marketing their product. We learned the information infrastructure of

their sales system and inventory management which attributed a significant part of

seven-eleven’s success. Their systems were updated each morning via the network. The

pros of having the CDCs outweighs the cons because it offers fresh product at all of their

convenience stores. Overall, the supply chain strategy of 7-11 in Japan is very responsive

and provides customers with what they need.

Problem 2: Demand Forecasting

1. Define the Real Problem a. 7.1. What role does forecasting play in the supply chain of a build-to-order server

manufacturer such as Dell?

b. 7.2. How could Apple use collaborative forecasting with its suppliers to improve its

supply chain?

c. 7.9. What information do the MSE, MAD, and MAPE provide to a manager? How can the

manager use this information?

d. 7.10. What information do the bias and TS provide to a manager? How can the manager

use this information?

2. Plan a. What information is available for solving the problem?

• Lecture Notes

• Textbook

• Internet

b. What assumptions need to be made to make the solution process manageable?

• Problem Solver

o Student

• Audience:

o CEO or CIO of a company

c. What analysis needs to be performed to resolve the issues defined in Step 1?

• 7.1. What role does forecasting play in the supply chain of a build-to-order

server manufacturer such as Dell?

• 7.2. How could Apple use collaborative forecasting with its suppliers to improve

its supply chain?

• 7.9. What information do the MSE, MAD, and MAPE provide to a manager? How

can the manager use this information?

• 7.10. What information do the bias and TS provide to a manager? How can the

manager use this information?

3. Execute the Plan a. 7.1. What role does forecasting play in the supply chain of a build-to-order

server manufacturer such as Dell?

• Dell obtains PC components in anticipation of customer orders and therefore

they rely on forecasting. Dell uses forecasting to communicate with their

suppliers and match production requirements. This forecast is used to predict

future demand, which determines the quantity of each component needed to

assemble a PC and the plant capacity required to perform the assembly.

b. 7.2. How could Apple use collaborative forecasting with its suppliers to

improve its supply chain?

• Collaborative forecasting requires all supply chain partners to share information

regarding parameters that might affect demand, such as the timing and

magnitude of promotions. Dell could share with their component’s suppliers all

of the promotions, e.g., holiday, back-to-school, etc., they have planned. These

suppliers could, in turn, notify their suppliers of discrete components that a

spike in demand is anticipated. These demand forecasts for end items

determine the demand for components and coupled with knowledge of

fabrication times, allows all members of the supply chain to provide the right

quantity at the right time to their customers.

c. 7.9. What information do the MSE, MAD, and MAPE provide to a manager?

How can the manager use this information?

• Mean Squared Error(MSE) - squared deviation of forecast from demand. It

estimates variance in forecasting error.

• Mean Absolute Deviation(MAD)- Absolute deviation of forecast from demand. It

estimates the standard deviation of the forecast error and gives us the absolute

error allowing us to estimate the expected value. MAD is used to provide

balanced estimation of the mean value.

• Mean Absolute Percentage Error (MAPE)- Absolute of forecast from demand as

percentage of the demand. It gives us the overall percentage of the absolute

error in terms of overall quantity that is forecasted.

• Managers can use this information to forecast accuracy and minimize error.

d. 7.10. What information do the bias and TS provide to a manager? How can the

manager use this information?

• By combining the errors that are detected throughout the entire period of using

the model the bias tells us about any kind of regular tendency for over and

undervaluing data. The fluctuation of the bias should be around 0. Tracking

signal is ratio of Bias to mean absolute deviation that accounts an unbiased

model that includes normal assumptions for predicting demand. Tracking signal

is expected to increase to get high probability. It fluctuates around 0 with an

interval of 6.0. Outside this interval is an alert signal for enlargement of the

regular bias.

4. Check your work a. Is the work correct in every detail?

• Using the book as a source of information, I can safely assume that work I have

written is correct.

b. Are my assumptions reasonable?

• Yes, they are because I used the book as source of information. So, I can assume

that the information I have provided is accurate and correct.

c. In terms of the things I know, do the results make sense?

• Yes, in terms of the things I understood from my research, the results do make a

lot of sense.

5. Learn and Generalize a. From reading the book and working on those discussion problems, I learned that it is

crucial that a forecast is not biased therefore MSE, MAD, MAPE and TS allow us to

minimize error and prevent bias in the forecast. I believe these discussion questions

helped me further understand the usefulness of Forecasting and its key components

MSE, MAD, etc. and their functions in giving the company a competitive advantage.

Problem 3: Tahoe Salt (Chapter 7 continued)

1. Define the Real Problem a. Forecast demand using the:

• Static method (make sure to include the appropriate error analysis)

• Moving Average and Simple Exponential Smoothing Forecasting methods.

2. Plan a. What information is available for solving the problem?

• Lecture Notes

• Textbook

• Internet

b. What assumptions need to be made to make the solution process manageable?

• Problem Solver

o Market Analyst

• Audience:

o CEO or CIO of a company

c. What analysis needs to be performed to resolve the issues defined in Step 1?

• Use previous homework’s static method solution and then include error

analysis into it

• Follow textbook to match solutions

3. Execute the Plan

Copied Static Method Forecasting over from HW 2 but now including error analysis:

t = Period

P = Periods in a cycle

St = estimate of seasonal factor for Period t Dt = actual demand observed in Period t

D’t: De-Seasonalized Data

Ft = forecast of demand for Period t

a. STEP 1 De-seasonalize the Data • Since there are an even number of period, I will have to find the average of two

averages corresponding with periods 1-4 and 2-5.

-

10,000

20,000

30,000

40,000

50,000

1 2 3 4 5 6 7 8 9 10 11 12

D e

m a

n d

Period

Quarterly Demand at Tahoe Salt

b. STEP 2 Regress the Data

• We obtain L = 18,439 and T = 524

• Regressed Equation: Regressed Demand = 18,439 + 524t

• Plugging =18,439+A2*524 into Excel and copying down the “Regressed Data”

coulomb to apply the regression equation to all actual demand points resulted

in the following:

c. STEP 3 Determine the Seasonal Factors

• Formula:

I then apply this formula to Excel by dividing columns D/F to derive to the seasonal factor.

RESULTS:

d. STEP 4 Calculate the Average Seasonal Factors

Savg1 = (S1+S5+S9)/3 = 0.47

Savg2 = (S2+S6+S10)/3 = 0.68

Savg3 = (S3+S7+S11)/3 =1.17

Savg4 = (S4+S8+S12)/3 = 1.66

e. STEP 5 Forecasting

• Finally, I forecast by multiplying the regressed factor and the seasonal factor

f. STEP 6 Error Analysis

• Error = Forecast – Demand

• Absolute deviation

• Mean squared error (MSE)

• Mean absolute deviation (MAD)

• Mean absolute percentage error (MAPE)

• Tracking signal (TS)

g. Adaptive Forecasting Moving Average:

• Using these formulas in excel we are able to calculate the Level, Forecast,

Error, Absolute Error, MSE, MAD, %Error, MAPE, and TS.

h. Adaptive Forecasting Simple Exponential Smoothing:

• The forecasting team next uses a simple exponential smoothing

approach, with a = 0.1, to forecast demand. This method is also tested on

the 12 quarters of historical data. Using Equation 7.11, the team

estimates the initial level for Period 0 to be the average demand for

Periods 1 through 12 (see worksheet Figure 7-8). The initial level is the

average of the demand entries in cells B3 to B14 in Figure 7-8 and results

in L0 = 22,083

• Using the given formulas in excel, the figure below was created:

4. Check your work a. Error Analysis

b. Are my assumptions reasonable?

• Yes, they are because using the book and using my lecture notes for the

problem, I was able to get all the information that I needed it. So, I can assume

that the information I have provided is accurate and correct.

c. In terms of the things I know, do the results make sense?

• Yes, in terms of the things I understood from the book, the results do make a lot

of sense.

5. Learn and Generalize a. The different ways to forecast demand allow us to see which one has larger

error. Error analysis allows us to see whether the quality of the forecast is good. I

believe with more practice I will be able to do this with ease.

Problem 4: Demand Forecasting for ABC Corporation

1. Define the Real Problem a. Consider monthly demand for the ABC Corporation, as shown in Table 7-3. Forecast the

monthly demand for Year 6 using the static method for forecasting. Evaluate the bias,

TS, MAD, MAPE, and MSE. Evaluate the quality of the forecast.

2. Plan a. What information is available for solving the problem?

• Lecture Notes

• Textbook

b. What assumptions need to be made to make the solution process manageable?

• Problem Solver

o Market Analyst

• Audience:

o CEO or CIO of a company

c. What analysis needs to be performed to resolve the issues defined in Step 1?

• Forecast the demand

• Evaluate the bias, TS, MAD, MAPE, and MSE.

• Evaluate the quality of the forecast.

3. Execute the Plan

Comment: The Break in the graph represent where the year ends.

Since we are doing an analysis on a yearly basis, periodicity (p) is 12. We must find the time at

which de-seasonalized demand starts.

Year Months Period Demand Dt De-Sea Demand

January 1 2,000

February 2 3,000

March 3 3,000

April 4 3,000

May 5 4,000

June 6 6,000

July 7 7,000 6,542

August 8 6,000 6,625

September 9 10,000 6,667

October 10 12,000 6,750

November 11 14,000 6,875

December 12 8,000 7,000

January 13 3,000 6,917

February 14 4,000 6,833

March 15 3,000 7,000

April 16 5,000 7,083

May 17 5,000 7,167

June 18 8,000 7,333

July 19 3,000 7,375

August 20 8,000 7,375

September 21 12,000 7,500

October 22 12,000 7,500

November 23 16,000 7,375

December 24 10,000 7,250

January 25 2,000 7,333

February 26 5,000 7,583

March 27 5,000 7,792

April 28 3,000 8,042

May 29 4,000 8,250

June 30 6,000 8,250

July 31 7,000 8,292

August 32 10,000 8,375

September 33 15,000 8,292

October 34 15,000 8,208

November 35 18,000 8,208

December 36 8,000 8,292

January 37 5,000 8,458

February 38 4,000 8,750

March 39 4,000 8,958

April 40 2,000 9,042

May 41 5,000 9,167

June 42 7,000 9,417

July 43 10,000 9,583

August 44 14,000 9,500

September 45 16,000 9,375

October 46 16,000 9,333

November 47 20,000 9,417

December 48 12,000 9,458

January 49 5,000 9,333

February 50 2,000 9,083

March 51 3,000 9,083

April 52 2,000 9,417

May 53 7,000 9,667

June 54 6,000 9,583

July 55 8,000

August 56 10,000

September 57 20,000

October 58 20,000

November 59 22,000

December 60 8,000 5

1

2

3

4

We obtain L = 5997.26 and T = 70.25

Regressed Equation: Regressed Demand = 5997.26 + 70.25t

Plugging = 5997.26 +A2*70.25 into Excel and copying down the “Regressed Data” coulomb to

apply the regression equation to all actual demand points resulted in the following:

Year Months Period Demand Dt De-Sea Demand

January 1 2,000

February 2 3,000

March 3 3,000

April 4 3,000

May 5 4,000

June 6 6,000

July 7 7,000 6,542

August 8 6,000 6,625

September 9 10,000 6,667

October 10 12,000 6,750

November 11 14,000 6,875

December 12 8,000 7,000

January 13 3,000 6,917

February 14 4,000 6,833

March 15 3,000 7,000

April 16 5,000 7,083

May 17 5,000 7,167

June 18 8,000 7,333

July 19 3,000 7,375

August 20 8,000 7,375

September 21 12,000 7,500

October 22 12,000 7,500

November 23 16,000 7,375

December 24 10,000 7,250

January 25 2,000 7,333

February 26 5,000 7,583

March 27 5,000 7,792

April 28 3,000 8,042

May 29 4,000 8,250

June 30 6,000 8,250

July 31 7,000 8,292

August 32 10,000 8,375

September 33 15,000 8,292

October 34 15,000 8,208

November 35 18,000 8,208

December 36 8,000 8,292

January 37 5,000 8,458

February 38 4,000 8,750

March 39 4,000 8,958

April 40 2,000 9,042

May 41 5,000 9,167

June 42 7,000 9,417

July 43 10,000 9,583

August 44 14,000 9,500

September 45 16,000 9,375

October 46 16,000 9,333

November 47 20,000 9,417

December 48 12,000 9,458

January 49 5,000 9,333

February 50 2,000 9,083

March 51 3,000 9,083

April 52 2,000 9,417

May 53 7,000 9,667

June 54 6,000 9,583

July 55 8,000

August 56 10,000

September 57 20,000

October 58 20,000

November 59 22,000

December 60 8,000 5

1

2

3

4

Year Months Period Demand Dt De-Sea Demand Regressed De-Sea Demand

January 1 2,000 6,068

February 2 3,000 6,138

March 3 3,000 6,208

April 4 3,000 6,278

May 5 4,000 6,349

June 6 6,000 6,419

July 7 7,000 6,542 6,489

August 8 6,000 6,625 6,559

September 9 10,000 6,667 6,630

October 10 12,000 6,750 6,700

November 11 14,000 6,875 6,770

December 12 8,000 7,000 6,840

January 13 3,000 6,917 6,911

February 14 4,000 6,833 6,981

March 15 3,000 7,000 7,051

April 16 5,000 7,083 7,121

May 17 5,000 7,167 7,192

June 18 8,000 7,333 7,262

July 19 3,000 7,375 7,332

August 20 8,000 7,375 7,402

September 21 12,000 7,500 7,473

October 22 12,000 7,500 7,543

November 23 16,000 7,375 7,613

December 24 10,000 7,250 7,683

January 25 2,000 7,333 7,754

February 26 5,000 7,583 7,824

March 27 5,000 7,792 7,894

April 28 3,000 8,042 7,964

May 29 4,000 8,250 8,035

June 30 6,000 8,250 8,105

July 31 7,000 8,292 8,175

August 32 10,000 8,375 8,245

September 33 15,000 8,292 8,316

October 34 15,000 8,208 8,386

November 35 18,000 8,208 8,456

December 36 8,000 8,292 8,526

January 37 5,000 8,458 8,597

February 38 4,000 8,750 8,667

March 39 4,000 8,958 8,737

April 40 2,000 9,042 8,807

May 41 5,000 9,167 8,878

June 42 7,000 9,417 8,948

July 43 10,000 9,583 9,018

August 44 14,000 9,500 9,088

September 45 16,000 9,375 9,159

October 46 16,000 9,333 9,229

November 47 20,000 9,417 9,299

December 48 12,000 9,458 9,369

January 49 5,000 9,333 9,440

February 50 2,000 9,083 9,510

March 51 3,000 9,083 9,580

April 52 2,000 9,417 9,650

May 53 7,000 9,667 9,721

June 54 6,000 9,583 9,791

July 55 8,000 9,861

August 56 10,000 9,931

September 57 20,000 10,002

October 58 20,000 10,072

November 59 22,000 10,142

December 60 8,000 10,212 5

1

2

3

4

Year Months Period Demand Dt De-Sea Demand Regressed De-Sea Demand

January 1 2,000 6,068

February 2 3,000 6,138

March 3 3,000 6,208

April 4 3,000 6,278

May 5 4,000 6,349

June 6 6,000 6,419

July 7 7,000 6,542 6,489

August 8 6,000 6,625 6,559

September 9 10,000 6,667 6,630

October 10 12,000 6,750 6,700

November 11 14,000 6,875 6,770

December 12 8,000 7,000 6,840

January 13 3,000 6,917 6,911

February 14 4,000 6,833 6,981

March 15 3,000 7,000 7,051

April 16 5,000 7,083 7,121

May 17 5,000 7,167 7,192

June 18 8,000 7,333 7,262

July 19 3,000 7,375 7,332

August 20 8,000 7,375 7,402

September 21 12,000 7,500 7,473

October 22 12,000 7,500 7,543

November 23 16,000 7,375 7,613

December 24 10,000 7,250 7,683

January 25 2,000 7,333 7,754

February 26 5,000 7,583 7,824

March 27 5,000 7,792 7,894

April 28 3,000 8,042 7,964

May 29 4,000 8,250 8,035

June 30 6,000 8,250 8,105

July 31 7,000 8,292 8,175

August 32 10,000 8,375 8,245

September 33 15,000 8,292 8,316

October 34 15,000 8,208 8,386

November 35 18,000 8,208 8,456

December 36 8,000 8,292 8,526

January 37 5,000 8,458 8,597

February 38 4,000 8,750 8,667

March 39 4,000 8,958 8,737

April 40 2,000 9,042 8,807

May 41 5,000 9,167 8,878

June 42 7,000 9,417 8,948

July 43 10,000 9,583 9,018

August 44 14,000 9,500 9,088

September 45 16,000 9,375 9,159

October 46 16,000 9,333 9,229

November 47 20,000 9,417 9,299

December 48 12,000 9,458 9,369

January 49 5,000 9,333 9,440

February 50 2,000 9,083 9,510

March 51 3,000 9,083 9,580

April 52 2,000 9,417 9,650

May 53 7,000 9,667 9,721

June 54 6,000 9,583 9,791

July 55 8,000 9,861

August 56 10,000 9,931

September 57 20,000 10,002

October 58 20,000 10,072

November 59 22,000 10,142

December 60 8,000 10,212 5

1

2

3

4

Seasonal Factor is then calculated by dividing the Demand by the RDD.

Year Months Period Demand Dt De-Sea Demand Regressed De-Sea Demand Seasonal Factor Avg Seasonal Factor

January 1 2,000 6,068 0.33 0.43

February 2 3,000 6,138 0.49 0.47

March 3 3,000 6,208 0.48 0.46

April 4 3,000 6,278 0.48 0.40

May 5 4,000 6,349 0.63 0.62

June 6 6,000 6,419 0.93 0.83

July 7 7,000 6,542 6,489 1.08 0.85

August 8 6,000 6,625 6,559 0.91 1.15

September 9 10,000 6,667 6,630 1.51 1.73

October 10 12,000 6,750 6,700 1.79 1.78

November 11 14,000 6,875 6,770 2.07 2.12

December 12 8,000 7,000 6,840 1.17 1.09

January 13 3,000 6,917 6,911 0.43

February 14 4,000 6,833 6,981 0.57

March 15 3,000 7,000 7,051 0.43

April 16 5,000 7,083 7,121 0.70

May 17 5,000 7,167 7,192 0.70

June 18 8,000 7,333 7,262 1.10

July 19 3,000 7,375 7,332 0.41

August 20 8,000 7,375 7,402 1.08

September 21 12,000 7,500 7,473 1.61

October 22 12,000 7,500 7,543 1.59

November 23 16,000 7,375 7,613 2.10

December 24 10,000 7,250 7,683 1.30

January 25 2,000 7,333 7,754 0.26

February 26 5,000 7,583 7,824 0.64

March 27 5,000 7,792 7,894 0.63

April 28 3,000 8,042 7,964 0.38

May 29 4,000 8,250 8,035 0.50

June 30 6,000 8,250 8,105 0.74

July 31 7,000 8,292 8,175 0.86

August 32 10,000 8,375 8,245 1.21

September 33 15,000 8,292 8,316 1.80

October 34 15,000 8,208 8,386 1.79

November 35 18,000 8,208 8,456 2.13

December 36 8,000 8,292 8,526 0.94

January 37 5,000 8,458 8,597 0.58

February 38 4,000 8,750 8,667 0.46

March 39 4,000 8,958 8,737 0.46

April 40 2,000 9,042 8,807 0.23

May 41 5,000 9,167 8,878 0.56

June 42 7,000 9,417 8,948 0.78

July 43 10,000 9,583 9,018 1.11

August 44 14,000 9,500 9,088 1.54

September 45 16,000 9,375 9,159 1.75

October 46 16,000 9,333 9,229 1.73

November 47 20,000 9,417 9,299 2.15

December 48 12,000 9,458 9,369 1.28

January 49 5,000 9,333 9,440 0.53

February 50 2,000 9,083 9,510 0.21

March 51 3,000 9,083 9,580 0.31

April 52 2,000 9,417 9,650 0.21

May 53 7,000 9,667 9,721 0.72

June 54 6,000 9,583 9,791 0.61

July 55 8,000 9,861 0.81

August 56 10,000 9,931 1.01

September 57 20,000 10,002 2.00

October 58 20,000 10,072 1.99

November 59 22,000 10,142 2.17

December 60 8,000 10,212 0.785

1

2

3

4

We then calculate the average seasonal factor for 12 periods. We take the seasonal factor for

each of the 12 months and average them.

Year Months Period Demand Dt De-Sea Demand Regressed De-Sea Demand Seasonal Factor Avg Seasonal Factor

January 1 2,000 6,068 0.33 0.43

February 2 3,000 6,138 0.49 0.47

March 3 3,000 6,208 0.48 0.46

April 4 3,000 6,278 0.48 0.40

May 5 4,000 6,349 0.63 0.62

June 6 6,000 6,419 0.93 0.83

July 7 7,000 6,542 6,489 1.08 0.85

August 8 6,000 6,625 6,559 0.91 1.15

September 9 10,000 6,667 6,630 1.51 1.73

October 10 12,000 6,750 6,700 1.79 1.78

November 11 14,000 6,875 6,770 2.07 2.12

December 12 8,000 7,000 6,840 1.17 1.09

January 13 3,000 6,917 6,911 0.43

February 14 4,000 6,833 6,981 0.57

March 15 3,000 7,000 7,051 0.43

April 16 5,000 7,083 7,121 0.70

May 17 5,000 7,167 7,192 0.70

June 18 8,000 7,333 7,262 1.10

July 19 3,000 7,375 7,332 0.41

August 20 8,000 7,375 7,402 1.08

September 21 12,000 7,500 7,473 1.61

October 22 12,000 7,500 7,543 1.59

November 23 16,000 7,375 7,613 2.10

December 24 10,000 7,250 7,683 1.30

January 25 2,000 7,333 7,754 0.26

February 26 5,000 7,583 7,824 0.64

March 27 5,000 7,792 7,894 0.63

April 28 3,000 8,042 7,964 0.38

May 29 4,000 8,250 8,035 0.50

June 30 6,000 8,250 8,105 0.74

July 31 7,000 8,292 8,175 0.86

August 32 10,000 8,375 8,245 1.21

September 33 15,000 8,292 8,316 1.80

October 34 15,000 8,208 8,386 1.79

November 35 18,000 8,208 8,456 2.13

December 36 8,000 8,292 8,526 0.94

January 37 5,000 8,458 8,597 0.58

February 38 4,000 8,750 8,667 0.46

March 39 4,000 8,958 8,737 0.46

April 40 2,000 9,042 8,807 0.23

May 41 5,000 9,167 8,878 0.56

June 42 7,000 9,417 8,948 0.78

July 43 10,000 9,583 9,018 1.11

August 44 14,000 9,500 9,088 1.54

September 45 16,000 9,375 9,159 1.75

October 46 16,000 9,333 9,229 1.73

November 47 20,000 9,417 9,299 2.15

December 48 12,000 9,458 9,369 1.28

January 49 5,000 9,333 9,440 0.53

February 50 2,000 9,083 9,510 0.21

March 51 3,000 9,083 9,580 0.31

April 52 2,000 9,417 9,650 0.21

May 53 7,000 9,667 9,721 0.72

June 54 6,000 9,583 9,791 0.61

July 55 8,000 9,861 0.81

August 56 10,000 9,931 1.01

September 57 20,000 10,002 2.00

October 58 20,000 10,072 1.99

November 59 22,000 10,142 2.17

December 60 8,000 10,212 0.785

1

2

3

4

Year Months Period Demand Dt De-Sea Demand Regressed De-Sea Demand Seasonal Factor Avg Seasonal Factor

January 1 2,000 6,068 0.33 0.43

February 2 3,000 6,138 0.49 0.47

March 3 3,000 6,208 0.48 0.46

April 4 3,000 6,278 0.48 0.40

May 5 4,000 6,349 0.63 0.62

June 6 6,000 6,419 0.93 0.83

July 7 7,000 6,542 6,489 1.08 0.85

August 8 6,000 6,625 6,559 0.91 1.15

September 9 10,000 6,667 6,630 1.51 1.73

October 10 12,000 6,750 6,700 1.79 1.78

November 11 14,000 6,875 6,770 2.07 2.12

December 12 8,000 7,000 6,840 1.17 1.09

January 13 3,000 6,917 6,911 0.43

February 14 4,000 6,833 6,981 0.57

March 15 3,000 7,000 7,051 0.43

April 16 5,000 7,083 7,121 0.70

May 17 5,000 7,167 7,192 0.70

June 18 8,000 7,333 7,262 1.10

July 19 3,000 7,375 7,332 0.41

August 20 8,000 7,375 7,402 1.08

September 21 12,000 7,500 7,473 1.61

October 22 12,000 7,500 7,543 1.59

November 23 16,000 7,375 7,613 2.10

December 24 10,000 7,250 7,683 1.30

January 25 2,000 7,333 7,754 0.26

February 26 5,000 7,583 7,824 0.64

March 27 5,000 7,792 7,894 0.63

April 28 3,000 8,042 7,964 0.38

May 29 4,000 8,250 8,035 0.50

June 30 6,000 8,250 8,105 0.74

July 31 7,000 8,292 8,175 0.86

August 32 10,000 8,375 8,245 1.21

September 33 15,000 8,292 8,316 1.80

October 34 15,000 8,208 8,386 1.79

November 35 18,000 8,208 8,456 2.13

December 36 8,000 8,292 8,526 0.94

January 37 5,000 8,458 8,597 0.58

February 38 4,000 8,750 8,667 0.46

March 39 4,000 8,958 8,737 0.46

April 40 2,000 9,042 8,807 0.23

May 41 5,000 9,167 8,878 0.56

June 42 7,000 9,417 8,948 0.78

July 43 10,000 9,583 9,018 1.11

August 44 14,000 9,500 9,088 1.54

September 45 16,000 9,375 9,159 1.75

October 46 16,000 9,333 9,229 1.73

November 47 20,000 9,417 9,299 2.15

December 48 12,000 9,458 9,369 1.28

January 49 5,000 9,333 9,440 0.53

February 50 2,000 9,083 9,510 0.21

March 51 3,000 9,083 9,580 0.31

April 52 2,000 9,417 9,650 0.21

May 53 7,000 9,667 9,721 0.72

June 54 6,000 9,583 9,791 0.61

July 55 8,000 9,861 0.81

August 56 10,000 9,931 1.01

September 57 20,000 10,002 2.00

October 58 20,000 10,072 1.99

November 59 22,000 10,142 2.17

December 60 8,000 10,212 0.785

1

2

3

4

Now we forecast the demand by taking the equation

Deseasonalized Demand = 5997.26 + 70.25t, and multiplying it by the average seasonal factor

for each period.

F61 = (5997.26 + 70.25 x 61)0.43 = 4387

F62 = (5997.26 + 70.25 x 62 )0.47 = 4913

F63 = (5997.26 + 70.25 x 63)0.46 = 4822

F64 = (5997.26 + 70.25 x 64)0.40 = 4178

a. STEP 6 Error Analysis

• Error = Forecast – Demand

• Absolute deviation

• Mean squared error (MSE)

• Mean absolute deviation (MAD)

• Mean absolute percentage error (MAPE)

• Tracking signal (TS)

The Results are all given in the table below!!

Now we can evaluate the Forecast

We can see from the tracking signals that 3 of the periods are outside the interval of [-6,6],

meaning an underestimation in demand. The MAPE provides evidence that the forecast error is

acceptable due to relatively low percentages which displays the minimal differences between

the forecasted and actual demand data. The amount of errors does not seem to be high which

means that the forecast was good.

Year Months Period Demand Dt De-Sea Demand Regres. De-Sea Demand Seasonal Factor Avg Seasonal Factor Forecast Error Abs Error MSE MAD % Error MAPE TS

January 1 2,000 6,068 0.33 0.43 2588 588 588 346,233 588 29 29 1

February 2 3,000 6,138 0.49 0.47 2913 -87 87 176,935 338 3 16 1.48

March 3 3,000 6,208 0.48 0.46 2872 -128 128 123,424 268 4 12 1.39

April 4 3,000 6,278 0.48 0.40 2500 -500 500 155,074 326 17 13 -0.39

May 5 4,000 6,349 0.63 0.62 3944 -56 56 124,678 272 1 11 -0.67

June 6 6,000 6,419 0.93 0.83 5356 -644 644 173,097 334 11 11 -2.48

July 7 7,000 6,542 6,489 1.08 0.85 5534 -1466 1466 455,274 496 21 12 -4.63

August 8 6,000 6,625 6,559 0.91 1.15 7551 1551 1551 698,909 628 26 14 -1.18

September 9 10,000 6,667 6,630 1.51 1.73 11489 1489 1489 867,517 723 15 14 1.03

October 10 12,000 6,750 6,700 1.79 1.78 11913 -87 87 781,531 660 1 13 1.00

November 11 14,000 6,875 6,770 2.07 2.12 14377 377 377 723,411 634 3 12 1.63

December 12 8,000 7,000 6,840 1.17 1.09 7488 -512 512 684,968 624 6 11 0.84

January 13 3,000 6,917 6,911 0.43 2948 -52 52 632,486 580 2 11 0.81

February 14 4,000 6,833 6,981 0.57 3313 -687 687 621,054 587 17 11 -0.37

March 15 3,000 7,000 7,051 0.43 3262 262 262 584,224 566 9 11 0.08

April 16 5,000 7,083 7,121 0.70 2836 -2164 2164 840,484 666 43 13 -3.18

May 17 5,000 7,167 7,192 0.70 4468 -532 532 807,684 658 11 13 -4.03

June 18 8,000 7,333 7,262 1.10 6059 -1941 1941 972,113 729 24 13 -6.30

July 19 3,000 7,375 7,332 0.41 6253 3253 3253 1,477,982 862 108 18 -1.55

August 20 8,000 7,375 7,402 1.08 8521 521 521 1,417,655 845 7 18 -0.97

September 21 12,000 7,500 7,473 1.61 12950 950 950 1,393,092 850 8 17 0.16

October 22 12,000 7,500 7,543 1.59 13411 1411 1411 1,420,317 875 12 17 1.76

November 23 16,000 7,375 7,613 2.10 16167 167 167 1,359,782 845 1 16 2.03

December 24 10,000 7,250 7,683 1.30 8411 -1589 1589 1,408,345 876 16 16 0.14

January 25 2,000 7,333 7,754 0.26 3308 1308 1308 1,420,411 893 65 18 1.60

February 26 5,000 7,583 7,824 0.64 3713 -1287 1287 1,429,517 908 26 19 0.16

March 27 5,000 7,792 7,894 0.63 3652 -1348 1348 1,443,881 924 27 19 -1.30

April 28 3,000 8,042 7,964 0.38 3171 171 171 1,393,363 898 6 19 -1.15

May 29 4,000 8,250 8,035 0.50 4992 992 992 1,379,242 901 25 19 -0.05

June 30 6,000 8,250 8,105 0.74 6762 762 762 1,352,642 896 13 19 0.80

July 31 7,000 8,292 8,175 0.86 6972 -28 28 1,309,033 868 0 18 0.80

August 32 10,000 8,375 8,245 1.21 9491 -509 509 1,276,209 857 5 18 0.22

September 33 15,000 8,292 8,316 1.80 14411 -589 589 1,248,065 849 4 17 -0.48

October 34 15,000 8,208 8,386 1.79 14910 -90 90 1,211,594 826 1 17 -0.60

November 35 18,000 8,208 8,456 2.13 17958 -42 42 1,177,029 804 0 16 -0.67

December 36 8,000 8,292 8,526 0.94 9334 1334 1334 1,193,744 819 17 16 0.97

January 37 5,000 8,458 8,597 0.58 3667 -1333 1333 1,209,484 833 27 16 -0.64

February 38 4,000 8,750 8,667 0.46 4113 113 113 1,177,990 814 3 16 -0.52

March 39 4,000 8,958 8,737 0.46 4042 42 42 1,147,830 794 1 16 -0.48

April 40 2,000 9,042 8,807 0.23 3507 1507 1507 1,175,911 812 75 17 1.39

May 41 5,000 9,167 8,878 0.56 5516 516 516 1,153,716 805 10 17 2.04

June 42 7,000 9,417 8,948 0.78 7466 466 466 1,131,412 796 7 17 2.65

July 43 10,000 9,583 9,018 1.11 7691 -2309 2309 1,229,068 832 23 17 -0.24

August 44 14,000 9,500 9,088 1.54 10462 -3538 3538 1,485,651 893 25 17 -4.19

September 45 16,000 9,375 9,159 1.75 15871 -129 129 1,453,004 876 1 17 -4.42

October 46 16,000 9,333 9,229 1.73 16409 409 409 1,425,057 866 3 16 -3.99

November 47 20,000 9,417 9,299 2.15 19748 -252 252 1,396,090 853 1 16 -4.35

December 48 12,000 9,458 9,369 1.28 10257 -1743 1743 1,430,330 872 15 16 -6.26

January 49 5,000 9,333 9,440 0.53 4027 -973 973 1,420,464 874 19 16 -7.36

February 50 2,000 9,083 9,510 0.21 4513 2513 2513 1,518,335 906 126 18 -4.32

March 51 3,000 9,083 9,580 0.31 4432 1432 1432 1,528,765 917 48 19 -2.71

April 52 2,000 9,417 9,650 0.21 3843 1843 1843 1,564,664 934 92 20 -0.69

May 53 7,000 9,667 9,721 0.72 6039 -961 961 1,552,552 935 14 20 -1.71

June 54 6,000 9,583 9,791 0.61 8169 2169 2169 1,610,934 958 36 21 0.59

July 55 8,000 9,861 0.81 8410 410 410 1,584,703 948 5 20 1.03

August 56 10,000 9,931 1.01 11432 1432 1432 1,593,035 957 14 20 2.52

September 57 20,000 10,002 2.00 17332 -2668 2668 1,689,937 987 13 20 -0.26

October 58 20,000 10,072 1.99 17908 -2092 2092 1,736,250 1,006 10 20 -2.34

November 59 22,000 10,142 2.17 21538 -462 462 1,710,439 996 2 20 -2.82

December 60 8,000 10,212 0.78 11179 3179 3179 1,850,406 1,033 40 20 0.365

1

2

3

4

4. Check your work a. Is the work correct in every detail?

• Using text and using my lecture notes for the data. I can safely assume that

work I have written is correct.

b. Are my assumptions reasonable?

• I can assume that the information I have provided is accurate and correct.

c. In terms of the things I know, do the results make sense?

• Yes, in terms of the things I understood from my research, the results do make a

lot of sense.

5. Learn and Generalize a. This was a tedious task as it required a lot of number punching, however I have

further strengthened my skill in demand forecasting as I am now able to perform

an error analysis.