23rd Batch EV Chapter 2 Demand Forecasting EV233072006

625 Operations & Supply Chain Management

Chapter 2 Demand Forecasting Problem

Book: Operations Management by William J. Stevenson (Chapter 3 Forecasting)

Question 01: What is naïve method of forecasting?

A naïve method of forecasting involves using the most recent observation as the forecast for future
periods, assuming that the most recent data point will continue unchanged.
For example, if you were forecasting the demand for a product using a naïve method and the
demand for the last month was 100 units, you would simply forecast that the demand for the next
month would also be 100 units, regardless of any other factors or trends.

Question 02: What is forecasting?

Forecasting is the process of predicting future events based on past data and analysis.

For example, a retail store might use forecasting to predict how many units of a particular product
they will sell in the upcoming months based on historical sales data, market trends, and external
factors like promotions or seasonal fluctuations. This helps the store ensure they have enough
inventory on hand to meet customer demand without overstocking and tying up capital.

Question 03: Why is forecasting important for operations management?

It helps in anticipating demand, optimizing resources, and planning production schedules
efficiently.
For example, a company manufacturing winter clothing needs accurate forecasts to determine how
many jackets to produce in advance of the cold season. Without forecasting, they risk either excess
inventory or stockouts, both of which can result in financial losses and customer dissatisfaction.

Question 04: Briefly explain various techniques of forecasting. Or What are the different
qualitative and quantitative techniques of forecasting

Qualitative techniques include:

Expert opinion: Relying on the judgment of experts in the field.
Delphi method: Iterative process involving a panel of experts making predictions anonymously.
Market research: Gathering data from customers, surveys, or focus groups.

Quantitative techniques include:

Time series analysis: Analyzing historical data to identify patterns and make predictions.
Regression analysis: Establishing relationships between variables to predict future outcomes.
Forecasting models: Using mathematical models such as exponential smoothing or moving
averages.
Simulation: Creating models to simulate different scenarios and predict outcomes.

1 | Page 625 Operations & Supply Chain Management Istiaque Ahmed Chowdhury
23rd Batch EV Chapter 2 Demand Forecasting EV233072006

Question 05: What is capacity? State the importance of capacity decisions.

Maximum output or production capability of a firm's facilities, processes, or resources over a given
period of time.

The importance of capacity decisions lies in their direct impact on a company's ability to meet
customer demand efficiently, maintain competitiveness, optimize resource utilization, and manage
costs effectively. Proper capacity management ensures smooth operations, avoids bottlenecks, and
supports business growth while minimizing risks associated with underutilization or
overutilization of resources.

Question 06: What is significant role of demand forecasting?

Demand forecasting plays a significant role in Operations & Supply Chain Management by
providing insights into future customer demand. It helps businesses make informed decisions
regarding production planning, inventory management, resource allocation, and overall supply
chain optimization. Accurate demand forecasting minimizes stockouts, reduces excess inventory
costs, improves customer satisfaction, and enhances overall operational efficiency.

Question 07: What are the principles of forecasting? Explain the forecasting process.

The principles of forecasting involve understanding historical data, identifying patterns,

considering external factors, and using appropriate methods.

The forecasting process typically includes data collection, analysis, model selection, validation,
and implementation. It aims to predict future demand or resource needs accurately.

2 | Page 625 Operations & Supply Chain Management Istiaque Ahmed Chowdhury
23rd Batch EV Chapter 2 Demand Forecasting EV233072006

Question 08: A chain sweet manufacturer has 7 stores in Chittagong. Sales figures and profits for
the stores are given in the following table:
Sales ('000) Profit ('000)
30 7
41 10
28 7
25 6
33 5
37 8
39 4
(i) Plot the data and decide if a linear model is reasonable:
(ii) Obtain a regression line for the data.
(iii) Predict profit for a store assuming sales of 15,000 TK

3 | Page 625 Operations & Supply Chain Management Istiaque Ahmed Chowdhury
23rd Batch EV Chapter 2 Demand Forecasting EV233072006

Question 09: An electrical contractor's records during the last five weeks indicate the number of
job requests:

Week: 1 2 3 4 5
Requests: 23 29 23 28 25
Predict the number of requests for week 6 using each of these methods:
a. Naive.
b. A four-period moving average. (Round your answer to 2 decimal places.)
c. Exponential smoothing with α = 0.20. Use 22 for week 2 forecast. (Round your intermediate
forecast values and final answers to 2 decimal places.)

4 | Page 625 Operations & Supply Chain Management Istiaque Ahmed Chowdhury
23rd Batch EV Chapter 2 Demand Forecasting EV233072006

Question 10: A lawn care company uses exponential smoothing with trend to forecast monthly
usage of its lawn care products. At the end of July, the company wishes to forecast sales for August.
The trend through June has been 15 additional gallons of product sold per month. Average sales
have been 57 gallons per month. The demand for July was 62 gallons. The company uses a = 0.20
and B = 0.10. Make a forecast including trend for the month of August.

5 | Page 625 Operations & Supply Chain Management Istiaque Ahmed Chowdhury
23rd Batch EV Chapter 2 Demand Forecasting EV233072006

Question 11: A manager at Fit Well department store wants to forecast sales of swimsuits for August
using a three- period weighted moving average. Sales for May, June, and July are 400, 500 and 600
respectively. The manager has decided to weight May (0.25), June (0.25). and July (0.50).

6 | Page 625 Operations & Supply Chain Management Istiaque Ahmed Chowdhury
23rd Batch EV Chapter 2 Demand Forecasting EV233072006

Question 12: The United Hospital is considering the purchasing of a new ambulance. The decision
will rest partly on the anticipated mileage to be driven next year. The miles driven during the past
9 year are as follows:

Year: 1 2 3 4 5 6 7 8 9 10
Mileage: 12 17 20 19 24 21 31 28 36 ?

i. Compute the forecast for the 2nd year to 10th year using exponential smoothing, an initial forecast
for the 1st year is 11000 miles and smoothing constant is 0.2.
ii. Compute Mean Absolute Deviation (MAD) and tracking signal.

7 | Page 625 Operations & Supply Chain Management Istiaque Ahmed Chowdhury
23rd Batch EV Chapter 2 Demand Forecasting EV233072006

Question 13: National Sean Inc. sells radio frequency inventory tags. Monthly sales for a seven-
month period were as follows:

Month February March April May June July August

Sales 19 18 15 20 18 22 20

Forecast sales volume for the month of September using each of the following:
i) three month moving average
ii) A weighted moving average using 0.60, 0.30, and 0.10, 0-60 applying to the most recent one.
iii) Exponential smoothing with a smoothing constant equal to 0.20. Assuming a March forecast of
19 (000).

8 | Page 625 Operations & Supply Chain Management Istiaque Ahmed Chowdhury
23rd Batch EV Chapter 2 Demand Forecasting EV233072006

Question 14: A commercial bakery has recorded sales (in dozens) for three products, as shown below:

a. Predict orders for the following day for each of the products using an appropriate naive method.
Hint: Plot each data set.
b. What should the use of sales data instead of demand imply?

1.a. To make a naive prediction for the orders of each product for the following day, you can use a simple
method like the average daily sales over the available data.
Calculate the Average Daily Sales:
For Blueberry Muffins: Sum up the daily sales for Blueberry Muffins and divide by 15.
30 + 34 + 32 + 34 + 35 + 30 + 34 + 36 + 29 + 31 + 35 + 31 + 37 + 34 + 33
15
Average Daily Sales ≈ 33.13 𝑑𝑜𝑧𝑒𝑛𝑠
So, the average daily sales for Blueberry Muffins are approximately 33.13 dozen.
For Cinnamon Buns: Sum up the daily sales for Cinnamon Buns and divide by 15.
18 + 17 + 19 + 19 + 22 + 23 + 23 + 25 + 24 + 26 + 27 + 28 + 29 + 31 + 33
15
𝐴𝑣𝑒𝑟𝑎𝑔𝑒 𝐷𝑎𝑖𝑙𝑦 𝑆𝑎𝑙𝑒𝑠 ≈ 24.67 𝑑𝑜𝑧𝑒𝑛𝑠
The average daily sales for Cinnamon Buns are approximately 24.67 dozen.
For Cupcakes: Sum up the daily sales for Cupcakes and divide by 15.
45 + 26 + 27 + 23 + 22 + 48 + 29 + 20 + 14 + 18 + 47 + 26 + 27 + 24 + 22
15
𝐴𝑣𝑒𝑟𝑎𝑔𝑒 𝐷𝑎𝑖𝑙𝑦 𝑆𝑎𝑙𝑒𝑠 ≈ 27.53 𝑑𝑜𝑧𝑒𝑛
The average daily sales for Cupcakes are approximately 27.53 dozen.
Predict Orders for the Following Day:
Based on the naive method, the predicted orders for the following day are as follows:

Blueberry Muffins: Approximately 33.13 dozen

Cinnamon Buns: Approximately 24.67 dozen
Cupcakes: Approximately 27.53 dozen

9 | Page 625 Operations & Supply Chain Management Istiaque Ahmed Chowdhury
23rd Batch EV Chapter 2 Demand Forecasting EV233072006

b. What should the use of sales data instead of demand imply?

The use of sales data instead of demand implies that the recorded values are actual sales made by the
bakery on each day. In other words, these values represent the quantity of products sold to customers.
Using sales data can be beneficial because it provides a more accurate reflection of the bakery's
performance and revenue generation.
However, there are a few important points to consider when using sales data for forecasting and
decision-making:
Explanation:
1. Demand vs. Sales: Sales data only represents the quantity of products sold, which is a function of
both customer demand and the bakery's ability to produce and stock products. If demand exceeds
supply, the recorded sales may not fully capture the potential demand for the products.
2. Seasonality and Trends: Sales data may show patterns of seasonality and trends, which can be
helpful for understanding the business's performance over time. It can also aid in planning for peak
seasons and identifying opportunities for growth.
3. Inventory Management: Using sales data can assist in inventory management. By analyzing sales
patterns, the bakery can adjust its production levels and stock to avoid overstocking or understocking
products.
4. Forecasting and Planning: Sales data can be used as historical data to develop more sophisticated
forecasting models. These models can provide more accurate predictions of future demand, allowing
the bakery to plan production, staffing, and marketing efforts more effectively.
5. Customer Behavior: Analyzing sales data can offer insights into customer preferences and behavior.
This knowledge can be used to tailor products and marketing strategies to meet customers' needs and
expectations better.
a. Using a naive method, the predicted orders for the following day are approximately:
Blueberry Muffins: 33.13 dozen
Cinnamon Buns: 24.67 dozen
Cupcakes: 27.53 dozen
b. Relying solely on sales data instead of demand data for inventory management can lead to inventory
problems like stockouts, overstocking, and missed opportunities due to not considering factors
influencing future demand. It's essential to integrate demand forecasting for better inventory decisions.

10 | Page 625 Operations & Supply Chain Management Istiaque Ahmed Chowdhury
23rd Batch EV Chapter 2 Demand Forecasting EV233072006

Question 15: National Scan, Inc., sells radio frequency inventory tags. Monthly sales for a seven-month
period were as follows:

a. Plot the monthly data on a sheet of graph paper.

b. Forecast September sales volume using each of the following:
(1) A linear trend equation.
(2) A five-month moving average.
(3) Exponential smoothing with a smoothing constant equal to .20, assuming a March forecast of
19(000).
(4) The naive approach.
(5) A weighted average using .60 for August, .30 for July, and .10 for June.
c. Which method seems least appropriate? Why? (Hint: Refer to your plot from part a.)
d. What does use of the term sales rather than demand presume?

a. Plot the monthly data on a sheet of graph paper:

b. Forecast September sales volume using the following methods:

(1) The naive approach:
The naive approach would involve using the sales figure for August (20,000 units) as the forecast for
September.
(2) A five-month moving average:
Calculate the average of the sales for the last five months (June to August), which is
18+22+20+18+205=19.6 (rounded to the nearest unit). Use this as the forecast for September.

11 | Page 625 Operations & Supply Chain Management Istiaque Ahmed Chowdhury
23rd Batch EV Chapter 2 Demand Forecasting EV233072006

(3) A weighted average using .60 for August, .30 for July, and .10 for June:
Calculate the weighted average as follows:
(0.60 × August sales) + (0.30 × July sales) + (0.10 × June sales)
=(0.60×20,000)+(0.30×22,000)+(0.10×18,000)
= 12,000 + 6,600 + 1,800
= 20,400 units

(4) Exponential smoothing with a smoothing constant equal to .20:

You can use the exponential smoothing formula:

Forecast for September = α × (Sales for August) + (1 - α) ×(Forecast for August)

=0.20×20,000+0.80×20,000

= 4,000 + 16,000

= 20,000 units

(5) A linear trend equation:

To use a linear trend equation, you would need to perform linear regression analysis on the historical
sales data to determine the equation that best fits the trend. The equation would be of the form:

Sales = a + b × Month

c. Which method seems least appropriate? Why? (Hint: Refer to your plot from part a.)

The least appropriate method would likely be the naive approach, where you simply use the sales figure
for the previous month (August) as the forecast for September. This method doesn't take into account
any trends or patterns in the data and assumes that the future will be exactly the same as the most
recent past. Other methods, like moving averages, weighted averages, and exponential smoothing,
provide more sophisticated forecasts that consider historical data over a longer period, making them
more suitable for capturing trends and seasonality in the sales data.

12 | Page 625 Operations & Supply Chain Management Istiaque Ahmed Chowdhury
23rd Batch EV Chapter 2 Demand Forecasting EV233072006

Question 16: A dry cleaner uses exponential smoothing to forecast equipment usage at its main plant.
August usage was forecasted to be 88 percent of capacity; actual usage was 89.6 percent of capacity. A
smoothing constant of 0.1 is used.
a. Prepare a forecast for September.
b. Assuming actual September usage of 92 percent, prepare a forecast for October usage.

Exponential Smoothing:
It is a forecasting strategy that progressively reduces the weight of older data points while highlighting
newer ones, allowing for trend exploration and prediction in time series data.
Explanation:
Formula:
𝐹𝑡+1 = 𝛼 × 𝐴𝑡 + (1 − 𝛼) × 𝐹𝑡
Where:
𝐴𝑡 = Previous Period Actual
𝐹𝑡 = Previous Period Forecast
𝛼 = Alpha or Smoothing Constant

What is given:
August Forecast (Faug) = 88 percent
August Actual (Aaug) = 89.6 percent
Smoothing Constant (𝛼) = 0.2
Also:
September Actual (Asep) = 92 percent
The objective is to compute forecasts for both September and October.
Part a: September Forecast
Utilizing the given values, we get:
𝐹𝑡+1 = 𝛼 × 𝐴𝑡 + (1 − 𝛼) × 𝐹𝑡
𝑆𝑒𝑝𝑡𝑒𝑚𝑏𝑒𝑟 𝐹𝑜𝑟𝑒𝑐𝑎𝑠𝑡, 𝐹𝐴𝑢𝑔𝑢𝑠𝑡 = (𝛼 ∗ 𝐴𝐴𝑢𝑔𝑢𝑠𝑡 + (1 − 𝛼) × 𝐹𝐴𝑢𝑔𝑢𝑠𝑡 )
𝑆𝑒𝑝𝑡𝑒𝑚𝑏𝑒𝑟 𝐹𝑜𝑟𝑒𝑐𝑎𝑠𝑡, 𝐹𝐴𝑢𝑔𝑢𝑠𝑡 = (0.2 × 89.6 + (1 − 0.2) × 88)
𝑆𝑒𝑝𝑡𝑒𝑚𝑏𝑒𝑟 𝐹𝑜𝑟𝑒𝑐𝑎𝑠𝑡, 𝐹𝐴𝑢𝑔𝑢𝑠𝑡 = 88.32
Hence:
September Forecast = 88.32 percent
Part b: October Forecast:
Given that: We know that:
September Actual (𝐴𝑆𝑒𝑝𝑡𝑒𝑚𝑏𝑒𝑟 ) = 92 percent September Forecast (𝐹𝑆𝑒𝑝𝑡𝑒𝑚𝑏𝑒𝑟 ) = 88.32 percent
𝐹𝑡+1 = 𝛼 × 𝐴𝑡 + (1 − 𝛼) × 𝐹𝑡
𝑂𝑐𝑡𝑜𝑏𝑒𝑟 𝐹𝑜𝑟𝑒𝑐𝑎𝑠𝑡, 𝐹𝑆𝑒𝑝𝑡𝑒𝑚𝑏𝑒𝑟 = (𝛼 × 𝐴𝑠𝑒𝑝 + (1 − 𝛼) × 𝐹𝑠𝑒𝑝)
𝑂𝑐𝑡𝑜𝑏𝑒𝑟 𝐹𝑜𝑟𝑒𝑐𝑎𝑠𝑡, 𝐹𝑆𝑒𝑝𝑡𝑒𝑚𝑏𝑒𝑟 = (0.2 × 92 + (1 − 0.2) × 88.32)
𝑂𝑐𝑡𝑜𝑏𝑒𝑟 𝐹𝑜𝑟𝑒𝑐𝑎𝑠𝑡, 𝐹𝑆𝑒𝑝𝑡𝑒𝑚𝑏𝑒𝑟 = 89.06
Hence:
October Forecast = 89.06 percent
Snippets: These projected insights provide a solid platform for informed decision-making and strategic
planning for the dry cleaner, allowing for more effective usage in the following months.

13 | Page 625 Operations & Supply Chain Management Istiaque Ahmed Chowdhury
23rd Batch EV Chapter 2 Demand Forecasting EV233072006

Question 17: An electrical contractor’s records during the last five weeks indicate the number of job
requests:
Week Request
1 26
2 26
3 20
4 25
5 28
Predict the number of requests for week 6 using each of these methods:
a. Naive.
b. A four-period moving average.
c. Exponential smoothing with .30. Use 20 for week 2 forecast.

Let us find the naive forecast for the given information:

Naive Forecast for Week 6 = 28
Explanation:
The Naive forecast for week 6 is the previous week's request (Week 5 Request)
b. A four-period moving average.
Let us find the four-period moving average for the available information:
28+25+20+26
4 period moving average= = 24.75
4

Explanation:
The formula is as follows:
𝑃1 + 𝑃2 + 𝑃3 + ⋯ + 𝑃𝑛
Simple Moving Average, 𝑆𝑀𝐴 =
𝑛
Where:
P1,P2,P3,…,Pn are the prices of an asset at different time periods (e.g., closing prices).
n is the number of periods over which the average is calculated.
c. Exponential smoothing with 0.15. Use 25 for week 2 forecast.
Let us find the forecast values with the help of exponential smoothing method:
Week Request Forecast
1 26 Explanation:
2 26 25 The formula for calculating the exponential smoothing forecast
3 20 25.15 (Ft) is as follows:
4 25 24.38 𝐹𝑡+1 = 𝛼 × 𝐴𝑡 + (1 − 𝛼) × 𝐹𝑡
5 28 24.47 Where:
6 25.00 𝐴𝑡 = Previous Period Actual
𝐹𝑡 = Previous Period Forecast
𝛼 = Alpha or Smoothing Constant

14 | Page 625 Operations & Supply Chain Management Istiaque Ahmed Chowdhury
23rd Batch EV Chapter 2 Demand Forecasting EV233072006

Question 18: A cosmetics manufacturer’s marketing department has developed a linear trend equation
that can be
used to predict annual sales of its popular Hand & Foot Cream.
𝐹𝑡 = 80 + 15𝑡
were
𝐹𝑡 = 𝐴𝑛𝑛𝑢𝑎𝑙 𝑠𝑎𝑙𝑒𝑠 (000 𝑏𝑜𝑡𝑡𝑙𝑒𝑠)
𝑡 = 0 𝑐𝑜𝑟𝑟𝑒𝑠𝑝𝑜𝑛𝑑𝑠 𝑡𝑜 1990
a. Are annual sales increasing or decreasing? By how much?
b. Predict annual sales for the year 2006 using the equation.

Given:
𝐹𝑡 = 80 + 15𝑡
t = 0 correspondents to 1990

Are annual sales increasing or decreasing and by how much:

For year 1990, t = 0

Therefore, annual sales in year 1990 will be:
F(0)=80+15(0)=80
= 80,000

For year 1991, t = 1:

Therefore, annual sales for year 1991 will be:
F(1)=80+15(1)=95
= 95000

Annual increase in sales:

Annual increase=Sales in 1991 − Sales in 1990
Annual increase =95,000−80,000=15,000
Annual increase = 15000

b. Predict annual sales for the year 2006 using the equation.
Annual sales in year 2006:

Value of t in year 2006 will be

t=2006−1990=16

Formula and Calculation:

F(16)=80 + 15t=80+15(16)=320
= 320000 bottles

15 | Page 625 Operations & Supply Chain Management Istiaque Ahmed Chowdhury
23rd Batch EV Chapter 2 Demand Forecasting EV233072006

Question 19: Freight car loadings over a 12-year period at a busy port are as follows:

a. Determine a linear trend line for expected freight car loadings.

b. Use the trend equation to predict expected loadings for weeks 20 and 21.
c. The manager intends to install new equipment when the volume exceeds 800 loadings per week.
Assuming the current trend continues, the loading volume will reach that level in approximately
what week?

a. Determine a linear trend line for expected freight car loadings.

Linear trend line is determined using least square method as below:

b. Use the trend equation to predict expected loadings for

weeks 20 and 21.
𝐹𝑜𝑟 𝑤𝑒𝑒𝑘 20, 𝑃𝑟𝑒𝑑𝑖𝑐𝑡𝑒𝑑 𝑒𝑥𝑝𝑒𝑐𝑡𝑒𝑑 𝑙𝑜𝑎𝑑𝑖𝑛𝑔𝑠
= 208.48 + 18.996 × 20 = 588
𝐹𝑜𝑟 𝑤𝑒𝑒𝑘 21, 𝑃𝑟𝑒𝑑𝑖𝑐𝑡𝑒𝑑 𝑒𝑥𝑝𝑒𝑐𝑡𝑒𝑑 𝑙𝑜𝑎𝑑𝑖𝑛𝑔𝑠
= 208.48 + 18.996 × 21 = 607

c. The manager intends to install new equipment when

the volume exceeds 800 loadings per week. Assuming
the current trend continues, the loading volume will
reach that level in approximately what week?

For given expected loadings (y) of 800,

800 − 208.48
𝑊𝑒𝑒𝑘, 𝑥 =
18.996
𝑊𝑒𝑒𝑘, 𝑥 = 31
The loading volume will reach 800 in approximately
week 31

16 | Page 625 Operations & Supply Chain Management Istiaque Ahmed Chowdhury
23rd Batch EV Chapter 2 Demand Forecasting EV233072006

Question 20: After plotting demand for four periods, an emergency room manager has concluded that
a trend adjusted exponential smoothing model is appropriate to predict future demand. The initial
estimate of
trend is based on the net change of 30 for the three periods from 1 to 4, for an average of +10 units.
𝑈𝑠𝑒 𝛼 = .5 𝑎𝑛𝑑 𝛽 = .4, and TAF of 250 for period 5. Obtain forecasts for periods 6 through 10.

Question 21: The demand for last six weeks of Pizzas sales are as follows
Week 1 50 Week 4 56
Week 2 65 Week 5 55
Week 3 52 Week 6 60
Forecast demand for pizza for week 7, and week 8 using simple moving average and weighted moving
average taking n=3. In case of weighted moving average, use .50, .30, .20 as weight whereas the recent
period should have higher weight. Which method gives better result?

Question 22: For forecasting demand company X uses trend and season corrected exponential
smoothing. Corresponding smoothing factors are α = 0.1, β=0.2, and γ = 0.05. For Q 4 of Year 2013
(which is 12th period), actual demand (A12) was 5000, Level (L12) was 5050 and Trend (T12)
was 50. And seasonal indices are, for Q1 =.45, for Q2 = 0.90, for Q3 = 1.40, and for Q4 = 1.10.
Calculate demand forecast for period Q1 and Q2 of 2014.

Question 23: Calculate MAD, MAPE, and MSE from the following information.

Question 24: Sales of Pizza at Pizza Hut for last 6 weeks were given below. Calculate the forecasted
demand for 7th week by using simple moving average method with n=3. Then repeat the forecast by
using the weighted moving average method with n=3 and weight of 0.50, 0.30, and 0.20, where 0.5
applies to the most recent demand. Calculate the MAD for each method. Which method seems better for
predicting Pizza demand?
Week 1 2 3 4 5 6
Pizza 50 65 52 56 55 60

17 | Page 625 Operations & Supply Chain Management Istiaque Ahmed Chowdhury
23rd Batch EV Chapter 2 Demand Forecasting EV233072006

Question 25: Weekly demand is as follows:

Estimate demand for next 4 weeks by moving average and also by simple exponential smoothing. Use
average for starting forecast for smoothing and alpha=0.1.
Evaluate MAD, & MAPE. Which method do you prefer and why?

Question 26: When should a company use qualitative forecasting? Sales of a company are given below.
Forecast for January was 900000 and Trend was -50000. Generate forecasts for February, March, and
April. Use α=0.1, β=0.
Month Sales
January 890,000
February 800,000
March 825,000
Weekly demand is as follows:
Week Demand Week Demand
1 108 5 96
2 116 6 119
3 118 7 96
4 124 8 102
Estimate demand for next 4 weeks by 4 weeks moving average and also by simple exponential
smoothing. Use all week’s average for starting forecast for smoothing and alpha=0.1.
Evaluate MAD. Which method do you prefer and why?

Question 27: From following data forecast the demand for next four periods using static method.
Assume that demand possess both trend and seasonal components.
Season: Q1,Y1 Q2,Y1 Q3,Y1 Q4,Y1 Q1,Y2 Q2,Y2 Q3,Y2 Q4,Y2
Demand: 8000 13000 23000 34000 10000 18000 23000 36000

Question 28: The actual and forecast data of a product by a given forecasting technique is given below.
Comment the rigorousness of the technique using Tracking Signal information.
Period 1 2 3 4 5 6 7 8 9
Actual 1600 2500 3500 3300 3200 3900 4700 4300 4400
Forecast 1933 1933 2033 2533 3100 3333 3467 3933 4300

Question 29: Given that 2008 demand was 2200 unit where as forecast was 1600 units. If the
smoothing constant, α = 0.3, calculate the forecasted demand of year 2009. Use exponential smoothing
forecasting techniques

18 | Page 625 Operations & Supply Chain Management Istiaque Ahmed Chowdhury
23rd Batch EV Chapter 2 Demand Forecasting EV233072006

Year 𝑨𝒄𝒕𝒖𝒂𝒍 𝑭𝒐𝒓𝒆𝒄𝒂𝒔𝒕 Error |𝐄𝐫𝐫𝐨𝐫| |𝐄𝐫𝐫𝐨𝐫|𝟐 %Error

𝑫𝒆𝒎𝒂𝒏𝒅, 𝑨𝒕 𝑫𝒆𝒎𝒂𝒏𝒅, 𝑭𝒕
1 310 --- --- --- --- ---
2 365 --- --- --- --- ---
3 395 --- --- --- --- ---
4 415 310 𝟑𝟏𝟎 + 𝟑𝟔𝟓 + 𝟑𝟗𝟓 58 |𝟓𝟖| 3364 𝟓𝟖
= 𝟑𝟏𝟎 × 𝟏𝟎𝟎
𝟑 𝟒𝟏𝟓
= 𝟏𝟑. 𝟗𝟕%
5 450 392 𝟒𝟏𝟓 + 𝟑𝟗𝟓 + 𝟑𝟔𝟓 58 |𝟓𝟖| 3364 𝟓𝟖
= 𝟑𝟗𝟐 × 𝟏𝟎𝟎
𝟑 𝟒𝟓𝟎
= 𝟏𝟐. 𝟖𝟖%
6 465 420 𝟒𝟓𝟎 + 𝟒𝟏𝟓 + 𝟑𝟗𝟓 45 |𝟒𝟓| 2025 𝟒𝟓
= 𝟒𝟐𝟎 × 𝟏𝟎𝟎
𝟑 𝟒𝟐𝟎
= 𝟏𝟎. 𝟕𝟏%
7 443 𝟒𝟔𝟓 + 𝟒𝟓𝟎 + 𝟒𝟏𝟓
= 𝟒𝟒𝟑
𝟑

19 | Page 625 Operations & Supply Chain Management Istiaque Ahmed Chowdhury