Supply chain and Logistic Management

Demand Forecasting in a Supply Chain

0| Supply chain and logistic management
© Dr. Saeed
Demand Forecasting in a Supply Chain
Defining Forecasting

Forecasting is a business function that attempts to predict sales and use of

products so they can be purchased or manufactured in appropriate
quantities in advance.

Forecast vs Prediction

A forecast is an objective estimate of future demand attained by projecting

the pattern of the events of the past into the future.

A prediction, on the other hand, is a subjective estimate of what events

will be happening in the future.

1| Supply chain and logistic management

© Dr. Saeed Ross (2015): Distribution Planning and Control
Demand Forecasting in a Supply Chain
Forecasting Levels

A forecast is usually classified by the future time horizon that it covers:

§ Short-range forecast:

- up to 1 year but is generally less than 3 months

- purchasing, job scheduling, workforce levels, job assignments, and

production levels

§ Medium-range forecast:

- 3 months to 3 years
- sales and production planning, budgeting

§ Long-range forecast:
- 3 years or more
- new product planning, facility location, research & development
2| Supply chain and logistic management
© Dr. Saeed Heizer, J., Render, B. (2017): Operations Management
Demand Forecasting in a Supply Chain
The Forecasting Process

§ Determine the use of the forecast

§ Select the items to be forecasted

§ Determine the time horizon of the forecast

§ Select the forecasting model

§ Gather the data needed to make the forecast

§ Make the forecast

§ Validate and implement the results

3| Supply chain and logistic management

© Dr. Saeed Heizer, J., Render, B. (2017): Operations Management
Demand Forecasting in a Supply Chain
Forecasting Techniques

Qualitative Methods
§ Used when situation is vague and little data exist
- New products
- New technology
§ Involves intuition, experience
- E.g., forecasting sales on internet
Quantitative Methods

§ Used when situation is stable and historical data exist

- Existing products
- Current technology
§ Involves mathematical techniques
- E.g., forecasting sales of colour television
4| Supply chain and logistic management
© Dr. Saeed Heizer, J., Render, B. (2017): Operations Management
Demand Forecasting in a Supply Chain
Overview of Qualitative Methods

Jury of executive opinion

§ Involves small group of high-level experts and managers

§ Group estimates demand by working together

§ Combines managerial experience with statistical models

§ Relatively quick

Sales force composite

§ Each salesperson projects his or her sales

§ Combined at district and national levels

§ Sales representative know customers’ wants

5| Supply chain and logistic management

© Dr. Saeed Heizer, J., Render, B. (2017): Operations Management
Demand Forecasting in a Supply Chain
Overview of Qualitative Methods

Delphi method

§ Iterative group process, continues until consensus is reached

§ 3 types of participants

- Decision makers: decision makers evaluate responses and make

decisions

- Staff: administering survey

- Respondents: people who can make valuable judgements
Consumer market survey

§ Ask customers about purchasing plans

§ What customers say and what they actually do are often different

§ Sometime difficult to answer

6| Supply chain and logistic management
© Dr. Saeed Heizer, J., Render, B. (2017): Operations Management
Demand Forecasting in a Supply Chain
Overview of Quantitative Methods

1. Naive Approach

2. Moving Averages
Time-series Models
3. Exponential smoothing

4. Trend projection

5. Linear regression Associated Models

Time-Series Models: A forecasting technique that uses a series of past

data points to make a forecast

Associated Models: Incorporate the variables or factors that might

influence the quantity being forecast.

7| Supply chain and logistic management

© Dr. Saeed Heizer, J., Render, B. (2017): Operations Management
Demand Forecasting in a Supply Chain
Time-Series Forecasting

§ Set of evenly spaced numerical data

- Obtained by observing response variable at regular time periods

§ Forecast based only on past values, no other variables important

- Assumes that factors influencing past and present will continue to

influence in future

8| Supply chain and logistic management

© Dr. Saeed Heizer, J., Render, B. (2017): Operations Management
Demand Forecasting in a Supply Chain
Time-Series Components

9| Supply chain and logistic management

© Dr. Saeed Heizer, J., Render, B. (2017): Operations Management
Demand Forecasting in a Supply Chain
Demand Charted over 4 Years

10 | Supply chain and logistic management

© Dr. Saeed Heizer, J., Render, B. (2017): Operations Management
Demand Forecasting in a Supply Chain
Naive Approach

§ Assume that demand in the next period will be equal to demand in the
most recent period

- if sales of a product - say, Samsung cell phones - were 68 units in

January, we can forecast that February’s sales will also be 68 phones

§ For some products, it is cost effective and efficient

§ Can be good starting point to compare with more sophisticated models

13 | Supply chain and logistic management

© Dr. Saeed Heizer, J., Render, B. (2017): Operations Management
Demand Forecasting in a Supply Chain
Moving Average

§ A forecasting method that uses an average of the n most recent periods

of data to forecast the next period

§ Moving averages are useful if we can assume that market demands will
stay fairly steady over time

§ Used if little or no trend

14 | Supply chain and logistic management

© Dr. Saeed Heizer, J., Render, B. (2017): Operations Management
Demand Forecasting in a Supply Chain
Weighted Moving Average

§ Used when trend is present

§ Weights can be used to place more emphasis on recent months

§ Choice of weights is somewhat arbitrary and based on experience

15 | Supply chain and logistic management

© Dr. Saeed Heizer, J., Render, B. (2017): Operations Management
Demand Forecasting in a Supply Chain
Weighted Moving Average

16 | Supply chain and logistic management

© Dr. Saeed Heizer, J., Render, B. (2017): Operations Management
Demand Forecasting in a Supply Chain
Weighted Moving Average

17 | Supply chain and logistic management

© Dr. Saeed Heizer, J., Render, B. (2017): Operations Management
Demand Forecasting in a Supply Chain
Problems with Moving Average Method

§ Increasing the size of n (the number of periods averaged) does smooth

out fluctuations better, but it makes the method less sensitive to changes
in the data

§ Cannot pick up trends very well as it is based on the averages

§ Require extensive records of past data

18 | Supply chain and logistic management

© Dr. Saeed Heizer, J., Render, B. (2017): Operations Management
Demand Forecasting in a Supply Chain
Exponential Smoothing

A weighted-moving-average forecasting technique in which data points are

weighted by an exponential function
Smoothing constant
A weighting factor used in an exponential smoothing forecast, a number
ranges from 0 to 1

19 | Supply chain and logistic management

© Dr. Saeed Heizer, J., Render, B. (2017): Operations Management
Demand Forecasting in a Supply Chain
Example Exponential Smoothing

Predicted demand for February = 142 Ford Mustangs

Actual demand in February = 153
Smoothing constant = 0.2 UNTIL HERE
Forecast for March = ?

Forecast for March = 142+0.2*(153-142)

= 142+2.2
= 144 Cars

If the smoothing constant is changed to .30, what is the new forecast?

145.3
20 | Supply chain and logistic management
© Dr. Saeed Heizer, J., Render, B. (2017): Operations Management
Demand Forecasting in a Supply Chain
Choosing Smoothing Constant

§ Exponential smoothing has been successfully applied in virtually every

type of business
§ The appropriate value of the smoothing constant, a, can make the
difference between an accurate forecast and an inaccurate forecast
§ High values of a are chosen when the underlying average is likely to
change
§ Low values of a are used when the underlying average is fairly stable.

21 | Supply chain and logistic management

© Dr. Saeed Heizer, J., Render, B. (2017): Operations Management
Demand Forecasting in a Supply Chain
Choosing Smoothing Constant

§ Exponential smoothing has been successfully applied in virtually every

type of business
§ The appropriate value of the smoothing constant, a, can make the
In picking a value for the smoothing
constant,
difference theaccurate
between an objective is toand
forecast obtain the mostforecast
an inaccurate
accurate
§ High values of a are chosen whenforecast
the underlying average is likely to
change
§ Low values of a are used when the underlying average is fairly stable.
We generally do this by selecting the model
that gives us the lowest forecast error

Forecast error
= Actual demand - Forecast value

22 | Supply chain and logistic management

© Dr. Saeed Heizer, J., Render, B. (2017): Operations Management
Demand Forecasting in a Supply Chain
Forecast error
Mean Absolute Deviation (MAD)
A measure of the overall forecast error for a model

Mean Squared Error (MSE)

The average of the squared differences between the forecasted and
observed values

Mean Absolute Percent Error

The average of the absolute differences between the forecast and actual
values, expressed as a percent of actual values
23 | Supply chain and logistic management
© Dr. Saeed Heizer, J., Render, B. (2017): Operations Management
Demand Forecasting in a Supply Chain
Comparisons of Forecast error

24 | Supply chain and logistic management

© Dr. Saeed Heizer, J., Render, B. (2017): Operations Management
Demand Forecasting in a Supply Chain
Comparisons of Forecast error

25 | Supply chain and logistic management

© Dr. Saeed Heizer, J., Render, B. (2017): Operations Management
Demand Forecasting in a Supply Chain
Comparisons of Forecast error

A low MSE is better because

we want to minimize MSE.
26 | Supply chain and logistic management
© Dr. Saeed Heizer, J., Render, B. (2017): Operations Management
Demand Forecasting in a Supply Chain
Comparisons of Forecast error

A low MSE is better because

we want to minimize MSE.
27 | Supply chain and logistic management
© Dr. Saeed Heizer, J., Render, B. (2017): Operations Management
Demand Forecasting in a Supply Chain
Comparisons of Forecast error

A low MSE is better because

we want to minimize MSE.
28 | Supply chain and logistic management
© Dr. Saeed Heizer, J., Render, B. (2017): Operations Management
Demand Forecasting in a Supply Chain
Comparisons of Forecast error

A low MSE is better because

we want to minimize MSE.
29 | Supply chain and logistic management
© Dr. Saeed Heizer, J., Render, B. (2017): Operations Management
Demand Forecasting in a Supply Chain
Exponential Smoothing with Trend Adjustments

A severe lag in the second, third, fourth, and fifth months, even
when our initial estimate for month 1 is perfect.

When trend is present, exponential smoothing must be

modified

30 | Supply chain and logistic management

© Dr. Saeed Heizer, J., Render, B. (2017): Operations Management
Demand Forecasting in a Supply Chain
Exponential Smoothing with Trend Adjustments

31 | Supply chain and logistic management

© Dr. Saeed Heizer, J., Render, B. (2017): Operations Management
Demand Forecasting in a Supply Chain
Example Exponential Smoothing with Trend Adjustments

32 | Supply chain and logistic management

© Dr. Saeed Heizer, J., Render, B. (2017): Operations Management
Demand Forecasting in a Supply Chain
Example Exponential Smoothing with Trend Adjustments

33 | Supply chain and logistic management

© Dr. Saeed Heizer, J., Render, B. (2017): Operations Management
Demand Forecasting in a Supply Chain
Example Exponential Smoothing with Trend Adjustments

34 | Supply chain and logistic management

© Dr. Saeed Heizer, J., Render, B. (2017): Operations Management
Demand Forecasting in a Supply Chain
Example Exponential Smoothing with Trend Adjustments

35 | Supply chain and logistic management

© Dr. Saeed Heizer, J., Render, B. (2017): Operations Management
Demand Forecasting in a Supply Chain
Example Exponential Smoothing with Trend Adjustments

36 | Supply chain and logistic management

© Dr. Saeed Heizer, J., Render, B. (2017): Operations Management
Demand Forecasting in a Supply Chain
Example Exponential Smoothing with Trend Adjustments

37 | Supply chain and logistic management

© Dr. Saeed Heizer, J., Render, B. (2017): Operations Management
Demand Forecasting in a Supply Chain
Example Exponential Smoothing with Trend Adjustments

Simple exponential smoothing is often referred to as first-order smoothing,

and trend- adjusted smoothing is called second-order smoothing or
double smoothing.
38 | Supply chain and logistic management
© Dr. Saeed Heizer, J., Render, B. (2017): Operations Management
Demand Forecasting in a Supply Chain
Seasonal Variations in Data

Seasonal Variations
Regular upward or downward movements in a time series that tie to
recurring events
- The multiplicative seasonal model can adjust trend data for seasonal
variation in demand

47 | Supply chain and logistic management

© Dr. Saeed Heizer, J., Render, B. (2017): Operations Management
Demand Forecasting in a Supply Chain
Seasonal Variations in Data

Steps in the process

§ Find the average historical demand for each season
§ Compute the average demand over all seasons
§ Compute a seasonal index for each season
§ Estimate next year’s total demand
§ Divide this estimate of total demand by the number of seasons, then
multiply it by the seasonal index for that season

48 | Supply chain and logistic management

© Dr. Saeed Heizer, J., Render, B. (2017): Operations Management
Demand Forecasting in a Supply Chain
Example Seasonal Index

A Des Moines distributor of Sony laptop computers wants to

develop monthly indices for sales. Data from the past 3 years,
by month, are available

49 | Supply chain and logistic management

© Dr. Saeed Heizer, J., Render, B. (2017): Operations Management
Demand Forecasting in a Supply Chain
Example Seasonal Index
If we expect the annual demand for computers to be 1,200 units next year, we
would use these seasonal indices to forecast the monthly demand as follows:

50 | Supply chain and logistic management

© Dr. Saeed Heizer, J., Render, B. (2017): Operations Management
Demand Forecasting in a Supply Chain
Example Seasonal Index
If we expect the annual demand for computers to be 1,200 units next year, we
would use these seasonal indices to forecast the monthly demand as follows:

51 | Supply chain and logistic management

© Dr. Saeed Heizer, J., Render, B. (2017): Operations Management
Demand Forecasting in a Supply Chain
Example Seasonal Index
If we expect the annual demand for computers to be 1,200 units next year, we
would use these seasonal indices to forecast the monthly demand as follows:

91.7, 81.5, and 86.6, which can be rounded to 92, 82, and 87

If next year’s annual demand is 1,150 laptops (instead of 1,200), what will the
January, February, and March forecasts be?

52 | Supply chain and logistic management

© Dr. Saeed Heizer, J., Render, B. (2017): Operations Management
Demand Forecasting in a Supply Chain
Example Problem - 1

Sales of hair dryers at the Walgreens stores in Youngstown, Ohio, over the
past 4 months have been 100, 110, 120, and 130 units (with 130 being the
most recent sales).
§ Develop a moving-average forecast for next month, using these three
techniques:
1. 3-month moving average
2. 4-month moving average
3. Weighted 4-month moving average with the most recent month
weighted 4, the preceding month 3, then 2, and the oldest month
weighted 1
4. If next month’s sales turn out to be 140 units, forecast the following
month’s sales (months) using a 4-month moving average
55 | Supply chain and logistic management
© Dr. Saeed Heizer, J., Render, B. (2017): Operations Management
Demand Forecasting in a Supply Chain
Example Problem - Solution

56 | Supply chain and logistic management

© Dr. Saeed Heizer, J., Render, B. (2017): Operations Management
Demand Forecasting in a Supply Chain
Example Problem - 2

57 | Supply chain and logistic management

© Dr. Saeed Heizer, J., Render, B. (2017): Operations Management
Demand Forecasting in a Supply Chain
Example Problem - Solution

58 | Supply chain and logistic management

© Dr. Saeed Heizer, J., Render, B. (2017): Operations Management
 Dr. Amad Saeed

Riphah International University, Lahore

Riphah School of Business and Management

phone: +92 (0)42-

email: amad.saeed@riphah.edu.pk
web: www.lahore.riphah.edu.pk

59 | Supply chain and logistic management

© Dr. Saeed