MATERIALS DEMAND FORECASTING

11/30/2021 Course Instructor: Gezu G. (MBA) 1

 Introduction
• The success of an organization depends on how well the
organization sees the future environment which is full of risks
and uncertainties.
• In order to make prediction about the future, we must use
the past and present data.
• These data helps in minimizing risk and/or uncertainties
about the future.
• Forecasting is one of the techniques which help to see the
future.
• It is also a basic tool to help managerial decisions making.
11/30/2021 Course Instructor: Gezu G. (MBA) 2
 Forecasting
• Forecasting is the art and science of predicting future events.

• Forecasts and planning usually vary.

• Forecasting deals with what we think will happen in the future

while planning deals with what we think should happen in the

future.

• Thus, through planning, we concisely attempt to alter future events,

whereas we use forecasting only to predict them.

• Good planning utilizes a forecast as input and quality of a decision

depends in large part on the quality of the forecast.

11/30/2021 Course Instructor: Gezu G. (MBA) 3
 Con….
• However, forecasting may suffer from errors, which can
be accommodated in three ways:

• by reducing the error through better forecasting

• by introducing more flexibility into operations

• by reducing the lead-time over which forecasts are

required.

• Forecasting is one of the inputs to all types of business

planning and control

11/30/2021 Course Instructor: Gezu G. (MBA) 4

1. Qualitative forecasting

 Are subjective, judgmental and based on estimates and opinions.

 They do not use specific quantitative or statistical models.

 They are useful when there is lack of data or when past data are not
reliable predictors of the future.

 They are used for:

• medium and long-range forecasts.

• for new product introductions where historical database is not

available.

 These techniques include the following.

11/30/2021 Course Instructor: Gezu G. (MBA) 5
• Grass Roots/Sales force composite: combining inputs from each

salesperson which is closest to his/her own territory may derive an

overall sales forecast.

• Market Research

• Panel Consensus

• Consumer Panel Survey

• Historical Analogy - ties the forecast of one item to the forecast of

a similar item. It is important in planning new products where a

forecast may be derived by using the history of a similar product.

11/30/2021 Course Instructor: Gezu G. (MBA) 6

• Delphi Method Through:

• Experts of variety of knowledge are chosen to participate.

• All participants provide a written response to the questions asked

through a questionnaire (or E-mail)

• Results are summarized along with statistics

• Results are summarized again, refining forecasts and conditions,

and new questions are developed again.

• The procedure is repeated for a reasonable number of rounds (a

minimum of three) until sufficient convergence is achieved.

• The estimates from the last round are then used as the forecasts.
11/30/2021 Course Instructor: Gezu G. (MBA) 7
2. Quantitative forecasting

• quantitative methods utilize an underlying mathematical and

statistical model to predict and estimate the future

requirement or demand based on past data.

• The basic assumption for the quantitative forecasting methods

is that past data because data patterns are reliable predication

of the future.

• This model includes time series model and causal models.

11/30/2021 Course Instructor: Gezu G. (MBA) 8

• The time series models

– attempt to predict the future values using the historical data.

– the demand forecast is done on the basis of the past demand value.

– based on the premise that the future is a function of what has

happen in the past.

• Causal models

– are used when one variable is related to and therefore, depend on

the values of some other variable(s).

– For example, the demand of sugar may depend on the consumption

of tea.

11/30/2021 Course Instructor: Gezu G. (MBA) 9

• There can be several time-series forecasting models, however,
which forecasting model, a firm should choose depend on:

• Time horizon to forecast

• Data availability

• Accuracy required

• Size of forecasting budget

• Availability of qualified personnel

• The firm's degree of flexibility

11/30/2021 Course Instructor: Gezu G. (MBA) 10
1. Last Period Demand (LPD)

• Last Period Demand method simply forecasts for the next

period the actual demand that occurred in the previous
period.

• The equation for last period demand is:

• Ft = At –1

Where

Ft = Forecasted demand for period t

At – 1 = Actual demand in the previous period

11/30/2021 Course Instructor: Gezu G. (MBA) 11
• The forecast for the 5th period is the actual demand of the 4th
period; that is, 70 units. In this technique no calculation is needed.

11/30/2021 Course Instructor: Gezu G. (MBA) 12

2. Arithmetic Mean (Average)

• Arithmetic mean method calculates the average of all past actual

demand of materials to arrive at a forecast.

• The equation for the arithmetic mean is:

Where
Ft = Forecasted demand for next period t

An = Actual demand for previous period n

n = number of time periods

11/30/2021 Course Instructor: Gezu G. (MBA) 13
• Example

11/30/2021 Course Instructor: Gezu G. (MBA) 14

3. Moving Average
• When demand for a product is neither growing nor declining rapidly,
and if it does not have seasonal characteristics, moving averages can be
useful in removing the random fluctuations for forecasting.
• more convenient to use past data to predict the future.
• calculate the next period's forecast by averaging the actual demand,
depending on the predetermined time period, the oldest demands
become out of calculation.
• For example, if we want to forecast for June with a five month moving
average, we can take the average of January, February, March, April and
May.

11/30/2021 Course Instructor: Gezu G. (MBA) 15

• The formula for the simple moving average is:

Where:

Ft = Forecast for the coming period t

n = Number of periods to be averaged

At -1 = Actual demand in the past period

At - 2, At - 3 & At - n = Actual demand two periods

ago, three periods ago and so on up to n periods

11/30/2021
ago. Course Instructor: Gezu G. (MBA) 16
• For Example:

– Forecast demand based on a three week simple moving

average.

11/30/2021 Course Instructor: Gezu G. (MBA) 17

• Example:

• The demand for A is observed for 10 months & it is given below.

• What is the forecast for month 11 using a 3 month forecast & a 4

months Forecast?
11/30/2021 Course Instructor: Gezu G. (MBA) 18
Con….
• The disadvantage in calculating a moving average
is that all individual elements must be carried as
data because a new forecast period involves
adding new data and dropping the earliest data.
• For a three or six period moving average, this is
not too severe.
• But plotting 60 day moving average for the use of
each of 20,000 items in inventory would involve a
significant amount of data.
11/30/2021 Course Instructor: Gezu G. (MBA) 19
4. Weighted moving average

• More recent data are more indicative of the future than are older data.

• Weighted moving average is computed to give more weights to more

recent data.

• A weighted moving average is computed by multiplying each period by a

weighting factor.

• For example, a department store may find that in a four-month period, the

best forecast is derived by using 40% of the actual sales for the most recent

month, 30 percent of two months ago, 20 percent of three months ago and

10 percent of four months ago.

11/30/2021 Course Instructor: Gezu G. (MBA) 20

• For Example:
• If actual sales experience was:

• The forecast for Month 5 would be

11/30/2021 Course Instructor: Gezu G. (MBA) 21

• Where:

– W1 = weight to be given to the actual demand for the period t-1

– W2 = weight to be given to the actual demand for the period t-2

– Wn = weight to be given to actual demand of the period t-n

• Thus,
– F5 = 0.40(95) + 0.30(105) + 0.20 (90) + 0.10(100)

= 38 + 31.5 + 18 + 10

= 97.5

• The sum of all the weights must be equal 1 (one)

• Suppose sales for month 5 actually turned out to be 110. Calculate Forecast for
month 6

11/30/2021 Course Instructor: Gezu G. (MBA) 22

• Assume that the weight of the four months forecast given below is 4:3:2:1 then,

Suppose sales for month 5 actually turned out to be 110. Then the forecast for
month 6 would be:

11/30/2021 Course Instructor: Gezu G. (MBA) 23

5. Exponential smoothing

• Unlike the previous methods of forecasting (simple and weighted

moving average), in the exponential smoothing a new average can be
computed from an old average and the most recent observed demand.

• In many applications the most recent actual demand are more

indicative of the future than those in the more distant past.

• In the exponential smoothing method, only three pieces of data are

needed to forecast the future:

• the most recent forecast, the actual demand that occurred for
that forecast period and a smoothing constant alpha ().

11/30/2021 Course Instructor: Gezu G. (MBA) 24

• This smoothing constant determines the level of smoothing and the
speed of reaction to difference between forecasts and actual demands.
• The value for the constant is determined both by the nature of the
product and by the manager’s sense of what constitutes a good
response rate.
• For example, if a firm produced a standard item with relatively stable
demand, the reaction to difference between actual and forecast demand
would tend to be small.
• But, if the firm were experiencing growth, it would be desirable to have
a higher reaction rate.

11/30/2021 Course Instructor: Gezu G. (MBA) 25

• The equitation for a simple exponential smoothing forecast is:

• Ft = Ft - 1 +  (At - 1 - Ft - 1)

Where:
Ft = the exponentially smoothed forecast for period t

Ft - 1 = the exponentially smoothed forecast made for the prior

period

At -1 = the actual demand in the prior period

 = the desired response rate, or smoothing constant (alpha)

• This equation states that the new forecast is equal to the old forecast
plus a portion of the error (the difference between the previous
forecast and actual demand).
11/30/2021 Course Instructor: Gezu G. (MBA) 26
• To demonstrate the method, assume that the long-run demand for the product

under study is relatively stable and a smoothing constant () of 0.05 is

considered appropriate. If the exponential method were used as a continuing

policy, a forecast would have been made for the last month.

• Assume that the last month’s forecast (Ft –1) was 1050 units. If 1,000 actually

were demanded rather than 1050, the forecast for this month would be:

Ft = Ft –1 +  (At - 1–Ft -1)

= 1050 + 0.050 (1000 -1050)

= 1050 + 0.05(-50)

= 1047.5 units

11/30/2021 Course Instructor: Gezu G. (MBA) 27

• Causal forecasting methods develop a cause and effect model
between demand and other variables.

– For example, the demand for ice cream may be related to

population, the average summer temperature, and time.

• Data can be collected on these variables and an analysis

conducted to determine the validity of the proposed model.

• Regression techniques are means of describing association

between two or more such variables.

11/30/2021 Course Instructor: Gezu G. (MBA) 28

• Simple regression uses only one independent variable. If the
data are a time series, the independent variable is the time
period, and the dependent variable is usually sales or demand
for materials.

• The equation (formula) for the simple linear regression is:

or

11/30/2021 Course Instructor: Gezu G. (MBA) 29

• Where:
–x = independent variable values
– y = dependent variable values
–a = y intercept
– b = slope of the regression line
– ∑y – Summation of the value of the dependent variable
– ∑x – Summation of the value of the independent variable
– n = Number of observations
– X = values of x that lie on the regression line
– Y = Value of the dependent y variable computed with the
regression
11/30/2021 Course Instructor: Gezu G. (MBA) 30
• Example:

• A manufacturer is developing a facility plan to provide

production capacity for its factory.

• The amount of capacity required in the future depends on

the number of products demanded by its customers.

• Using the simple linear regression, the manufacturer can

forecast annual demand for the products for each of the next
3 years.

• The data below shows past actual sales of its products.

11/30/2021 Course Instructor: Gezu G. (MBA) 31
• Now we construct the following table to determine the values of a and
b in the simple linear regression equitation Y = a + bX
11/30/2021 Course Instructor: Gezu G. (MBA) 32
11/30/2021 Course Instructor: Gezu G. (MBA) 33
• Solution for a and b values

11/30/2021 Course Instructor: Gezu G. (MBA) 34

• Once the values of a and b are known, the regression
equation is

Y = a + bX = 913.33 + 215.758X

• Now to forecast the demand for the next 3 years we

substitute 11, 12 and 13, the next three values for x in to the
regression equation for x:

Y11 = 913.333 + 215.758(11) = 3,286.7 units

Y12 = 913.333 + 215.758(12) = 3,502.4 units

11/30/2021
Y13 = 913.333 Course
+ 215.758(13) = 3,718.2 units
Instructor: Gezu G. (MBA) 35
 Example
• Consider a large firm organization engaged in
producing barely.
• The organization feels that the demand for its
product (barely) is dependent or related to the
number of cans of beer of 1 liter consumed every
year in a certain locality.
• To establish the demand forecast for its product,
the organization has collected the following
historical data of hectares of land that had been
11/30/2021 Course Instructor: Gezu G. (MBA) 36
Required;

• If the numbers of liters of beer to be consumed in the coming period is 48000

litters (orders already received from clients). Forecast the number of quintals
of barely that could be demanded
11/30/2021 in the
Course Instructor: year
Gezu 2000.
G. (MBA) 37
• 11/30/2021
The demand for barely is in Course
the Instructor:
year 2000 = 1.05 (48000) + 9.08
Gezu G. (MBA) 38
 THANK YOU!!

11/30/2021 Course Instructor: Gezu G. (MBA) 39