MATERIALS MANAGEMENT

CHAPTER TWO

FORECASTING

4-1
Why forecasting is importance

4-2
 INTRODUCTION
• Future environment is unknown.

• What will happen in the future is a quest of manager.

• Data helps in minimizing risk and/or uncertainties about

the future.

• Forecasting is a benchmark for planning.

4-3
 What is forecasting?
• Is the Art(Experience, judgment, and technical expertise) and
Science (principles, models, procedural data collection,
framework) of predicting future events.
• It involves the combination of both mathematical data and
manager’s perception.
• Taking historical data and projecting them into the future with
some sort of mathematical models.

• Estimation of the occurrence, timing, and magnitude of

uncertain future events.
4-4
 Forecasting … Cont’d
 Forecasting is the Process of
??
predicting a future event such as:

 Sales or demand

 Production

 Inventory

 Personnel

 Facilities
4-5
 Principles of Forecasting
1. Forecasts are rarely perfect, actual results usually differ from
predicted values:

 Forecasts attempt to look into the unknown future and, except by sheer
luck, it will be wrong to some degree.

 Errors are inevitable and must be expected.

 Since forecasts are expected to be wrong, the real question is “By how
much?”
 So, every forecast should include an estimate of error might be
95%,99%, 90%, and in any expected amount. 4-6
 Principle of forecasting… Cont’d
2. Forecasts are more accurate for families or groups: forecasts
are more accurate for large groups of items than for individual
items in a group.

E.g. Forecasting class average is easier than forecasting single

individual score of the student.

4-7
 Principle of forecasting… Cont’d
3. Forecasts are more accurate for nearer time periods. The near
future holds less uncertainty than the far future.

“Tomorrow is expected to be pretty much like today”

4. Forecasting techniques generally assume that the same

underlying systems that existed in the past will continue to exist
in the future.

4-8
 Why Forecasting?
• Demand for products and services is usually uncertain and
forecasting is inevitable in developing plans to satisfy future
demand.
• Customers usually demand delivery in reasonable time, and
manufacturers must anticipate future demand to shorten the
delivery time.
• Firms that make-to-order cannot begin making a product
before a customer places an order, So they have to ready
materials and subassemblies available to shorten the delivery time.
4-9
 Cont’d
Generally Forecasting can be used for;

Strategic planning (long range planning)

Finance and accounting (budgets and cost controls)

Marketing (future sales, new products)

Production and operations

4 - 10
 Features of Good Forecasting
 The forecast should be timely; Usually, a certain amount of time is
needed to respond to the information contained in a forecast.

 The forecast should be accurate; and the degree of accuracy

should be stated. This will enable users to plan for possible errors
and will provide a basis for comparing alternative forecasts.

 The forecast should be reliable; it should work consistently.

4 - 11
 Cont’d
• The forecast should be expressed in meaningful units: Financial
planners need to know how many dollars will be needed, production
planners need to know how many units will be needed.

• The forecast should be in writing: written forecast will permit an

objective basis for evaluating the forecast once actual results are in.

• The forecasting technique should be simple to understand and use.

• The forecast should be cost-effective:

4 - 12
 Forecasting Time Horizons
 Short-range forecast: Up to 1 year, Purchasing, job
scheduling, workforce levels, job assignments, production
levels.

 Medium-range forecast: up to 3 years, Sales and production

planning, budgeting.

 Long-range forecast: 3+ years, New product planning,

facility location, research and development.
4 - 13
 Steps in Forecasting Process

1. Determine the purpose of forecast: what is to be forecasted, how it

will be used, when it will be needed, the level of detail, amounts of
resources and the level of accuracy.

2. Establish a time horizon: keeping in mind that accuracy decreases

as the time horizon increases.
3. Data preparation: Obtain, edit, and analyze appropriate data
4. Select a forecasting technique: quantitative and qualitative or
mixed.
4 - 15
 Steps in forecasting….Cont’d
5. Make the forecast: deploying techniques and make forecast.
6. Monitor the forecast: determine whether it is good or not.
If it is not good, reexamine the method, assumptions, and validity of data, and
modify as needed.
For example, if demand is much less than the forecast, an action such as a
price reduction or a promotion may be needed.
Conversely, if demand is much more than predicted, increased output may
be advantageous. That may require working overtime, outsourcing, or taking
other measures.

4 - 16
 Forecasting Techniques

• There are many forecasting methods, but they can

usually be classified into two categories:
1. Qualitative

2. Quantitative

4 - 17
 Qualitative Forecasting
• Is projections based on intuition, judgment and opinions.

• By their nature, it is subjective.

• Such techniques are used more to forecast general business trends
and the potential demand for large families of products.
• It may not be good technique for specific item.
• These methods are used primarily when there is no available data.

• Production and inventory forecasting is usually concerned with the

demand for particular end items, and qualitative techniques are
rarely applied. 4 - 18
 1. Delphi Method
• It is a process used to arrive at a group opinion or decision by
surveying a panel of experts.
• Experts respond to several rounds of questionnaires, and the
responses summarized and shared with the group after each round.
• The experts are usually not known to each other, and their interaction
takes place through a coordinator.

• Then experts adjust their answers each round, based on how they
interpret the group response.
• The ultimate result is meant to be a true consensus of what the group
thinks.
4 - 19
 Cont’d
Freedom of expression: anonymity of the experts allows to express
opinions without any social pressure.

Right to change opinions: The experts are free to change their opinions at
any time without the fear of criticism.

Regular feedback: The experts are informed about the other participants’
opinions in the study after each round and allowed for any improvement.

It is time-consuming and laborious for both facilitators and experts.

4 - 20
 2. Sales Force Composite
In this method sales force members will be asked to estimate the
likely sales in their respective areas.

Finally, the estimates are combined at the district or regional or

national level to obtain the overall forecast.

The sales force composite methods encompasses the aggregate

judgments of the entire sales force.

4 - 21
 Cont’d
• The intimate knowledge and experience of the sales force in their
respective territories can be used efficiently.

• Since the sales agents forecast the sales by themselves, put more
efforts to achieve them.

• The responsibility to forecast sales rests on the shoulders of the sales

agent and thus could be held accountable if anything goes wrong.

• Since the sales agents are not the experts in forecasting they may not
use proper forecasting techniques.
4 - 22
 3. Market research or Consumer Panel Survey
• It forecasts future demand through consumer surveys and questionnaires.

• Consumers are questioned about their purchase plan in a consumer panel.

• The aim of this method is to forecast product and service demand on the
basis of subjective judgment of consumer purchase.

• The basic assumption to this model is “the consumer in the panel are the
representatives of the ultimate/final purchasers”.
4 - 23
 Cont’d
• Helps to identify potential markets, select appropriate marketing
techniques and promotion measures.

• Assists companies in studying marketing problems and solutions.

• Reduces the gap between the producers and consumers.

• This may not be always accurate as a result of uncertain consumer

behavior.

• It demands qualified & experienced specialists, that require significant

time & money. 4 - 24
 Quantitative Forecasting
• A statistical techniques for making projection about the future through
numerical facts.

• It use mathematical models to represent relationship among relevant

variables based on historical data, or known relationship.

• Using the causal relationship among the variable forecasting can be

performed using linear regression.

• Also there are many formal and less formal statistical methods of
forecasting. 4 - 25
Time series: for quantitative forecasting most commonly we use
this time series data.

 It is a series of data points indexed in time order.

 Most commonly, a time series is a sequence taken at successive
equally spaced period of time.
 If historical data for demand are plotted against a time scale, they may
show us any shapes or consistent patterns.
 A time series data has four components:
 Trend, Seasonality, Cyclical and Random.
4 - 26
 Time series components
1. Trend: - Over a long period, time series may have an overall tendency
either to move upwards or downwards.
E.g. Population goes upward
Endangered species of animals goas downward

4 - 27
Time series components … cont’d
2. Seasonality :- The fluctuation occurs periodically, the movements
recurring within a definite period or season (weather, holiday seasons,
or particular events ).
A large increase in sales of umbrellas during the rainy season would be
an example of seasonality.

4 - 28
Time series components … cont’d
3. Cyclical movement: - The values of the data exhibit rises and
falls that are not of a fixed frequency often due to economic
conditions.
• For example, in peak cycle the sales of company may be
high because the level of economic performance may be high.

4 - 29
 Time series components … cont’d
4. Random Variation: - the variations are erratic and irregular and are
usually caused by some unpredictable reason. They follow no discernible
pattern, so its challenging to make prediction.

The larger the random component of a time series, the less accurate the
forecasts based on those data.

4 - 30
 Types of quantitative methods
i. Naive Method; - the forecast for any periods is equal the
previous periods actual value.
ii. Averaging Methods;
A simple moving average=

Weighted Moving Average= ∑ni* weights

iii. Casual or Regression method= y= a + bx

iv. Exponential smoothing = NF= (ά) (LAD) + (1-ά) (PF)

4 - 31
 Quantitative techniques …Cont’d
Months Demand
January 300
February 350
March 400
April 400
May 450
Jun 500
Forecast demand for July? ?

[Link]ïve Methods; - the forecast for any periods is equal to

the actual value of the previous period.
• Using naïve method the demand for July is 500.

4 - 32
B. Averaging Methods: These methods utilize historical data for
calculating average of the past demand.
Types of average method:
simple moving and weighted moving average.

i. Moving or simple moving average; is a simple arithmetic average of a set of

observed values, from the present time period to a certain time period.
 Specifically in this method, equal weight is given to all periods.
Required: calculate 3, 4, and 5 month moving average?

SMA= sum of demands for “n” period

Number of period or “n”
4 - 33
ii. Weighted Moving Average;
 This method is quite similar with simple moving average, but here we
add or incorporates weights for demand.
 The principle of weight distribution is based on greater weight is
given to the most recent data.

Example; From the monthly data given above, compute a weighted three
months moving average for July, where the weights are 0.5, 0.3 weights and
0.2 for the months respectively.
= (0.5*500+ 0.3*450 + 0.2*400)
= 250+135+80
=465
4 - 35
 iii. causal or regression method
• Used when changes in one or more independent variable can be used to
predict the change in the dependent variable.
• Most common techniques is linear regression analysis.
• Forecasting an outcome based on predictor variables using the least square
technique.
y=a + bx
y= value of dependent variables
a= y-axis intercept
b=slope of the regression line
x= the independent variable

4 - 36
 The trend line and projection equation are given as;
Y = a + bX Y= a + bx
∑Y = na + b∑X........................... (1) b=
∑XY = a∑X + b∑X2.................. (2) a= ȳ - b(x̄ )
y= trend line to be predicted or
dependent variable
x̄ = mean of x
ȳ= mean of y
a= the y intercept
b= the slop of the trend line ȳ= mean of dependent
x= independent variable in our x̄ = mean of independent
case time
4 - 37
ILLUSTRATION; suppose a manufacturer of transistors in Addis
Abeba decides to forecast the sales of its products during the next
year 1994 by trend projection method. He collects data on his sales
for the past five years as follows; forecast sales of 2015?

Year Sales in 000

2010 50
2011 60
2012 55
2013 70
2014 75
4 - 38
4 - 39
4 - 40
4 - 41
 Cont’d
D. Exponential smoothing; - weighted averaging methods based on
previous forecast plus a percentage of the forecast error.

• The weight given to latest actual demand is called a smoothing

constant and is represented by the Greek letter alpha (α) >0, <1.
• 𝜶 close to 0: signifies that future forecasted values are the average of historical
data (giving more weights to historical data)
• 𝜶 close to1: signifies that future forecast values are the results of the recent
observation (giving more weights to recent observations).

• New forecast = (ά) (latest actual demand) + (1-ά) (previous

forecast)
4 - 42
 Cont’d
Example

The old forecast for May was 220, and the actual demand for May
was 190. If alpha (α) is 0.15, calculate the forecast for June? and
If June demand turns out to be 218, calculate the forecast for July?

•June forecast = (0.15) (190) + (1 - 0.15) (220) = 215.5

•July forecast = (0.15) (218) + (0.85) (215.5) = 215.9

4 - 43
Thank you

44 4 - 44