OPERATIONS MANAGEMENT: FORECASTING
2. Technological forecast are concerned with rates of technological progress,
Forecasting is the art and science of predicting future events. Forecasting may
involve taking historical data (such as past sales) and projecting them into the
future with a mathematical model. It may be subjective or an intuitive prediction. It
may be based on demand-driven data, such as customer plans to purchase, and
projecting them into the future. Or the forecast may involve a combination of these,
that is, a mathematical model adjusted by a manager’s good judgment.
Few businesses, however, can afford to avoid the process of forecasting by
just waiting to see what happens and then taking their chances. Effective planning
in both the short run and long run depends on a forecast of demand for the
company’s products.
*FORECASTING TIME HORIZONS
A forecast is usually classified by the future time horizon that it covers. Time
horizons fall into three categories:
1. Short-range forecast: This forecast has a time span of up to 1 year but is generally
less than 3 months. It is used for planning purchasing, job scheduling, workforce
levels, job assignments and production levels.
2. Medium-range forecast: A medium-range, or intermediate, forecast generally spans
from 3 months to 3 years. It is useful in sales planning, production planning and
budgeting, cash budgeting, and analysis of various operating plans.
3. Long-range forecast: Generally 3 years or more in time span, long-range forecast
are used in planning for new products, capital expenditures, facility location or
expansion, and research and development.
Medium- and long-range forecasts are distinguished from short-rrange forecasts by
three features:Intermediate and long-range forecasts deal with more comprehensive
issues supporting management decisions regarding planning and products, plants
and processes.
1. Short term forecasting usually employs different methodologies than longer-term
forecasting. Mathematical techniques, such as moving averages, exponential
smoothing, and trend exploration, are common to short run projections.
2. Short-range forecasts tend to be more accurate than longer-range forecasts.
Factors that influence demand change every day. Thus as time horizon
lengthens, it is likely that forecasts accuracy will diminish
*TYPES OF FORECASTS
1. Economic forecasts address the business cycle by predicting inflation rates,
money supplies, housing starts and other planning indicators.
which can result in the birth of exciting new products, requiring new plants and
equipment.
3. Demand forecast are projections of demand for a company’s product or
services. Demand-driven forecast drive a company’s production, capacity,
and scheduling system and serves as inputs to financial, marketing, and
personnel planning.
Economic and technological forecasting are specialized techniques that
may fall outside the role of the operations manager.
*The Strategic Importance of Forecasting
Good forecast are of critical importance in all aspects of a business: The
forecast is the only estimate of demand until actual demand becomes known.
Forecasts of demand therefore drive decisions in many areas. Let’s look at the
impact of product demand forecast on three activities: (1) supply-chain
management, (2) human resources and (3) capacity.
Supply Chain Management
Good supplier relations and the ensuing advantages in product innovation,
cost, and speed to market depend on accurate forecasts.
Human Resources
Hiring, training, and laying off workers all depend on anticipated demand. If the
human resources department must hire additional workers without warning, the
amount of training declines, and the quality of the work force suffers.
Capacity
When capacity is inadequate, the resulting shortages can lead to loss of
customers and market share.
*SEVEN STEPS IN THE FORECASTING SYSTEM
1. Determine the use of forecast.
2. Select the items to be forecasted.
3. Determine the time horizon of the forecast.
4. Select the forecasting model.
5. Gather the data needed to make the forecast.
6. Make the forecast.
7. Validate and implement the results.
These seven steps present systematic way of initiating, designing, and
implementing a forecasting system. When the system is to be used to generate
[Date] 1
OPERATIONS MANAGEMENT: FORECASTING
forecast regularly over time, data must be routinely collected. Then actual Overview of Quantitative Methods
computations are usually made by computer. Regardless of the system, each 1. Naïve approach -Time series models
company faces several realities: 2. Moving averages -Time series models
3. Exponential smoothing -Time series models
 Outside factors that we cannot predict or control often impact the forecast.
4. Trend projection -Associative model
 Most forecasting techniques assumes that there is some underlying stability in the
5. Linear regression -Associative model
system
 Both product family and aggregated forecasts are more accurate than individual Time series models predict on the assumption that the future is a function of the past. In other
product products. words, they look at what has happened over a period of time and use a series of past to make a
forecast.
*FORECASTING APPROACHES
Associative models incorporate the variables or factors that might influence the quantity
There are two general approaches to forecasting:
being forecast.
1. Quantitative forecast use a variety of mathematical models that rely in
*Time series forecasting
historical data and/or associative variables to forecast demand.
- based on sequence of evenly spaced (weekly, monthly, quarterly, and so on)
2. Subjective or Qualitative forecast incorporate such factors as the
data points.
decision maker’s intuition, emotions, personal experiences, and value
-Forecasting time-series data implies that future values are predicted only from
system in reaching a forecast.
past values and that other variables, no matter how potentially valuable, may
Overview of Qualitative Techniques be ignored.
In this section, we consider 4 different qualitative forecasting techniques:
Decomposition of a Time series
1. Jury of executive opinion: Under this method, the opinions of a group of high- Analyzing time series means breaking down past data into components and
level experts or managers, often in combination with statistical models, are then projecting them forward. A time series has four components:
pooled to arrive at a group estimate or demand.
1. Trend is the gradual upwards or downward movement of the data over
2. Delphi model: There are three different types of participants in the Delphi
time. Changes in income, population, age, distribution, or cultural views
method: decision makers, staff personnel and respondents. Decision
may account for movement in trend.
makers usually consist of a group of 5 to 10 experts who will be making the
2. Seasonality is a data pattern that repeats after a period of days, weeks,
actual forecasts. Staff personnel assist decision makers by preparing,
months, or quarters.
distributing, collecting, and summarizing a series of questionnaires and
3. Cycles are patterns in the data that occur every several years. They are
survey results. The respondents are a group of people, often located in
usually tied into the business cycle and are major importance in short-
different places, whose judgments are valued. This group provides input to
term business analysis and planning. Predicting business cycles are
the decision makers before the forecast is made.
often difficult because they may be affected by political events or by
3. Sales force composite: In this approach, each salesperson estimate what sales
international turmoil.
will be in his/ her region. These forecasts are then reviewed to ensure that
4. Random variations are “blips” in the data caused by chance and
they are realistic. Then they are combined at the district and national levels
unusual situations. They follow no discernable pattern, so they cannot
to reach an overall forecasts.
be predicted.
4. Market survey: This methods solicits input from customers or potential
customers regarding future purchasing plans. It can help not only in *Naïve Approach
preparing a forecast but also in improving product design and planning for The simplest way to forecast is to assume that demand in the next period
new products. The consumer market survey and sales force composite will be equal to demand in the most recent period. It turns out that for some
methods can, however, suffer from overly optimistic forecasts that arise product lines, this naïve approach is the most cost-effective and efficient
from customer input.

[Date] 2
OPERATIONS MANAGEMENT: FORECASTING
forecasting model. At least it provides a starting point against which some
sophisticated models that follow can be compared.
*Moving Averages
A moving average forecast uses a number of historical actual data values
to generate a forecasts. Moving averages are useful if we can assume that
market demands will stay fairly steady over time.
Mathematically, the simple moving average (which serves as an estimate
of the next period’s demand) is expressed as follows:
MOVING ∑ demand in previous n periods
= ∑ Weights
AVERAGE
n
Where n is the number of periods in the moving average.
Example:
When a detectable trend or pattern is present, weights can be used to place more
emphasis on recent values. This practice makes more forecasting techniques more
responsive to changes because more recent periods may be more heavily
weighted. Choice of weights is somewhat more arbitrary because there is no set
formula to determine them. Therefore deciding weights to use requires some
experience.
A weighted moving average may be expressed mathematically as:
WEIGHTED
∑ ((Weight for period n )(Demand in period))
MOVING =
AVERAGE
Example:
Eilezeal's Milktea Shop wants forecast sales by weighting the past 3-months, with
more weight given to recent data to make them more significant.

Eilezeal's Milktea Shop wants a 3-month moving average forecasts for next ACTUAL
January. MONTH SALES 3-month moving average
January 10
Approach:
February 12
ACTUAL
March 13
MONTH SALES 3-month moving average
April 16
January 10
May 19
February 12
June 23
March 13
July 26
April 16
August 30
May 19
September 28
June 23
October 18
July 26
Nov ember 16
August 30
December 14
September 28
October 18 Weights Applied: Period
3 Last month
Nov ember 16
2 2 months ago
December 14 1 3 months ago
6 Sum of weights

[Date] 3
OPERATIONS MANAGEMENT: FORECASTING
*Exponential Smoothing develop a linear trend line by a precise statistical method, we can apply the least-
-Is another weighted-moving-average forecasting method. It involves very little square method. This approach results in a straight line that minimizes the sum of the
record keeping of past data and is fairly easy to use. The basic exponential squares of the vertical differences or deviations from the line to each of the actual
smoothing formula can be shown as follows: observations.

Last period's forecast + A least-squares line is described in terms of its y-intercept (the height at which it
New Forecast = ὰ (Last period's actual demand-Last period's intercepts the y –axis) and its expected change (slope). If we can compute the y-
intercept and the slope, we can express the line with the following equation:
forecast)
ŷ=a + bx
Where ὰ is a weight, or smoothing constant, chosen by the forecaster, that has a
value greater than or equal to 0 and less than or equal to 1. where ŷ (called “y hat”) = computed value of the variable to be predicted
The concept is not complex. The latest demand is equal to the old forecast (called the dependent variable)
adjusted by a fraction of the difference between the last period’s demand and last a = y –axis intercept
period’s forecast. b = slope of the regression line ( or the rate of change in y for given changes in x)
x = the independent variable (which in this case is time)
Example:
Statisticians have developed equations that we can use to find values of a and b for
In January, a car dealer predicted February demand for 142 Ford Mustangs. Actual
any regression line. The slope b is found by:
February demand was 153 autos. Using a smoothing constant chosen by
management of ὰ=.20, the dealer wants to forecast March demand using the ∑xy-nxy
exponential smoothing model. b =
∑x2-nx2
where
b = slope of the regression line
∑ = summation sign
x = known values of the independent variable
Measuring Forecast Error y = known values of the dependent variable
The overall accuracy of any forecasting model- moving average, exponential x= average of the x-values
smoothing or other – can be determined by comparing the forecasted values with y= average of the y-values
the actual or observed values. If (F), denotes the forecast in period (t) and A t n= number of data points or observations
denotes the actual demand in period, the forecast error (or deviation) is defined as:
We can compute the y-intercept a as follows:
FORECAST a = y-bx
= Actual Demand - Forecast Value
ERROR
Example:
Forecasts tend to be more accurate as they become shorter. Therefore, forecast The demand for electric power at MERALCO over the past 7 years is shown
error tends to drop with shorter forecasts. in the following table, in megawatts. The firm wants to forecast next year’s
demand by fitting a straight-line trend to these data.
Trend Projection
This technique fits a trend line to series of historical data points and then projects the
slope of the line into the future for medium to long-range forecasts. If we decide to

[Date] 4
OPERATIONS MANAGEMENT: FORECASTING
ELECTRICAL POWER AVERAGE AVERAGE
YEAR X2 SEASONAL
DEMAND XY
MONTH YEAR 1 YEAR 2 YEAR 3 PERIOD MONTHLY
1 74 INDEX
DEMAND DEMAND
2 79
JANUARY 80 85 105
3 80
4 90 FEBRUARY 70 85 85
5 105 MARCH 80 93 82
6 142 APRI L 90 95 115
7 122
MAY 113 125 131
Notes on the Use of the Least-Squares Method JUNE 110 115 120
Using the least-squares method implies that we have met three JULY 100 102 113
requirements: AUGUST 88 102 110
1. We always plot the data because least-squares data assume a SEPTEMBER 85 90 95
linear relationship. If a curve appears to be present, curvilinear OCTOBER 77 78 85
analysis is probably needed. NOVEMBER 75 82 83
2. We do not predict time periods far beyond our given data base. DECEMBER 82 78 80
3. Deviations around the least-squares line are assumed to be random
and normally distributed, with most observations to close to the line ***If we expect the annual demand for computers to be 1,200 units next year,
and only a smaller number farther out. compute for the forecasted monthly demand.

Seasonal Variations in Data Summary

Seasonal variations in data are regular movements in a time series that relate to
recurring events such as weather or holidays. Seasonality may be applied to hourly,
daily, weekly, monthly, or other recurring patterns. Similarly, understanding seasonal
variations is important for capacity planning in organizations that handle peak
loads.
Time series forecasts involve reviewing the trend of data over a series of time
periods. The presence of seasonality makes adjustments in trend-line forecasts
necessary. Seasonality is expressed in terms of the amount that actual values differ
from average values in the time series. Analyzing data in monthly or quarterly terms
usually makes it easy for a statistician to spot seasonal patterns.
Example:
Forecasts are a critical part of the operations manager’s function.
Demand forecasts drive a firm’s production, capacity, and scheduling
systems and affect the financial marketing, and personnel planning
functions.
There are variety of qualitative and quantitative forecasting
techniques. Qualitative approaches employ judgment, experience,
intuition, and a host of other factors that are difficult to quantify.
Quantitative techniques uses historical data and causal, or associative,
relations to project future demands.

A RGC distributor of Dell laptop computers wants to develop monthly

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

[Date] 5