• Managers are always trying to make better estimates of what will happen in the future

in the face of uncertainty. Making good estimates is the main purpose of forecasting -
The art and science of predicting future events.
• An increasingly complex world economy makes forecasting challenging
• It may be a subjective or an intuitive prediction. It may be based on demand-driven
data, Or the forecast may involve a combination of these, that is, a mathematical
model adjusted by a manager’s good judgment.
• There is seldom one superior method of forecasting.
• Because there are limits to what can be expected from forecasts, we develop error
measures. Preparing and monitoring forecasts can also be costly and time consuming.
• Effective planning in both the short run and long run depends on a forecast of demand
for the company’s products.

Learning Objective 4.1 - Understand the three time horizons

and which models apply for each

• 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
forecasts 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-range forecasts by
three features:
1. Intermediate and long-range forecasts deal with more comprehensive issues
supporting management decisions regarding planning and products, plants,
and processes.
2. Short-term forecasting usually employs different methodologies than longer-
term forecasting. Mathematical techniques, such as moving averages,
exponential smoothing, and trend extrapolation are common to shortrun
projections.
3. Short-range forecasts tend to be more accurate than longerrange forecasts. As
the time horizon lengthens, it is likely that forecast accuracy will diminish.
• Organizations use three major types of forecasts in planning future operations:
1. Economic forecasts address the business cycle by predicting inflation rates,
money supplies, housing starts, and other planning indicators.
2. Technological forecasts are concerned with rates of technological progress
 3. Demand forecasts are projections of demand for a company’s products or
services. There are demand-driven forecasts , where the focus is on rapidly
identifying and tracking customer desires.
• Demand-driven forecasts drive a company’s production, capacity, and scheduling
systems and serve as inputs to financial, marketing, and personnel planning. In
addition, the payoff in reduced inventory and obsolescence can be huge.
• Economic and technological forecasting are specialized techniques that may fall
outside the role of the operations manager.
• Let’s look at the impact of product demand forecast on three activities:
1. Supply-chain management - Good supplier relations and the ensuing
advantages in product innovation, cost, and speed to market depend on
accurate forecasts.
▪ Reduced costs and increased accuracy also drives innovation.
▪ Finalizing main demand also facilitates improved forecasting of
demands for related accessories.
▪ Creating a common forecasting process by discussing with different
supply chain partners and suppliers gives birth to Collaborative
Planning forecasting and Replenishment (CPFR).
2. Human resources- Hiring, training, and laying off workers all depend on
anticipated demand.
▪ Without planned staffing, the amount of training declines and quality
of the workforce suffers.
3. Capacity - When capacity is inadequate, the resulting shortages can lead to
loss of customers and market share.
▪ Insufficient capacity means lost sales.
▪ Over capacity means increased cost.
• 7 Steps in forecasting system :- These steps are followed in sequence for an effective
forecast -
1. Determine the use of the 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 - Error measures are also applied in this
step.
• These seven steps present a systematic way of initiating, designing, and implementing
a forecasting system.

Learning Objective 4.2 - Explain when to use each of the four

qualitative models
 • Quantitative forecasts use a variety of mathematical models that rely on historical
data and/or associative variables to forecast demand.
• Subjective or qualitative forecasts incorporate such factors as the decision maker’s
intuition, emotions, personal experiences, and value system in reaching a forecast.
• In practice, a combination of the two is usually most effective.
• We consider four different qualitative forecasting techniques:
1. Jury of executive opinion: Under this method, the opinions of a group of
high-level experts or managers, often in combination with statistical models,
are pooled to arrive at a group estimate of demand.
2. Delphi method : There are three different types of participants in the Delphi
method
1. Decision makers usually consist of a group of 5 to 10 experts who will
be making the actual forecast.
2. Staff personnel assist decision makers by preparing, distributing,
collecting, and summarizing a series of questionnaires and survey
results
3. The respondents are a group of people, often located in different
places, whose judgments are valued. This group provides inputs to the
decision makers before the forecast is made.
3. Sales force composite : In this approach, each salesperson estimates what
sales will be in his or her region. These forecasts are then reviewed to ensure
that they are realistic. They can be aggregated at district or national level to
achieve an overall forecast.
4. Market survey : This method solicits input from customers or potential
customers regarding future purchasing plans. It can help not only in preparing
a forecast but also in improving product design and planning for new products.

Overview of Quantitative Methods-

• Five quantitative forecasting methods, all of which use historical data, are described
in this chapter. They fall into two categories:
1. Time-series models - They predict on the assumption that the future is a
function of the past.
▪ They look at what has happened over a period of time and use a series
of past data to make a forecast.
▪ There are four types of approaches in this model -
1. Naive approach
2. Moving averages
3. Exponential smoothing
4. Trend projection
2. Associative models - They incorporate the variables or factors that might
influence the quantity being forecast.
▪ Linear regression is one of the associative models.
Learning Objective 4.3 - Apply the naive, moving-average,
exponential smoothing, and trend methods

• A time series is based on a sequence of evenly spaced (weekly, monthly, quarterly,

and so on) data points.
• Forecasting time-series data implies that future values are predicted only from past
values and that other variables, no matter how potentially valuable, may be ignored.
• A time series has four components:
1. Trend is the gradual upward or downward movement of the data over time.
2. Seasonality is a data pattern that repeats itself after a period of days, weeks,
months, or quarters.
3. Cycles are patterns in the data that occur every several years. They are usually
tied into the business cycle and are of major importance in short-term business
analysis and planning.
4. Random variations are “blips” in the data caused by chance and unusual
situations.

Naive Approach

• In this approach, we assume that demand in the next period will be equal to demand
in the most recent period.
• For some product lines, this naive approach is the most cost-effective and efficient
objective forecasting model.

Moving Averages

• A moving-average forecast uses a number of historical actual data values to generate

a forecast.
• Moving averages are useful if we can assume that market demands will stay fairly
steady over time .
• A 4-month moving average is found by simply summing the demand during the past 4
months and dividing by 4.
• When a detectable trend or pattern is present, weights can be used to place more
emphasis on recent values. Choice of weights is somewhat arbitrary because there is
no set formula to determine them.
 • The magnitude of value of weights is not important as long as relative weights
(having same ratio) of a model are same.
• Moving averages do, however, present three problems:
1. 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.
2. Moving averages cannot pick up trends very well. Because they are averages,
they will always stay within past levels and will not predict changes to either
higher or lower levels. That is, they lag the actual values.
3. Moving averages require extensive records of past data.
• If recent data is given higher relative weight, then weighted moving average reacts
much quickly to variations in data.

Exponential smoothing

• This trend requires very little record keeping of past data.

New forecast = Last period’s forecast + a (Last period’s actual demand − Last period’s
forecast)
 • Here a 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 ( a is actually alpha)
• Above equation can also be written mathematically as:

Ft = Ft-1 + a (At-1 - Ft-1)

• The concept is not complex. The latest estimate of demand is equal to the old forecast
adjusted by a fraction of the difference between the last period’s actual demand and
last period’s forecast.

• The smoothing constant , a , is generally in the range from .05 to .50 for business
applications. It can be changed to give more weight to recent data (when a is high) or
more weight to past data (when a is low). If the value reaches 1, then formula terms in
Naive approach model.
• 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.

Exponential Smoothing with Trend Adjustment

 • Simple exponential smoothing, the technique we just illustrated in Examples 3 to 6 , is
like any other moving-average technique: It fails to respond to trends.
• In this method the idea is to compute an exponentially smoothed average of the data
and then adjust for positive or negative lag in trend. The new formula is:

Forecast including trend (FITt) = Exponentially smoothed forecast average (Ft) +

Exponentially smoothed trend (Tt)

• This procedure requires two smoothing constants: a for the average and b (it is beta)
for the trend. We then compute the average and trend each period:

Ft = a(Actual demand last period) + (1 - a)(Forecast last period + Trend estimate last
period)
or
Ft = a(At - 1) + (1 - a)(Ft - 1 + Tt - 1)
Tt = b(Forecast this period - Forecast last period) + (1 - b)(Trend estimate last period)
or:
Tt = b(Ft - Ft - 1) + (1 - b)Tt - 1
 • The value of the trend-smoothing constant, b (beta), resembles the a constant because
a high b is more responsive to recent changes in trend.
• Simple exponential smoothing is often referred to as first-order smoothing , and
trend adjusted smoothing is called second-order smoothing or double smoothing .

Trend Projections

• This technique fits a trend line to a series of historical data points and then projects
the slope of the line into the future for medium- to long-range forecasts.
• Several mathematical trend equations can be developed (for example, exponential and
quadratic), but in this section, we will look at linear (straight-line) trends only.
 • If we decide to develop a linear trend line by a precise statistical method, we can
apply the least-squares method . This approach results in a straight line that
minimizes the sum of the squares of the vertical differences or deviations from the
line to each of the actual observations.
• A least-squares line is described in terms of its y -intercept

y = a + bx

• These a and b are not alpha and beta.

• Statisticians have developed equations that we can use to find the values of a and b for
any regression line. The slope b is found by:

Learning Objective 4.4 - Compute three measures of forecast

accuracy
• If Ft denotes the forecast in period t , and At denotes the actual demand in period t ,
the forecast error (or deviation) is defined as:

Forecast error = Actual demand - Forecast value

= At - F t

• Several measures are used in practice to calculate the overall forecast error. These
measures can be used to compare different forecasting models, as well as to monitor
forecasts to ensure they are performing well.

Mean Absolute Deviation

• This value is computed by taking the sum of the absolute values of the individual
forecast errors (deviations) and dividing by the number of periods of data ( n ):
Mean Squared Error

• MSE is the average of the squared differences between the forecasted and observed
values. Its formula is:
 • The MSE tends to accentuate large deviations due to the squared term

Mean Absolute Percent Error

• A problem with both the MAD and MSE is that their values depend on the magnitude
of the item being forecast.
• To avoid this problem, we can use the mean absolute percent error (MAPE) . This is
computed as the average of the absolute difference between the forecasted and actual
values, expressed as a percentage of the actual values.
• The MAPE is perhaps the easiest measure to interpret.
Learning Objective 4.5 - Develop seasonal indices

• 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.
• Understanding seasonal variations is important for capacity planning in organizations
that handle peak loads.
• Seasonality is expressed in terms of the amount that actual values differ from average
values in the time series. This is how it's dealt with.
• In what is called a multiplicative seasonal model , seasonal factors are multiplied by
an estimate of average demand to produce a seasonal forecast.
• Here are the steps we will follow for a company that has “seasons” of 1 month:
1. Find the average historical demand each season (or month in this case) by
summing the demand for that month in each year and dividing by the number
of years of data available. For example, if, in January, we have seen sales of 8,
6, and 10 over the past 3 years, average January demand equals (8 + 6 + 10)/3
= 8 units.
2. Compute the average demand over all months by dividing the total average
annual demand by the number of seasons. For example, if the total average
demand for a year is 120 units and there are 12 seasons (each month), the
average monthly demand is 120/12 = 10 units.
3. Compute a seasonal index for each season by dividing that month’s historical
average demand (from Step 1) by the average demand over all months (from
Step 2). For example, if the average historical January demand over the past 3
years is 8 units and the average demand over all months is 10 units, the
seasonal index for January is 8/10 = .80. Likewise, a seasonal index of 1.20
for February would mean that February’s demand is 20% larger than the
average demand over all months.
4. Estimate next year’s total annual demand.
5. Divide this estimate of total annual demand by the number of seasons, then
multiply it by the seasonal index for each month. This provides the seasonal
forecast .
• Read cexample 9, 10, 11 for detailed application of seasonal indices. (Pg. 127-131)
• Cycles are like seasonal variations in data but occur every several years , not weeks,
months, or quarters.
• Forecasting cyclical variations in a time series is difficult. This is because cycles
include a wide variety of factors that cause the economy to go from recession to
expansion to recession over a period of years
• Forecasting demand for individual products can also be driven by product life cycles

Learning Objective 4.6 - Conduct a regression and correlation

analysis
• Unlike time-series forecasting, associative forecasting models usually consider
several variables that are related to the quantity being predicted.
• This approach is more powerful than the time-series methods that use only the
historical values for the forecast variable.
• Example : the sales of Dell PCs may be related to Dell’s advertising budget, the
company’s prices, competitors’ prices and promotional strategies, and even the
nation’s economy and unemployment rates. In this case, PC sales would be called the
dependent variable , and the other variables would be called independent variables
• The most common quantitative associative forecasting model is linear-regression
analysis. It is a straight-line mathematical model to describe the functional
relationships between independent and dependent variables.
• We now deal with the same mathematical model that we saw earlier, the least-squares
method. But we use any potential “cause-and-effect” variable as x.
• The final part of Example shows a central weakness of associative forecasting
methods like regression. Even when we have computed a regression equation, we
must provide a forecast of the independent variable x —in this case, payroll—before
estimating the dependent variable y for the next time period
• you can imagine the difficulty of determining future values of some common
independent variables (e.g., unemployment rates, gross national product, price
indices, and so on).
• The forecast of $3,250,000 for Nodel’s sales in Example 12 is called a point estimate
of y . The point estimate is really the mean , or expected value , of a distribution of
possible values of sales.
• To measure the accuracy of the regression estimates, we must compute the standard
error of the estimate , Sy, x . This computation is called the standard deviation of the
regression.
 • Regression can be done individually for particular independent variables.

Correlation coefficient -
• The regression equation is one way of only expressing the nature of the relationship
between two variables. Regression lines are not “cause-and-effect” relationships.
• Another way to evaluate the relationship between two variables is to compute the
coefficient of correlation. This measure expresses the degree or strength of the linear
relationship (still doesn't imply causality).
• Usually identified as r , the coefficient of correlation can be any number between +1
and -1 (look fig below for interpretation)
 • Another measure does exist. It is called the coefficient of determination and is
simply the square of the coefficient of correlation—namely, r2

Multiple-Regression Analysis -

• Multiple regression is a practical extension of the simple regression model we just

explored. It allows us to build a model with several independent variables instead of
just one variable.
• The mathematics of multiple regression becomes quite complex (and is usually
tackled by computer)

Learning Objective 4.7 - Use a tracking signal

• Once a forecast has been completed, it should not be forgotten.

• A firm needs to determine why actual demand (or whatever variable is being
examined) differed significantly from that projected.
• A tracking signal is a measurement of how well a forecast is predicting actual values
• The tracking signal is computed as the cumulative error divided by the mean absolute
deviation (MAD) :
• Positive tracking signals indicate that demand is greater than forecast. Negative
signals mean that demand is less than forecast.
• Small deviations are okay, but positive and negative errors should balance one
another so that the tracking signal centers closely around zero.
• A consistent tendency for forecasts to be greater or less than the actual values (that is,
for a high absolute cumulative error) is called a bias error.
• Once tracking signals are calculated, they are compared with predetermined control
limits.

• Control limits are not so low as to be triggered with every small forecast error and not
so high as to allow bad forecasts to be regularly overlooked.
• Adaptive forecasting refers to computer monitoring of tracking signals and self-
adjustment if a signal passes a preset limit.
• Adaptive smoothing An approach to exponential smoothing forecasting in which the
smoothing constant is automatically changed to keep errors to a minimum.
• Focus forecasting : Forecasting that tries a variety of computer models and selects
the best one for a particular application. The forecast method yielding the least error is
selected by the computer, which then uses it to make next month’s forecast.