I.

Date:
Indicate the date that you will be the presenter

II. Objective:
Itemized in bullet form at least 3 objectives

III. Discussion:

Forecasting

Planning is an important part in business. This is one of the duties of a manager. However, if
there are uncertainties in the planning, the managers will find it difficult to do so effectively. This is
when forecasting comes in. Forecasts help managers by reducing some of the uncertainty in order to
develop more meaningful plans. It is important to anticipate the consumer wants and businesses can
correctly forecast what the buyers want are more successful than those who simply guesses and guesses
wrong. Yes, the managers do not know exactly what the consumers wants but by analyzing previous
buying patterns, they can come up with a reasonable approximation of what buyers will want.

A forecast is a statement about the future value of a variable such as demand and a basic input in
the decision processes of operations management. They are predictions about the future. The better those
predictions, the more informed decisions can be.

Forecast accuracy is a function of the ability of forecasters to correctly model demand, random
variation, and sometimes unforeseen events. To make forecasts, two aspects must be considered: the
current factors or conditions; past experience in a similar situation. Sometimes, one will rely more on
one than the other, depending on the relevant approach in the situation.

Forecasts are made with reference to a specific time horizon. A time horizon, also known as a
planning horizon, is a fixed point of time in the future at which point certain processes will be evaluated
or assumed to end. It can be long-range, covering several years or more; important for long term
decisions of an organization such as new products or services, new equipment, new facilities, or
something else that will require a somewhat long lead time to develop, construct, or otherwise
implement. It can also be short term, covering a day to a week; helpful in planning and scheduling day
to day operations.

Uses of forecast in business organizations:

Accounting. New product/process cost estimates, process cost estimates, profit projections, cash
management.

Finance. Equipment and replacement needs, timing and amount of funding/borrowing needs

Human resources. Hiring activities including recruitment, interviewing, training, layoff,

planning including outplacement, counselling.

Marketing. Pricing and promotion, e-business strategies, global competition strategies.

Management Information System. New information systems, internet services.

Operations. Schedules, capacity planning, work assignments and workloads, inventory

planning, make-or-buy decisions, outsourcing, project management.

Product service design. Revision of current features, design of new product.

In most uses of forecasts, decisions in one area have consequences in the other. Hence, it is
important for managers to coordinate decisions. Forecasting is also an important component of yield
management, which relates to the percentage of capacity being used. Accurate forecasts can help
managers plan tactics to match capacity with demand, hence achieving high yield levels.
 Two uses for forecasts: to help managers plan the system, and help them plan the use of the
system. Planning the system involves long-range plans such as the types of products and services to
offer, what facilities and equipment to have, where to locate, and others. Planning the use of the system
refers to short-range and intermediate-range planning. This includes tasks such as planning inventory
and workforce levels, planning purchasing and production, budgeting, and scheduling.

Other than demand, business forecasting is also used to predict profit, revenues, costs,
productivity changes, prices and availability of energy and raw materials, interest rates, movements of
key economic indicators (gross domestic product, inflation, government borrowing), and the prices of
stocks and bonds.

Features Common to All Forecasts:

1. Techniques generally assume the same underlying causal system that existed in the past will
continue to exist in the future.

2. Forecasts are rarely perfect; actual results often differ from predicted ones so allowances
should be made for forecast errors.

3. Forecasts for groups of items tend to be more accurate than forecasts for individual items. This
is due to errors among items in a group usually has a cancelling effect.

4. Forecast accuracy decreases as the time horizon increases. The short-range forecasts hold
fewer uncertainties than longer range forecasts so it tends to be more accurate.

Elements of a Good Forecast

Timely. A certain amount of time is needed to respond to the information contained in a forecast. The
forecasting horizon must cover the time necessary to implement possible changes.

Accurate. 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.

Reliable. Forecasts should work consistently. If it wasn’t, it will make users hesitate for everytime a
new forecast is issued.

Expressed in meaningful units. Financial planners need to know how much money will be needed,
production planners need to know how many units will be needed, and schedulers need to know what
machines and skills will be required. The choice of units depends on user needs.

In writing. Although this will not guarantee that all concerned are using the same information, it will at
least increase the likelihood of it. In addition, a written forecast will permit an objective basis for
evaluating the forecast once actual results are in.

Simple to understand and use. Users often lack confidence in forecasts based on sophisticated
techniques. Fairly simple forecasting techniques enjoy widespread popularity because users are more
comfortable working with them.

Cost-effective. The benefits should outweigh the costs.

Steps in the Forecasting Process

1. Determine the purpose of the forecast. How will it be used and when will it be needed? This
step will provide an indication of the level of detail required in the forecast, the amount of resources
(personnel, computer time, dollars) that can be justified, and the level of accuracy necessary.

2. Establish a time horizon. The forecast must indicate a time interval, keeping in mind that
accuracy decreases as the time horizon increases.
 3. Select a forecasting technique. Obtaining the data can involve significant effort. Once
obtained, the data may need to be filtered to get rid of outliers and obviously incorrect data before
analysis.

4. Obtain, clean, and analyze appropriate data.

5. Make the forecast.

6. Monitor the forecast. A forecast has to be monitored to determine whether it is performing in

a satisfactory manner. If it is not, reexamine the method, assumptions, validity of data, and so on;
modify as needed; and prepare a revised forecast.

Approaches to Forecasting

Qualitative. It permits inclusion of soft information in the forecasting process. Soft information
examples are human factors, personal opinions, hunches. Those factors are often omitted or downplayed
when quantitative techniques are used because of the difficulty to quantify.

Quantitative. It consists of analyzing objective, or hard data. They usually avoid personal biases that
sometimes contaminate qualitatively methods. In practice, either or both approaches might be used to
develop a forecast.

Judgemental. It relies on analysis of subjective inputs obtained from various sources, such as consumer
surveys, the sales staff, managers and executives, and panels of experts.

Time Series. It attempts to project past experience into the future and uses historical data with the
assumption that the future will be like the past. It smooths out random variations in historical data such
as attempting to identify specific patterns in the data and project those patterns into the future, without
trying to identify causes of the patterns.

Associative Models. It uses equations that consist of one or more explanatory variables that can be used
to predict demand.

Forecasts Based on Judgment and Opinion

Executive. A small group of upper-level managers may meet and collectively develop a forecast. It is
often used as a part of long-ranged planning and new product development and has the advantage of
bringing together the considerable knowledge and talents of various managers. However, the risk is the
view of one persona will prevail and the possibility that diffusing responsibility for the forecast over the
entire group may result in less pressure to produce a good forecast.

Salesforce. Members of the sales staff or the customer service staff are often good sources of
information because of their direct contact with consumers. However, there are several drawbacks: 1)
Staff members may be unable to distinguish between what customers would like to do and what they
actually will do. 2) These people are sometimes overly influenced by recent experiences and after
several periods of low sales, their estimates may tend to become pessimistic; after several periods of
good sales, they may tend to be too optimistic. 3) If forecasts are used to establish sales quotas, there
will be a conflict of interest because it is to the salesperson’s advantage to provide low sales estimates.

Consumer Surveys. Organizations seeking consumer input usually resort to consumer surveys which
enable them to sample consumer opinions. Advantage is that they can tap information that might not be
available elsewhere. Disadvantage, however, is that A considerable amount of knowledge and skill is
required to construct a survey, administer it, and correctly interpret the results for valid info. Surveys
can also be expensive and time-consuming and even under the best conditions, surveys of the general
public must contend with the possibility of irrational behavior patterns.
Delphi Method

The Delphi Method is an iterative process intended to achieve a consensus forecast and it
involves circulating a series of questionnaires among individuals who possess the knowledge and ability
to contribute meaningfully.

Responses are kept anonymous, which tends to encourage honest responses and reduces the risk
of bias opinions. Each new questionnaire is developed using the info extracted from the previous one
thus enlarging the scope of information on which participants can base their judgments.

It has been applied to a variety of situations, not all of which involve forecasting. But as a
forecasting tool, the method is useful for technological forecasting, that is, for assessing changes in
technology and their impact on an organization. Often the goal is to predict when a certain event will
occur. For the most part, these long term, single time forecasts, which usually have very little hard
information to go by or data that are costly to obtain. So the problem does not lend itself to analytical
techniques rather judgments of experts who possess sufficient knowledge to make predictions are used.

FORECASTS BASED ON TIME SERIES DATA

A time series is a time-ordered sequence of observations taken at regular intervals. While

forecasting techniques based on time series data are made on the assumption that future values of the
series can be estimated from past values, data may be measurements of various things. Through merely
plotting the data and visually examining the plot, analysis of time series data can be done and numerous
patterns can be seen. Behaviors observed might be any of the following:

1. Trend – A long-term upward or downward movement in data (e.g., population shifts,

changing incomes, cultural changes).

2. Seasonality – Short-term regular variations related to the calendar or time of day (e.g.,
restaurants, supermarkets, theaters).

3. Cycles – Wavelike variations lasting more than one year (e.g., economic, political, agricultural
conditions)
 4. Irregular Variations – Caused by unusual circumstances, not reflective of typical behavior,
and must be identified and removed, if possible (e.g., weather conditions, strikes, major change
in a product or service).

6. Random Variations – Residual variations after all other behaviors are accounted for (e.g.,
small “bumps” of random variability).

Note: A demand forecast should be based on a time series of past demand rather than unit sales since it
would not truly reflect demand if one or more stockouts occurred.

A. Naive Methods

A naive forecast uses a single previous value of a time series as the basis of a forecast. In simple
words, it is a forecast for any period that equals the previous period’s actual value. This approach can be
used with any of the following:

1. Stable Series – The last data point becomes the forecast for the next period (i.e., a demand of
20 cases last week means a forecast of 20 cases this week).

2. Seasonal Variations – The forecast for this “season” is equal to the value of the series last
“season” (i.e., a forecast for demand for passes to Tokyo Disneyland this summer is equal to the
demand for passes last summer).

3. Trend – The forecast is equal to the last value of the series plus or minus the difference
between the last two values of the series (i.e., having the last two values of 50 and 53, the next
value would be 56 from the sum of the difference and last value, 3 and 53, respectively).

It may appear too simplistic at first glance but it is nonetheless a legitimate forecasting tool.
Advantages of it may be considered: a) Has virtually no cost; b) quick and easy to prepare; and c) easily
understandable. The method’s inability to provide highly accurate forecasts is its main objection.

Note: The accuracy of a naive forecast can serve as a standard of comparison against which to judge the
cost and accuracy of other techniques for a manager must think if the increased accuracy is worthy of
resources required for it.

B. Techniques for Averaging

Historical data typically contain a certain amount of random variation (white noise) that tends to
obscure systematic movements in the data. Averaging techniques smooth the variations in the data or
randomness due to relatively unimportant factors which can’t be reliably predicted. To completely
remove any randomness is ideal as it is usually impossible to distinguish which is which between two
kinds of variations. Practically, small variations are random while the large variations are “real”.

As compared to the original data, a forecast based on an average tends to exhibit less variability
because the individual highs and lows in the data offset each other when they are combined. It’s
advantageous since movements merely reflect random variability rather than true change in the series
and response to these changes usually entails considerable cost which makes it desirable to avoid
reactions these minor changes.

These techniques generate forecasts that reflect recent values of a time series. While they also
can handle step changes or gradual changes in the level of the series, these techniques work best when a
series tends to vary around an average. There are three techniques for averaging, namely:
1. Moving Average – A forecast that uses a number of the most recent actual data values in
generating a forecast. It averages a number of recent actual values, updated as new values
become available. Equation to be used would be:

∑𝑛𝑖=1 𝐴𝑡 − 1 𝐴𝑡 − 𝑛 + … + 𝐴𝑡 − 2 + 𝐴𝑡 − 1
𝐹𝑡 = MA𝑛 = =
𝑛 𝑛
Where: 𝐹𝑡 = Forecast for time period t

MA𝑛 = n period moving average

𝐴𝑡 − 𝑖 = Actual value in period t – 1

n = Number of periods (data points) in moving average

Sample Problem: Compute a three-period moving average forecast given demands for
shopping carts for the last five periods.

Period Demand

1 42 Solution:

2 40 43+40+41
F6 = = 41.33
3
3 43

4 40 the 3 most recent demands

5 41

If actual demand in period 6 turns out to be 38, the moving average forecast for period 7
40+41+38
would be: F7 = = 39.67
3

Note: The forecast is updated by adding the newest value and dropping the oldest and
then recomputing the average as each new actual value becomes available. Subtract the
oldest value from the newest value and add that amount to the moving total for each
update.

The moving average forecast lags the actual values but the forecasted values are smooth
as compared with the actual values. The moving average can incorporate as many data points as
desired and the decision maker’s selection of number of periods to include must take into
account its sensitivity to each new data point. The fewer the data points in an average, the more
sensitive (responsive) the average tends to be which could be helpful if responsiveness is
important, even to random variations. Conversely, more data points will result to a smoother one
but less responsive to “real” changes.

The advantages of a moving average forecast are that it is easy to compute and easy to
understand while its disadvantage is that all values in the average are weighed equally.

Note: Decreasing the number of values in the average increases the weight of more recent values
but loses the potential information from less recent values.

2. Weighted Moving Average – A weighted average is similar to a moving average but assigns
more weight to the most recent values in a time series. The most recent value might be assigned
a weight of .40, the next most recent value a weight of .30, the next after that a weight of .20, and
the next after that a weight of .10 which must sum to 1.00 with the heaviest weight to the most
recent values. In general:

Ft = WnAt - n + Wn - 1At - (n - 1) + W1At - n

Sample Problem:

Period Demand Given the following data,

1 42 a. Compute a weighted average forecast

2 40 using a weight of .40 for the most

3 43 recent period, .30 for the next most

4 40 recent, .20 for the next, and .10 for the

5 41 next.

b. If the actual demand for period 6 is 39, forecast demand for period 7 using the same

weights as in part a.

Solution: a. F6 = .10(40) + .20(43) + .30(40) + .40(41) = 41.0

b. F7 = .10(43) + .20(40) + .30(41) + .40(39) = 41.2

Note: If four weights are used, only the four most recent demands are used to prepare the
forecast

Its advantage over a simple moving average is that the weighted average is more
reflective of the most recent occurrences but the choice of weights is arbitrary and involves trial
and error to find a suitable weighting scheme.

3. Exponential Smoothing – Exponential smoothing is a sophisticated weighted averaging

method that is still relatively easy to use and understand. It is based on the previous forecast plus
a percentage of the difference between that forecast and the actual value of the series at that
point. In other words:

Next Forecast = Previous Forecast + ɑ(Actual – Previous Forecast)

where (Actual – Previous Forecast) represents the forecast error and ɑ is a percentage of
the error. In equation form:

Ft = Ft – 1 + ɑ(At - 1 – Ft – 1) (3-2a)

Where: Ft = Forecast for period t

Ft – 1 = Forecast for the previous period (i.e., period t – 1)

ɑ = Smoothing constant

At – 1 = Actual demand or sales for the previous period

The smoothing constant ɑ represents a percentage of the forecast error. Each new forecast
is equal to the previous forecast plus a percentage of the previous error.

Sample Problem: Suppose the previous forecast was 42 units, actual demand was 40
units, and ɑ = .10. What would be the new forecast?

Solution: Ft = 42 + .10(40 - 42) = 41.8

If the actual demand turns out to be 43, the next forecast would be:

Ft = 41.8 + .10(43 - 41.8) = 41.92

An alternate form of formula 3-2a reveals the weighting of the previous forecast and the
latest forecast actual demand:

Ft = (1 - ɑ)Ft – 1 + ɑAt – 1 (3-2b)

If ɑ = .10 and the constant given on the first example except ɑ, it will be:

Ft = .90(42) + .10(40) = 41.8

The quickness of forecast adjustment to error is determined by the smoothing constant, ɑ.

The closer its value is to zero, the slower the forecast will be to adjust to forecast errors and the
greater the smoothing. Conversely, the closer its value to 1.00, the greater the responsiveness and
the lesser the smoothing.
 Selecting a smoothing constant is basically a matter of judgement or trial and error and
the goal is to select a smoothing constant that balances the benefits of smoothing random
variations with the benefits of responding to real changes if and when they occur. Values of ɑ
ranging from .05 to .50 are commonly used where low values are used when the underlying
average tend to be stable while higher ones are used when the underlying average is susceptible
to change.

Partly because of its ease of calculation and partly because of the ease with which the
weighting scheme can be altered, exponential smoothing is one of the most widely used
techniques in forecasting.

Note: A number of different approaches can be used to obtain a starting forecast such as the
naive approach for simplicity and use of averaging, that provide better starting forecast because
that would tend to be more representative, in practice.

IV. References:

Books or online sources