CHAPTER 14: FORECASTING

What is Forecasting

- Vital to every business organization and for every significant management decision
- The basis of corporate planning and control

Purpose of Forecasting in different functional areas

finance and accounting -Provide the basis for budgetary planning and cost control

marketing - Help them to plan new products, compensate sales personnel and make other key
decisions based on their sales forecasting

production and operations -aid them to make periodic decisions involving supplier selection,
process selection, capacity planning, and facility layout, as well as for continual decisions about
purchasing, production planning, scheduling and inventory

2 Forecasting Approach

-In considering what forecasting approach to use, we must consider the purpose of the forecast.

1. Strategic Forecasts
-medium- and long-term forecasts that are used for decisions related to strategy and aggregate
demand (used to help set the strategy of how, in aggregate sense, we will the demand)
- for very high-level demand analysis
Example: What do we expect the demand to be a group of products over the next year?

2. Tactical Forecasts
- Short term forecasts used for making day-to day decisions related to meeting demand
- Its goal is to estimate the demand in the relatively short term (few weeks/months)
- Ensure that in the short term we are able to meet customer lead time expectations and
other criteria related to the availability of the products or services

Example: When should the inventory for an item be replenished?

How much production should we schedule for an item next week?

(NOT SURE IF NEED PA ISAMA UNG DECOUPLING POINTS)

What is Demand? - A need for a particular product or component. The demand could come from any
numbers of sources (e.g., customer order or forecast, an interplant environment, a branch warehouse
request for a service part or the manufacturing of another product)

Component of Demands

1. Average demand for the period

2. Trend
3. Seasonal element
4. Cyclical elements – are more difficult to determine because the time span may be unknown or
the cause of the cycle may not be considered
- It may come from in occurrences such as political elections, war, economic conditions,
or sociological pressures
5. Random variation – cause by chance events
- Statistically, when all the known causes for demand (average, trend, seasonal, cyclical,
and autocorrelation) are subtracted from total demand, what it remains is the
unexplained portion of demand. If we cannot identify the cause of this remainder, it is
assumed to be purely random chance.
6. Autocorrelation – denotes the persistence of occurrence.
- Specifically, the value expected at any point is highly correlated with its own past values.
In waiting line theory, the length of a waiting line is highly correlated. That is, if a line is
relatively long at one time, then shortly after than time, we would expect the line still to
be long

QUANTITATIVE FORECASTING MODELS – (Forecasting can be classified into Four Basic Types)

4 Basic Types of Forecasting: (Qualitative, Time Series Analysis, Causal Relationships and Simulation)

1. Qualitative- techniques are subjective or judge mental and are based on estimates and
opinions.

QUALITATIVE TECHNIQUES IN FORECASTING

1. Market Research – sets out to collect data in a variety of ways (surveys, interviews, and
so on) to test hypothesis about the market. This is typically used to forecast long-range
and new product sales

The Gilmore Research Group – one of the firms that offer marketers software or databases to help them
more accurately forecast sales from specific market areas, products or segment. (insert the hindsight
pictures)

2. Panel Consensus- free open exchange at meetings. The idea is that discussion by the
group will produce better forecasts than any one individual. Participants maybe
executives, salespeople, or customers.
-
3. Historical Analogy- Ties what is being forecast to a similar item. Important in planning
new products where forecast may be derived by using the history of a similar product

4. Delphi Method- Group of experts responds to questionnaire. A moderator compiles

results and formulates a new questionnaire that is submitted to the group. Thus, there is
a learning process for the group as it receives new information and there is no influence
of group pressure or dominating individuals.

2. Time Series Analysis- is based in the idea that data relating to past demand can be used
to predict future demand. (Past Data may include several components, such as trend,
seasonal, or cyclical influences, and are described in the following section)
Example: Sales figures collected for the past six weeks can be used to forecast sales for
the seventh week. Quarterly sales figures collected for the past several years can be
used to forecast future quarters.

Simple Moving Average – A time period containing a number of data points is averaged
by dividing the sum of the point values by the number of points. Each, therefore, has
equal influence.
Definition- a forecast in which the average is taken over a period which changes
over time
Application- works well in stable condition
Formula:
Advantages: - random fluctuations are cancelled
-discard irrelevant past data
Disadvantages: - experimentation needed to identify variable
-does not compensate for seasonalities
-responds to trends with a delay
Weighted Moving Average – Specific points may be weighted more or less than the
others, as seen fit by experience.
Definition- forecast by assigning weights to the actual past demand data
Application- significant trend and erratic demand
Formula:
Advantages: - responds more rapidly to changes in demand
-most recent data emphasized
-responds well to erratic demand
-can handle seasonality
Disadvantages: - may over respond to seasonalities especially for short seasonal
periods

Exponential Smoothing- Recent data points are weighted more with declining
exponentially as date become older.
Definition- forecast based on a weighted sum of part observations; weights
depend on so called smoothing parametersa
 Application- appropriate for a series that move randomly above and below a
constant term
Formula:

3. Causal Relationships- (discussed using the linear regression technique)- assumes that
demand is related to some underlying factor or factors in the environment.
- Tries to understand the system underlying and surrounding the item being forecast.
Example: Sales may be affected by advertising, quality and competitors.

Linear Regression Analysis

Regression – defined as a functional relationship between two or more
correlated variables. It is used to predict one variable given the other
- similar to least squares method in time series but many contain multiple variables.
Basis is that forecast is caused by the occurrence of other events.

Multiple Regression Analysis

-in this analysis, a number of variables are considered, together with the effects of each
on the item of interest.
Example: In the home furnishings field, the effects of the number of marriages, housing
starts, disposable income, and the trend can be expressed in a multiple regression—A
equation

4. Simulation- (allow the forecaster to run through a range of assumptions about the
condition of the forecast.)
- Dynamic models, usually computer-based, that allow the forecaster to make
assumptions about the internal variables and external environment in the model.
- Depending on the variables in the model, the forecaster may ask such questions:
What would happen to my forecast if price increased by 10 %?
What effect would a mild national recession have on my forecasts?

FORECAST ERRORS

Forecast Errors – the difference between what actually occurred and what was forecast. In statistics,
these errors are called “residuals”.

Demand for product is generated through the interaction of a number of factors too complex to
describe accurately in a model. Therefore, all forecasts certainly contain some error.

Sources of Errors – errors can come from a variety of sources.

Common Source: many forecasters are unaware of its projecting past trends into future.

Example: When we talk about statistical errors in regression analysis, we are referring to the
deviation of observations from our regression line. It is common to attach a confidence band (that as
statistical control limits) to the regression line to reduce the unexplained error. But we then use this
regression line as a forecasting device by projecting it into the future, the error may not be correctly
defined by the projected confidence band. This is because the confidence interval is based on past data;
it may not hold for projected data points and therefore cannot be used with the same confidence. In
fact, we experience has shown that the actual errors tend to be greater than those predicted from
forecast models.

Classification of Errors:

1. Bias Errors – occur when a consistent mistake is made.

Sources: the failure to include the right variables
the use of the wrong relationship among variables
a mistaken shift in the seasonal demand from where it normally occurs
the existence of some undetected secular trend
2. Random Errors- can be defined as those that cannot be explained by the forecast model
being used.

Measurement of Errors

Three Common Terms used to describe the degree of error:

1. Standard Error - the square root of a function

2. Mean Squared Error (Variance)- tells you how close a regression line is to a set of points. It does
this by taking the distances from the points to the regression line (these distances are the
“errors”) and squaring them. The squaring is necessary to remove any negative signs. It also
gives more weight to larger differences. It’s called the mean squared error as you’re finding the
average of a set of errors.
3. Mean absolute deviation- Expresses accuracy in the same units as the data, which helps
conceptualize the amount of error
-The MAD is a good statistic to use when analyzing the error for a single item. However, if you
aggregate MADs over multiple items you need to be careful about high-volume products
dominating the results

WEB BASED FORECASTING: COLLABORATIVE PLANNING, FORECASTING AND REPLENISHMENT (CPFR)

Collaborative Planning, Forecasting and Replenishment (CPFR) – an internet tool to coordinate

forecasting, production and purchasing in a firm’s supply chain.

- Being used as a means of integrating all members of an n-tiers supply chain, including
manufacturers, distributors, and retailers.
(Exhibit 18.17)

Objectives: To exchange selected internal information on a shared web server in order to provide for
reliable, long term future views of demand in the supply chain.

STEPS IN CPFR

Step 1: Creation of a front-end partnership agreement

Step 2: Joint business planning

Step 3: Development of demand forecasts

Step 4: Sharing forecasts

Step 5: Inventory replenishment