FORECASTING

Forecasting is the art and science of predicting future events. Until the last decade, forecasting
was largely and art, but it has become a science as well.
Forecasting is one input to all types of business planning and control, both inside and outside
the operations functions.
Forecasting time horizon: Short range – will refer to less than six months.
Medium range – is defined from six months to two years.
Long range - will mean two years or more into the future.

Forecasting plays a pivotal role in the operations of modern management. It is an important

and necessary aid to planning and planning is the backbone of effective operations.

METHODS OF FORECASTING
Qualitative forecasting methods:
Qualitative forecasting methods utilize managerial judgment, experience, relevant data, and an
implicit mathematical model.
Qualitative forecasting forecast should be used when past data are not reliable indicators of
future conditions.

TYPES OF QUALITATIVE FORECASTING

1. Delphi method: Forecast developed by a panel of experts a series of questions on successive

rounds. Anonymous responses of the panel are fed back on each round to all participants.
Three to six rounds may be used to obtain convergence of the forecast.
2. Market surveys: Panels, questionnaires, test markets, or used t gather data on market
conditions.
3. Life-cycles analogy: Prediction based on the introduction, growth, and maturity phases of
similar products. Uses the S. shaped sales growth curve.
4. Informed Judgment: Forecast may be made by a group of or an individual on the basis of
experience, hunches or facts about the situation. No rigorous method is used.

Quantitative forecasting methods:

Qualitative forecasting methods: utilize underlying mathematical model to arrive at a forecast.
The basic assumption for all the quantitative method is that past data and data patterns are
reliable predictors of the future.
TYPES OF QUANTITATIVE FORECASTING

1. Moving Averages: Forecast is based on arithmetic average or weighted average of a given

number of past data points.

At= Dt + Dt-1…+Dt-N+1/N F= sum of n demands/n

At= Average computed through period

Dt=Demand during period t
t= time
N=number of periods

Example: Demand forecasting (Moving Average)

The demand for an Item is observed for 8 months and recorded below:
Calculate 3 monthly moving average.
What is the forecast for month 8?

Month Demand 3 monthly moving

average
1 280
2 288
3 266
4 295 278
5 302 283
6 310 287.7
7 303 302.3
8 305

F8= (302+310+303)/3 = 305

One way to make moving average respond more rapidly to changes in demand is to place
relatively more weight on recent demands than on earlier ones.
This is called weighted moving average.

n
At=W1Dt+W2Dt-1+…+W2Dt-N+1 Condition: ∑ Wi=1
i=1
Example: Demand forecasting (Weighted Moving Average)
Forecast sales using 4-week weighted moving average with weights 0.4, 0.3, 0.2, and 0.1

WEEK DEMAND 4WMA

1 39
2 44
3 40
4 45
5 38 42.7
6 43 41.1
7 39 41.6
8 40.6

F5=.4 (45) + 0.3 (40) + .02 (44)+.01 (39) = 42.7

F6=.4 (38) + 0.3 (45) + .02 (40)+.01 (44) = 41.1
F7=.4 (43) + 0.3 (38) + .02 (45)+.01 (40) = 41.6
F8=.4 (39) + 0.3 (43) + .02 (38)+.01 (45) = 40.6

2. Exponential smoothing – is based on the very simple idea that a new average can be
computed from an old average and the most recent observed demand.
(0 ≤ α ≤ 1).
3. Mathematical models: A linear or nonlinear model fitted to time- series data, usually by
regression methods. Includes trend lines, polynomials, log linear, etc.
Uses: Same as moving average but limited due to expenses, to a few products.
4. Box Jenkins- Autocorrelation methods: Autocorrelation methods used to identify time series
and to fit the best model . Requires about 60 past data points.

Causal forecasting Method

Causal forecasting methods develop a cause and effect model demand and other variables.
Example: The demand for ice cream may be related to population, the average summer
temperature, and time.

One of the most important features of causal models is that they are used to predict turning
points in the demand function. In contrast, time series model can be used only to predict the
future demand pattern on the basis of the past. They cannot predict upturns and downturns
In the demand level.
Causal models therefore are more widely used for facility and process planning.

SELECTING A FORECASTING METHOD

The most important factors in selecting a model:

1. User and system sophistication. – How sophisticated are the managers, inside and outside of
operations, who expected to use the forecasting results? It has been found out that the
forecasting method must be matched the knowledge and sophistication of the user.
2. Time and resources available: The selection of a forecasting method will depend on the time
available in which to collect data and prepare the forecast. This may involve the time of the
users, forecasters, and data collectors.
3. Use or decision characteristics. The forecasting method be related to the use or decisions
required. The use, in turn, is closely related to characteristics such as accuracy required, time-
horizon of the forecast, and the number of items to be forecast.
4. Data availability: The choice of forecasting method is often constrained by available data. The
quality of data available is also concern. Poor data lead to poor forecasts. Data should be
checked for extraneous factors or unusual points.
5. Data pattern: The data pattern in the data will affect the type of forecasting method selected. If
the time series is flat, a first order method cab be used. However, if the data show trends or
seasonal patterns, more advanced method will be needed.
 COLLABORATIVE PLANNING, FOREACASTING, AND REPLENISHMENT
Collaborative planning, forecasting, and replenishment (CPFR) is a relatively new approach aimed at
achieving more accurate forecasts. The basic idea is to share information between customers and
suppliers in the supply chain during planning and forecasting process.

Example: A customer may have information on future planned sales promotion or inventory
adjustments that are not known the supplier. In this case a forecast based on the time series data alone
by the supplier would be inaccurate, but it could be adjusted if the customer information made
Available.

Example Illustration :
Done by the seller

Done by the buyer

The Important points to remember about CPFR.
1. All parties must be willing to share sensitive information about demand data, future sales
promotion, potential orders, new products, lead times, and so forth. Assurances must be
provided that the competitors will not have an access to sensitive information.
2. A long- term collaborative relationship that is mutually beneficial is needed .This will require an
atmosphere of trust and ongoing management attention.
3. Sufficient time and resources must be provided for CPFR to succeed. In other words, there is a
cost to receive the benefits of CPRF.