FORECASTING

Forecasting is a statement about the future value of a variable such as demand. It is a basic
input in the decision process of operation management because they provide information on
future demand. The importance of forecasting to operations management cannot be overstated.
The primary goal of operations is too much supply to demand. Having a forecast to demand is
essential for determining how much capacity or supply will be needed to meet demand.

Forecast Two Important aspects:

1. Expected level of demand
 This can be a function of some structural variation, such as a trend or seasonal
variation.
2. The degree of accuracy that can be assign to a forecast
 Forecasts accuracy is a function of the ability of forecaster correctly model demand,
random variation, and sometimes unforeseen events.

Importance of Forecasting in the planning process:

 They enable managers to anticipate the future so they can plan accordingly.
Some examples of uses of forecasts in business organization:

 Accounting. New product/ process cost estimates, profit projections, cash management.
 Finance. Equipment/ equipment replacement needs, timing and amount of funding/
borrowing needs.
 Human resources. Hiring activities, including recruitment, interviewing, training, lay off
planning, including outplacement counselling.
 Marketing. Pricing and promotion, e-business strategies, global competition strategies.
 MIS. New/ revised information systems, Internet services.
 Operations. Schedules, capacity planning, work assignment and workloads, inventory
planning, make-or – buy decisions, outsourcing, and project management.
 Product/ service design. Revision of current features, design of new product or services.

Two uses of forecasts:

1. To help manager plan the system
 Planning the system generally involves long-range plans about the types of products
and services to offer, what facilities and equipment to have, where to locate, and so
on.
2. To help them plan the use of the system.
 Planning the use of the system refers to short- range and intermediate- range
planning, which involve tasks such as planning inventory and workplace levels,
planning purchasing and production, budgeting, and scheduling.

Features common to all forecasts

1. Forecasting techniques generally assumes that the same underlying causal system that
existed in the past will continue to exist in the future.
 2. Forecasts are not perfect; actual results usually differ from predicted values; the presence
of randomness precludes a perfect forecasts. Allowance should be made for forecast errors.
3. Forecasts for groups of items tend to be more accurate than forecasts for individual items
because forecasting errors among items in a group usually have a cancelling effect.
4. Forecasts accuracy decreases as the time period covered by the forecasts – the time
horizon- increases. Generally speaking, short range forecasts must contend with fewer
uncertainties than longer-range forecast, so they tend to be more accurate.

Elements of a good Forecasts:

A properly prepared forecast should fulfil certain requirements:

1. The forecast should be timely.

2. The forecast should be accurate, and the degree of accuracy should be stated.
3. The forecast should be reliable: it should work consistently.
4. The forecasts should be expressed in meaningful units.
5. The forecasts should be in writing.
6. The forecasts techniques should be simple to understand and use.
7. The forecasts should be cost- effective: the benefits should overweigh the cost.

Steps in forecasting Process:

1. Determine the purpose of the forecast.

2. Establish a time horizon.
3. Select forecasting technique.
4. Obtain, clean, and analyse appropriate data.
5. Make the forecasts.
6. Monitor the forecasts.

Two General Approaches to forecasting:

 Qualitative methods
 Consist mainly of subjective inputs, which often defy precise numerical description.
 Quantitative methods
 Involves either the projection of historical data or the development of associative
models that attempt to utilize causal (explanatory) variables to make a forecasts.

Accuracy and Control of Forecasts

Accuracy and control of forecasts is a vital aspect of forecasting. Thus, minimizing forecast
error is every forecasters objective. However, the complex nature of real-world variables makes it
almost impossible to correctly predict future values of those variables.

When making periodic forecasts, it is important to monitor forecast errors to determine if the
errors are within reasonable bounds.

Forecast Error - difference between the actual value and the value that was predicted for a given
period.
 Hence, Error = Actual – Forecasts

Positive errors result when the forecast is too low, negative errors when the forecasts is too
high.

Summarizing Forecast accuracy

Forecast accuracy is a significant factor when deciding among forecasting alternatives.
Accuracy is based on the historical error performance of a forecast.

Three commonly used measures for summarizing historical errors are:

 Mean Absolute Deviation (MAD)

 The average absolute error
 Mean Squared Error (MSE)
 The average of squared errors.
 Mean Absolute Percent Error(MAPE)
 The Average absolute percent error.

Forecasting Techniques:

 Judgemental forecasts
 Rely 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 forecast
 Simply attempt to project past experience into the future. These techniques use
historical data with the assumption that the future will be like the past period.
 Associative models
 Use equation that consist of one more explanatory variables that can be used to
predict demand.

Forecast based on Judgement and Opinion:

 Executive opinions
 Salesforce opinions
 Consumer surveys
 Other approaches

Forecasts based on Time-series Data:

Time- series – is a time-ordered sequence of observations taken at regular intervals.
Forecasting techniques based on time-series data are made on the assumptions that future values
of the series can be estimated from past value.

Analysis of time-series data requires the analyst to identify the underlying behaviour of the
series. These behaviours can be described as follows:
  Trends
o Refers to a long-term upward or downward movement in the data.
 Seasonality
o Refers to a short term, fairly regular variations generally related to factors
such as the calendar or time of day.
 Cycles
o Are wavelike variations of more than one year’s duration.
 Irregular variations
o Caused by unusual circumstances, not reflective or typical behaviour.
 Random variations
o Are residual variations that remain after all other behaviors have been
accounted for.

Naïve forecasts
A simple way but widely used approach to forecasting is the naive approach. A naive forecast
uses a single previous value of a time series as the basis of a forecast.

The naive approach can be used in the following:

Stable series- the last data point becomes the forecast for the next period
Seasonal variations – forecast for the next “season” is equal to the value of the series last
“season”
Trend – forecast is equal to the last value of the series plus or minus the difference between
the last two values of the series.

Period Actual Change from previous value

Forecast
t- 1 50
t- 2 53 +3
(Next) t
53+3= 56

Techniques for Averaging

Averaging techniques smooth fluctuations in a time series because the individual high and
lows in the data offset each other when they are combined into an average. A forecast based on
the average thus tend to exhibit less variability than the original data.

Averaging techniques generate forecasts that reflect recent values of a time series (e.g.
the average value over the last several periods)

Three techniques for averaging are described as follows:

1. Moving average.
2. Weighted moving average.
3. Exponential smoothing.

Moving average
 - forecasts uses a number of the most recent actual data values in generating a
forecasts.

Formula:

Ft= MA =∑ⁿἱ= 1 ᴬt -ἱ = ᴬt-n + ᴬt -2 + ᴬt - 1

n n

Where:
Ft = forecast for time period t
MAn= n period moving average
At- 1 =Actual value in period t-1
n= number of periods (data points) in the moving average
For example, MA₃ would refer to a three-period moving average forecasts, and MA₃ would refer to
a five- period moving average forecasts.
Compute the three period moving average forecasts given demand for shopping carts for the last
five periods.

Period Demand
1 42
2 40
3 43
4 40 the 3 most recent demands
5 41

F₆= 43+40+41 = 41.33

3
If actual demand in period 6 turns out to be 38, the moving average forecast for period 7 would be

F₇ = 40+41+38 =39.67
3

Weighted average
is similar to a moving average, except that it assigns more weight to the most recent
values in a time series. For instancethe most recent value migth be assign a weight of 40, the
next most recent value a weight of 30, the next after that weight of 20, and the next after that
a weight of 10, . Note that the weights must sum to 1.00, and that the heaviest weight are
assign to the most recent values.

Ft = Wt (At) + Wt-1 (A1-1)+… + Wt- n(At-n)

Where
Wt= weight for the period t,Wt-1 = weigth for period t-1, etc.
At= actual value in period t, At-1= actual value for period t-1, etc.
Example:
a. Compute a weighted average forecast using a weight of .40 for the most recent
period ,.30for the next most recent, 2.0 for the next , and .10 for the next.
b. If the actual demand for period 6 is 39, forecast demand for period 7 using the same weigth
as in part a.
Period Demand
1 42
2 40
3 43
4 40
5 41

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

b. F₇ = .10 (43) + .20(40) +.30(41) +.40(39)=40.2

Exponential smoothing
is a sophisticated weighted averaging method that is still relatively easy to use and
understand. Each new forecast is based on the previous forecasts plus a percentage of the
difference between the forecasts and the actual value of the series at that point. That is:

Next forecast = previous forecasts + α(actual- previous)

Where (actual- previous forecasts) represent the forecasts error and αis a percentage of the
error. More concisely,
Ft = Ft-1 + α(At-1 – Ft-1)
Where:
Ft = forecasts for period t
Ft -1 = forecast for the previous period (i.e, period t- 1)
α= smoothing constant
At-1 = actual demand or sales for the previous period

The smoothing constant a represent a percentage of the forecasts error. Each new
forecasts is equal to the previous forecasts plus a percentage of the previous error. For example,
suppose the previous forecasts was 42 units, actual demand was 40 units, and α =.10. the new
forecsts would be computed as follows:

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

Then, if the actual demand turns out to be 43, the next forecasts would be
Ft = 41.8 + .10 (43-41.8) = 41.92