FORECASTING DEMAND
LESSON 4
FORECASTING
Forecast is a statement about the future value of a variable of
interest.
Forecasting is a technique that uses historical data as inputs to
make informed estimates that are predictive in determining the
direction of future trends.
2 IMPORTANT ASPECTS OF FORECASTS
Expected level of demand.
The level of demand may be a function of some structural variation
such as trend or seasonal variation.
Degree of accuracy.
Related to the potential size of forecast error.
FEATURES COMMON TO ALL FORECASTS
1. Techniques assume some underlying causal system that existed in the
past will persist into the future.
2. Forecasts are not perfect.
3. Forecasts for groups of items are more accurate than those for individual
items.
4. Forecast accuracy decreases as the forecasting horizon increases
ELEMENTS OF A GOOD FORECAST
Timely – a certain amount of time is needed to respond to the information contained in a
forecast.
Accurate - any forecasting needs to be as accurate and researched as possible.
Reliable - method should consistently provide a good forecast
Expressed in meaningful units - forecasts that are overly complicated tend not to instill a lot
of confidence in users.
In writing - The forecast needs to be in a unit of measurement that is the most meaningful to
whoever will be using it.
Technique should be simple to understand and use
Cost effective - The cost of making the forecast should not outweigh the benefits obtained
from the forecast.
6 STEPS IN FORECASTING PROCESS
3. Select a forecasting technique
1. Determine the purpose of the forecast
4. Obtain, clean, and analyze appropriate
2. 2. Establish a time horizon
data
Time Horizons 5. Make the forecast
Forecasting Short-Term Demand
6. Monitor the forecast
Forecasting Medium-Term Demand
Forecasting Long-Term Demand
FORECASTING APPROCHES
QUALITATIVE APPROACH QUANTITATIVE APPROACH
Techniques involve either the
Techniques permit the
projection of historical data or the
inclusion of soft information
development of associative
These factors are difficult, or methods that attempt to use causal
impossible, to quantify variables to make a forecast
These techniques rely on hard data
FORECASTING METHODS
JUDGEMENTAL FORECASTING
TIME-SERIES FORECASTING METHOD
METHOD
Forecasts that project patterns identified in recent
Forecasts that use subjective inputs such as
time-series observations
opinions from
– Executive opinions
Time-series - a time-ordered sequence of
– Salesforce opinions
observations taken at regular time intervals
– Consumer surveys
– Delphi method Assume that future values of the time-series can be
estimated from past values of the time series
OTHER FORECASTING METHODS
Focus Diffusion
– “best current performance” – Historical data on which to base a forecast are
not available for new products
• Apply several forecasting methods
• Predictions are based on rates of product
to the last several periods of historical
adoption and usage spread from other
data established products
• The method with the highest • Take into account facts such as
accuracy is used to make the forecast
– Market potential
for the following period
– Attention from mass media
– Word-of-mouth
TIME-SERIES BEHAVIORS
TREND SEASONALITY
– A long-term upward or downward – Short-term, fairly regular variations
movement in data related to the calendar or time of day
• Population shifts
• Changing income
TIME-SERIES BEHAVIORS
CYCLES VARIATION
Random Variation – Residual variation that remains
after all other behaviors have been accounted for
– Wavelike variations lasting more than one year
Irregular variation – Due to unusual circumstances
• These are often related to a variety of economic,
that do not reflect typical behavior
political, or even agricultural conditions
• Labor strike
• Weather event
TIME-SERIES FORCASTING
Naïve Forecast Averaging
– Uses a single previous value of a These techniques work best when a
time series as the basis for a forecast series tends to vary about an
• The forecast for a time period is average
equal to the previous time period’s Averaging techniques smooth
value variations in the data
They can handle step changes or
gradual changes in the level of a
series
USING FORECAST INFORMATION
Reactive approach
– View forecasts as probable future demand
– React to meet that demand
Proactive approach
– Seeks to actively influence demand
Advertising
Pricing
Product/service modifications
