SUPCH 3

Forecasting

Predicting future demand based on past demand information.

Uncertainty

The difference between the amount of information required and the amount already possessed by the organization.

Quantitative methods

Forecasting methods that rely on quantitative data and analytical techniques.

Qualitative methods

Forecasting methods based on subjective opinions from one or more experts.

Time series

A variable that is measured over time in sequential order to detect patterns for forecasting future values.

Simple Moving Average (SMA)

Forecasting method using the average of a set of past observations over a specified period.

Weighted Moving Average (WMA)

Forecasting method that gives different weights to past observations, depending on their significance.

Exponential Smoothing

A forecasting technique that uses a smoothing constant to react to changes in the demand.

Mean Absolute Deviation (MAD)

The average absolute error in the forecast, used to measure accuracy of forecasting methods.

Trend

A long-term relatively smooth pattern or direction that persists usually for more than one year.

Seasonal variation

A short-term, calendar repetitive behavior present within a time series.

Cyclical variation

A wavelike pattern describing long-term behavior within a time series.

Random variation

Irregular, unpredictable changes in a time series that can obscure more predictable components.

Forecast error

The difference between actual values and forecasted values.

Dependent variable

The output variable in a regression model that is being predicted or explained.

Independent variable

The input variable in a regression model that is used to predict the dependent variable.

R-squared (R²)

A statistical measure that represents the goodness of fit of the estimated linear model.

Forecast parameter (α)

A coefficient that determines how much weight is given to the most recent actual demand in exponential smoothing.