Thursday, December 14

Math 540 – Quantitative Methods Professor: Subhashis Nandy Forecasting Methods

Google+ Pinterest LinkedIn Tumblr +

Robert Lyles

MATH 540 – Quantitative Methods

Professor: Subhashis Nandy

Forecasting Methods

Lecture Outline

§Strategic Role of Forecasting in Supply Chain Management and TQM

§Components of Forecasting Demand

§Time Series Methods

§Forecast Accuracy

§Regression Methods

Forecasting Components

§Short-range Forecast

§Encompasses the immediate future and are concerned with the daily operations of a business firm.

§Medium-range Forecast

§Encompasses anywhere from 1-2 months to 1 year.

§Long-range Forecast

§Encompasses a period longer than 1-2 years.

Forms of Forecast Movement


§a gradual, long-term up or down movement of demand

§Random variations

§movements in demand that do not follow a pattern


§an up-and-down repetitive movement in demand

§Seasonal pattern

§an up-and-down repetitive movement in demand occurring periodically

Forms of Forecast Movement

Forecasting Methods


§use management judgment, expertise, and opinion to predict future demand

§Time series

§statistical techniques that use historical demand data to predict future demand

§Regression methods

§attempt to develop a mathematical relationship between demand and factors that cause its behavior

Forecasting Process

Time Series

§Assume that what has occurred in the past will continue to occur in the future

§Relate the forecast to only one factor – time


§Moving Average

§Exponential Smoothing

§Linear Trend Line

Moving Average

Good for stable demand with no pronounced behavioral patterns.

Exponential Smoothing

This is an averaging method that weights the most recent past data more strongly than more distant past data.

Effect of Smoothing Constant

Adjusted Exponential Smoothing

Linear Trend Line

Seasonal Adjustments

Forecast Accuracy

§Forecast error

§difference between forecast and actual demand


§mean absolute deviation


§mean absolute percent deviation

§Cumulative error

§Average error or bias

Mean Absolute Deviation (MAD)

Other Accuracy Measures

Comparison of Forecasts

Linear Regression

Correlation and Coefficient of Determination

Multiple Regression









About Author

Leave A Reply