Week 5 Discussion

Forecasting

One common use of organizational data is the creation of forecasts of future demand from information about prior demand. For example,

if a shoe manufacturer has seen demand surge by 35% in each of the last four Augusts, due to parents purchasing new shoes for their

children to wear at the beginning of the school year, then the company may predict that demand for the coming August will surge by 35%.

While there is no guarantee that the future will be like the past, there are many environments in which the future does behave like the past.

The use of historical demand data to forecast future demand is accomplished through a set of techniques known as time series

forecasting. Time series forecasts tend to recognize and exploit four different properties that can be seen by looking at historical demand

data. These four properties are seasonality, cyclicality, trend, and irregular patterns.

Time series models can be either additive or multiplicative. In additive models, each component of the model is simply added to all of the

other components of the model, treating each component as if it independent of all other models. In multiplicative models, all factors are multiplied by one another, meaning that each component impacts and is impacted by all of the other factors in the model.

There are three basic trend models that attempt to exploit patterns identi�ed in past demand data. These three models are known as the

linear trend model, the exponential trend model, and the quadratic trend model.

The success of any business depends on its future estimates. On the basis of these estimates, a businessperson plans for things such as

production, sales, and the additional funds involved in those things. Forecasting is a method of foretelling the course of business activity

based on the analysis of past and present data.

Additional Materials

View a Pdf Transcript of  Forecasting Methods  (media/week5/SUO_BUS3059%20W5%20L2%20Forecasting%20Methods.pdf?

_&d2lSessionVal=413TjsBLZG4ot5goGhUoGZTkm&ou=84108) 