Forecasting

Forecast

a basic input in decision process of operations management bcs they provide info on future demand

an estimate about future value of a variable such as demand

1. expected level of demand

2. degree of accuracy

2 important aspects of forecasts

Expected Level of Demand

can be a function of trend/seasonal variation

Degree of Accuracy

ability of forecasters to correclty model demand, random variation, and unforeseen events

• what existed in the past will continue to exist in the future

• forecasts are not perfect

• forecasts for groups tend to be more accurate vs indiv items

• forecast accuracy decreases as time horizon increases

common features to all forecasts

- timely

- reliable

- accurate

- meaningful

- written

- easy to use

elements of a good forecast

1. determine purpose

2. establish time horizon

3. select forecasting technique

4. gather & analyze data

5. make forecast

6. monitor forecast

steps in foercasting process

qualitative, quantitative

approaches to forecasting

Qualitative

consist mainly of subjective inputs which often defy precise numerical description

Quantitative

involves projection of numerical data or development of associative models that attempt to utilize casual variables

- judgemental

- time series

- associative models

types of forecasts

Judgemental

uses subjective inputs such as opinions from consumer surveys, sales staf, managers, exec, and experts

qualitative

A judgemental forecast is __________

• Consumer surveys

• Delphi method

• Executive opinions

• Sales force opinions

CDES

Time series

uses historical data that project patterns identified in recent time-series observations

quantitative

A time series forecast is __________

Associative models

uses explanatory variables to predict future demand

- naive

- simple moving average

- weighted moving average

- exponential smoothing

techniques for averaging forecasts

Naive

forecast for any period that equals the previous period's actual value

assumes demand in next period is same as demand in most recent period

Weighted average

more recent values in a series are given more weight in computing a forecast

Exponential smoothing

a weighted averaging method based on previous forecast plus a percentage of forecast error

Simple moving average

technique that averages a number of recent actual values, updated as new values become available