Om 301 Chapter 4

Front 1

forecasting

Back 1

the art and science of predicting future events

Front 2

economic forecasts

Back 2

planning indicators that are valuable in helping organizations prepare medium-to long-range forecasts

Front 3

technological forecasts

Back 3

long-term forecasts concerned with the rates of technological progress

Front 4

demand forecasts

Back 4

projection of a company's sales for each time period in the planning horizon

Front 5

the forecast is the only estimate of demand until actual demand becomes known.

Back 5

forecasts of demand drive decisions in many areas, including: human resources, capacity, supply-chain management.

Front 6

forecasting follows seven basic steps:

Back 6

1 determine the use of the forecast 2 select the items to be forecasted 3 determine the time horizon of the forecast 4 select the forecasting model(s) 5 gather the data needed to make the forecast 6 make the forecast 7 validate and implement the results

Front 7

forecasting approaches are:

Back 7

quantitative forecasts, qualitative forecasts, jury of executive opinion, delphi method, sales force composite, consumer market survey, time series

Front 8

quantitative forecasts

Back 8

forecasts that employ mathematical modeling to forecast demand

Front 9

qualitative forecast

Back 9

forecasts that incorporate such factors as the decision maker's intuition, emotions, personal experiences, and value system

Front 10

jury of executive opinion

Back 10

takes the opinion of a small group of high-level managers and results in a group estimate of demand

Front 11

delphi method

Back 11

uses an interactive group process that allows experts to make forecasts

Front 12

sales force composite

Back 12

based on salesperson' estimates of expected sales

Front 13

consumer market survey

Back 13

solicits input from customers or potential customers regarding future purchasing plans

Front 14

time series

Back 14

uses a series of past data points to make a forecast

Front 15

a time series has four components

Back 15

1 trend 2 seasonality 3 cycles 4 random variations

Front 16

naive approach

Back 16

simplest time series approach that assumes that demand in the next period is equal to demand in the most recent period

Front 17

moving averages

Back 17

time-series forecasting that uses an average of the most recent periods (n) of data to forecast the next period

Front 18

moving average=

Back 18

sum(demand in previous periods (n))
----------------------------------------------------
n (periods)

Front 19

weighted moving average

Back 19

sum(weight for period n)(demand in period n)
--------------------------------------------------
sum(weights)

Front 20

exponential smoothing

Back 20

time-series forecasting, a weighted-moving-average forecasting technique which data points are weighted by an exponential function

Front 21

smoothing constant

Back 21

time-series forecasting approach, weighting factor, alpha, used in an exponential smoothing forecast (alpha is a number between 0 and 1)

Front 22

exponential smoothing formula

Back 22

Ft = Ft-1 + alpha(At-1 - Ft-1)

Front 23

F1

Back 23

new forecast

Front 24

Ft-1

Back 24

previous period's forecast

Front 25

alpha

Back 25

smoothing (or weighting) constant (a number between 0 and 1)

Front 26

At-1

Back 26

previous period's actual demand

Front 27

mean absolute deviation (MAD)

Back 27

time-series forecasting, a measure of the overall forecast error for a model

Front 28

MAD formula

Back 28

Sum[Actual - Forecast]
------------------------------------
n

Front 29

Mean squared error (MSE)

Back 29

time-series forecasting, the average of the squared differences between the forecast and observed values

Front 30

MSE formula

Back 30

Sum(Forecast errors)^2
-----------------------------------
n

Front 31

Mean absolute percent error (MAPE)

Back 31

time-series forecasting, the average of the absolute differences between the forecast and actual values, expressed as a percentage of actual values

Front 32

Mean absolute percent error formula

Back 32

Sum100[Actualt - Forecastt]/Actualt
------------------------------------------------------
n

Front 33

exponential smoothing with trend adjustment

Back 33

forecast including trend (FITt) = Exponentially smoothed forecast (Ft) + Exponentially smoothed trend (Tt)

Front 34

Trend projection

Back 34

a time-series forecasting method that fits a trend line to a series of historical data points and then projects the line into the future for forecasts

Front 35

trend projection and regression analysis

Back 35

yhat = a + bx,
where b = Sumxy - n(xbar)(ybar)
-------------------------------
Sumx^2 - n(xba)r^2
where a = ybar - b(xbar)

Front 36

yhat

Back 36

computed value of the variable to be predicted (called the dependent variable)

Front 37

a

Back 37

y-axis intercept

Front 38

b

Back 38

slope of the regression line (or the rate of change in y for given changes in x)

Front 39

x

Back 39

the independent variable (which in this case is time)

Front 40

seasonal variations

Back 40

regular upward or downward movements in a time series that tie to recurring events

Front 41

cycles

Back 41

patterns in the data that occur every several years

Front 42

Unlike time-series forecasting, associative forecasting models usually....

Back 42

consider several variables that are related to the quantity being predicted. Once these variables have been found, a statistical model is built and used to forecast the item of interest. More powerful than a time-series method that use only the historical values for the forecasted value

Front 43

linear-regression analysis

Back 43

associative forecasting method, a straight-line mathematical model to describe the functional relationships between independent and dependent variables

Front 44

standard error of the estimate

Back 44

associative forecasting method, a measure of variability around the regression line

Front 45

coefficient of correlation

Back 45

associative forecasting method, a measure of the strength of the relationship between two variables

Front 46

coefficient of determination

Back 46

associative forecasting method, a measure of the amount of variation in the dependent variable about its mean that is explained by the regression equation

Front 47

multiple regression

Back 47

associative forecasting method with > 1 independent variable

Front 48

Multiple regression forecast

Back 48

yhat = a + b1x1 + b2x2

*yhat is the dependent variables, sales
*a is a constant, the y intercept
*x1 and x2 are the values of the two independent variables
*b1 and b2 are the coefficients for the two independent variables

Front 49

tracking signal

Back 49

monitoring and controlling forecast, a measurement of how well the forecast is predicting actual values

Front 50

tracking signal formula

Back 50

Sum(Actual demand in period i - Forecast demand in period i)
--------------------------------------------------
MAD

Front 51

Bias

Back 51

monitoring and controlling forecast that is consistently higher or lower than actual values of a time series

Front 52

adaptive smoothing

Back 52

monitoring and controlling forecast approach to exponential smoothing forecasting in which the smoothing constant is automatically changed to keep errors to a minimum

Front 53

focus forecasting

Back 53

monitoring and controlling forecasting that tries a variety of computer models and selects the best one for a particular application

Front 54

service-sector forecasting may require good short-term demand records, even per 15 minute intervals.

Back 54

demand during holidays or specific weather events may also need to be tracked.