Class 5 Flashcards
Define Forecast
A statement about the future
Describe Naive Forecast with equation
forecast for any period equals the previous period’s actual value
F(t)=A(t-1)
Describe Moving Average Forecast with equation
Averages a number of recent actual values, updated as new values become available
Ft=∑Demand in previous n periods/n
Describe Exponential Smoothing Forecast
Weighted averaging method based on previous forecast plus a percentage of the forecast error
Describe Linear Trend
Identifying and projecting the trend
Describe Seasonal Relative
The proportion, by season, that seasonality will affect an underlying demand trend
What does MAD stand for? Describe with equation
Mean Absolute Error - Average absolute forecast error
MAD=∑[e]/n
What does MSE stand for? Describe with equation
Mean Squared Error - Average of sqaured forecast errors
MSE=∑e^2 /n
What does MAPE stand for? Describe with equation
Mean Absolute Percent Error - Average absolute value of forecast error relative to actual
MAPE=∑{([e]/A) x 100}/n
Describe Tracking Signal with equation
The ratio of the cumulative error to MAD
Tracking Signal = ∑(Actual - forecast)/MAD
Describe Control Chart
A visual tool for monitoring forecast errors
What are the 3 types of forecasts? include examples
1) Judgenmental - uses subjective inputs to improve the selection of historical data and/or associative variables
ex. executive opinions, sales force opinions, consumer surveys, historical analogies, expert opinion
2) Quantitative - uses historical data
ex. 6 patterns - level,trend, seasonality, cycle, irregular variation, random variation
3) Associative models - uses explanatory variables to predict the future
ex. economy, weather, technological change, demographic change, violence, war
6 patterns a time series can follow
1) level - little or gradual upwards/downwards movement
2) Trend - Long-term, consistent movement in data
3) Seasonality - Short-term regular variations in data
4) Cycle - Wavelike variations of more than one year’s duration
5) Irregular Variation - unusual, inconsistent
6) Random Variation - residual, unaccountable
3 principle measures of forecast accuracy
1) Forecast Error
2) Mean Absolute Deviation
3) Mean Squared Error
4) MeanAbsolute Percent Error
What is the main tool used to monitor a forecast?
Control Chart - a visual tool for monitoring forecast errors
