12_posting_-_Forecasting_2

12_posting_-_Forecasting_2 - Forecasting 2 Trying to...

Info iconThis preview shows pages 1–8. Sign up to view the full content.

View Full Document Right Arrow Icon
10/15/2010 1 Forecasting 2 Trying to predict the future is like trying to drive down a country Trying to predict the future is like trying to drive down a country road at night with no lights while looking out the back window road at night with no lights while looking out the back window . Peter Drucker Peter Drucker
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
10/15/2010 2 How can we compare across forecasting models? We need a metric that provides estimation of accuracy Forecast Error Forecast error = Difference between actual and forecasted value (also known as residual ) Errors can be: 1. biased (consistent) 2. random 3. combination
Background image of page 2
10/15/2010 3 Measuring Accuracy: MAD MAD = Mean Absolute Deviation It is the average absolute error in the observations 1. Higher MAD implies worse performance (higher deviation from forecast – VARIATION ). 2. If errors are normally distributed, then σ ε =1.25MAD (or 1 MAD = 0.8 σ ε )
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
10/15/2010 4 Measuring Accuracy: MAD 99.73% of all actual demand points should fall within + 3.75 MAD from forecast demand
Background image of page 4
10/15/2010 5 Measuring Accuracy: RSFE RSFE = Running Sum of Forecast Errors It is the sum of all errors (not absolute) in the observations Again, higher RSFE indicates worse performance (more deviation from forecast – BIAS )
Background image of page 5

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
10/15/2010 6 Measuring Accuracy: Tracking signal The tracking signal is a measure of how often our predictions have been above or below the actual value and the magnitude of the error MAD RSFE TS = Positive tracking signal: the actual value is above our predicted value Negative tracking signal: the actual value is below our predicted value
Background image of page 6
10/15/2010 7 Example: bottled water at Kroger Month Actual Forecast Jan 1,325 1370 Feb 1,353 1341 Mar 1,305
Background image of page 7

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Image of page 8
This is the end of the preview. Sign up to access the rest of the document.

Page1 / 23

12_posting_-_Forecasting_2 - Forecasting 2 Trying to...

This preview shows document pages 1 - 8. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online