Search This Blog

Google+ Followers

Tuesday, 16 April 2013

Predicting Future Sales Performance


MacIver’s Algorithm



The most accurate predictor
of Future Sales Performance,
and it is FREE, my gift to you.


It can be used to Recruit and Select, to Promote

or to Identify your Future Top Sales Performers.

I am prepared to state that this is more accurate
and has higher validity than any Psychometric ‘test’
or any Recruitment Agency.



This simple three-factor algorithm will substantially out perform any and all ‘Tests’,
and will do at least as well, but usually far better,
at predicting Future Sales Performance than any Expert.

a.) Average (%) of Annual (actual) Performance against target (last five years.)
                (Reduce the total by twenty per cent for each year less than five years)

b.) BEST Quarter’s (%) MINUS WORST Quarter’s (%) Sales Performance (last five years)

c.) Current Sales Velocity (%)   (Last quarter´s Performance against target)


Average last 5 year Annual performance = 87% 

Best quarter 137% minus worst quarter 48% = 89% 

Current Sales Velocity = 115%


(A times B times C) 87% times 89% times 115% = 89%


Then, 89% is the PROBABILITY of this Candidate achieving Target in their first 12 months; redo figures to predict year two when year one actual figure is achieved.


Thanks to Jeff Michaels of Intended Results (@IntendedResults) for encouraging me to Blog this.


Update 04/2013:  I have received a number of direct comments, and I am always happy to receive them here as well.  Based on this feedback and in particular some of the questions I have to caveat the USE of the Algorithm, not the Algorithm, but its use!

Possible fundamental limitations of predictive model based on data fitting

1) History cannot always predict future: using relations derived from historical data to predict the future implicitly assumes there are certain steady-state conditions or constants in the complex system. This is almost always wrong when the system involves people.

2) The issue of unknown unknowns: in all data collection, the collector first defines the set of variables for which data is collected. However, no matter how extensive the collector considers his selection of the variables, there is always the possibility of new variables that have not been considered or even defined, yet critical to the outcome.

3) Self-defeat of the algorithm: after an algorithm becomes an accepted standard of measurement, it can be taken advantage of by people who understand the algorithm and have the incentive to fool or manipulate the outcome.



1 comment:

  1. My pleasure, Brian, but thanks right back to you. It is practical, executable and helpful. Well done!