Abstract

Due to their simple applicability score systems are in widespread use as a tool
for decision taking.  
Unfortunately, as we all feel, they are somehow not apt to
take into account interdependencies among the variables (symptoms/attributes)
wich is overcome by probabilisticsystems.  In order to analyze which assumptions
are inherent in score systems we translate them into probabilistic systems - a
more powerful framework - thus making available their technical machinery for
this analysis task.  
Such a straightforward translation (as also given in KR00
reveals some properties of score systems, but leads to an exponential number of
probabilistic rules.  For this reason we also developed several further
translations into probabilistic systems, which keep the simplicity of a score
system (i.e.  they use the same amount of rules as the score system). Moreover,
the resulting probabilistic systems show their structure more explicitely than
score systems, and they are also open to the addition of further knowledge.