DM: RE: Introductions

[Abraham Meidan (by way of Dorothy Firsching <firschng@cais.com>)]

Hi,

We are a software house that among other things develops applications 
for 
data mining. Till now we have developed two commercial applications --

(1) WizRule is an application for data auditing and cleansing. 
WizRule 
reads the data set under investigation, automatically reveals the 
rules 
that govern the data and points at the deviations from the set of the 
discovered rules as suspected errors and cases to be audited. In 
order to 
avoid false alarms WizRule (version 3) includes an algorithm that 
calculates the level of unlikelihood of each deviation.

(2) WizWhy an application for issuing predictions and 
classifications. 
WizWhy read the train file, reveals the rules in this file, and 
calculates 
the significance level of each of these rules. These rules and their 
significance levels are then used in order to issue prediction for 
new 
cases.

Both product are based on our 2 proprietary algorithms for revealing 
rules 
--
(1) An algorithm that revels ALL if-then and if-then-not rules. This 
algorithm is somewhat similar to association rules, but is much 
faster.
(2) An algorithm that reveals mathematical formula rules, such as 
Field A = 
Field B + Field C * Field D.

Best regards,

Abraham
abraham@wizsoft.com