Z-score

Z-Scores and Modified Z-Scores

Z-score is a statistical measurement of a number in relationship to the mean of the group of numbers. It refers to points along the base of the standardized normal curve. The center point of the curve has a z-value of 0. The distance from the mean is measured by standard deviations. StrayDot generates a report with a list of all vendors and highlights the outliers.

How to use it ?

StrayDot flags all transactions with a z-score above 2.5 and 3.0 or higher indicating the payment is more than 2.5 standard deviations above the mean. Results from a modified version of Z Score test are also shown to help spot the outliers more effectively.

What does our fraud detection analytics software do?

We run more than a dozen separate tests with just the basic data. In fact over half the test for employee, payroll, accounts payable, check, and business fraud are run with just check data, check amount and payee. Here are the tests we run:

Benford’s law

single and double digits

Similar vendors

(you set the similarity percentage)

Non-business day transaction

(US Holidays included)

Under cut-off amounts

(you set the limits)

Z-score

(also helps identify vendors putting stress on the business)

Fictitious vendor search

(you select the search words like PO Box, or consultant)

Amounts Exactly Twice

As much as other

Amounts starting with

Same First Four Digits