Seminar-1

 Frank Benford was a research physicist at General electric in the 1930s

 He noticed something unusual in the book of logarithmic tables
 He noticed numbers beginning with the digit 1 were being looked more often than
numbers beginning with 2 through 9
 He found that this pattern was wide spread in nature
 Benford’s law states that in many naturally occurring collection of numbers, the
leading significant digit is likely to be small
 Leading digit of a number: Start from the left of each number and ignore the sign,the
decimal point and any zeros,the first digit between 1 and 9 is the leading digit
 For example 3 is the leading digit of 37.3447 and 6 is the leading digit of -0.06345
 For example, in sets which obey the law, the number 1 appears as the most
significant digit about 30% of the time, while 9 appears as the most significant digit
less than 5% of the time
 If the digits were distributed uniformly, they would each occur about 11.1% of the
time
 Benford’s law could be used as an indicator of accounting and expenses fraud
 A recent example is Mark Nigrini’s research
 One fraudster wrote numerous checks to himself just below US $100,000, causing
digits 7,8 and 9 to have aberrant percentages of actual occurrence in Benford’s law
analysis
 Benford’s law could be used as an indicator of accounting and expenses fraud
 A recent example is Mark Nigrini’s research
 One fraudster wrote numerous checks to himself just below US $100,000, causing
digits 7,8 and 9 to have aberrant percentages of actual occurrence in Benford’s law
analysis
 We say a data set satisfies Benford’s Law for the Leading Digit if the probability of

observing a first digit of d is approximately .

 Explanations
1. Scale invariant : A system remain unchanged when multiplied by a constant is
called Scale invariant
 2. Base invariance : Groups of numbers that follow Benford’s law in one base
also follow Benford’s law if converted into another base
 Analysis of Benford's law
1. Ones Scaling test : One scaling test determines the fraction of numbers
having a leading digit of one , as the set of numbers is repeatedly multiplied
by a constant slightly greater than unity such as 1.01. If the set of numbers
follow Benford’s law, the fraction will remain close to 0.301

Seminar - 2
2. Benford's law as a convolution :

where ost(g) is the ones scaling of g and sf(g) is sampling function of g

Position along the logarithmic axis will be denoted by the variable, g.
3. Solving in the frequency domain :

Fourier transforms of pdf(g), sf(g), and ost(g), as PDF(f), SF(f), and OST(f)