Benford forensic screen

Benford’s law says that in most naturally occurring financial data, small first digits dominate: about 30% of numbers start with 1, only about 5% start with 9. Fabricated or heavily managed numbers tend to drift from that curve, which is why forensic accountants use the test. Here we run it in the open, on ourselves first: every tracked investor’s reported 13F position values, and every board name’s financial statements.

Read the limits before the table: deviation from Benford has many benign causes. Concentrated portfolios deviate mechanically (we measured a -0.79 rank correlation between book size and deviation, so the investor screen adjusts for book size and flags only residual outliers). Small samples are low power. Nothing here is an accusation of misreporting; it is a screen that says where a second look could start.

Tracked investors: 13F value conformity

Investor	Positions filed	Benford MAD	Conformity (Nigrini bands)	Size-adjusted residual	Adjusted flag
mandel	3,783	0.0327	nonconforming	0.0202	residual outlier
starboard	4,066	0.0300	nonconforming	0.0179	residual outlier
ackman	854	0.0398	nonconforming	0.0156	residual outlier
burry	910	0.0371	nonconforming	0.0137	residual outlier
watsa	4,671	0.0215	nonconforming	0.0100	—
ubben	237	0.0531	nonconforming	0.0091	—
abrams	1,700	0.0256	nonconforming	0.0080	—
semper	3,282	0.0210	nonconforming	0.0077	—
greenblatt	66,265	0.0087	acceptable conformity	0.0042	—
ainslie	22,022	0.0101	acceptable conformity	0.0038	—
egerton	3,357	0.0169	nonconforming	0.0037	—
oakmark	18,089	0.0104	acceptable conformity	0.0036	—
sachem_head	1,444	0.0216	nonconforming	0.0026	—
loeb	4,956	0.0136	marginal	0.0024	—
hound	4,118	0.0144	marginal	0.0024	—
bridgewater	34,973	0.0073	acceptable conformity	0.0018	—
de_shaw	285,120	0.0049	close conformity	0.0017	—
tci	960	0.0245	nonconforming	0.0016	—
viking	7,669	0.0108	acceptable conformity	0.0014	—
citadel	771,110	0.0038	close conformity	0.0010	—
spier	392	0.0357	nonconforming	0.0010	—
two_sigma	172,580	0.0040	close conformity	0.0005	—
russo	9,910	0.0085	acceptable conformity	0.0000	—
kantesaria	682	0.0265	nonconforming	-0.0003	—
millennium	258,604	0.0028	close conformity	-0.0005	—
druckenmiller	4,819	0.0108	acceptable conformity	-0.0005	—
valueact	1,527	0.0180	nonconforming	-0.0006	—
coatue	12,589	0.0071	acceptable conformity	-0.0006	—
whale_rock	3,977	0.0115	acceptable conformity	-0.0008	—
rochon	4,474	0.0104	acceptable conformity	-0.0013	—
point72	76,289	0.0030	close conformity	-0.0013	—
renaissance	186,086	0.0021	close conformity	-0.0014	—
himalaya	382	0.0333	nonconforming	-0.0018	—
tepper	3,191	0.0116	acceptable conformity	-0.0019	—
ariel	16,552	0.0049	close conformity	-0.0021	—
marks	22,542	0.0041	close conformity	-0.0022	—
southeastern	5,322	0.0084	acceptable conformity	-0.0024	—
soros	19,188	0.0041	close conformity	-0.0025	—
corvex	3,546	0.0102	acceptable conformity	-0.0027	—
light_street	3,205	0.0108	acceptable conformity	-0.0027	—
robbins	5,741	0.0077	acceptable conformity	-0.0029	—
peltz	1,002	0.0191	nonconforming	-0.0033	—
tiger_global	6,358	0.0063	acceptable conformity	-0.0038	—
hosking	12,393	0.0039	close conformity	-0.0039	—
polen	7,667	0.0048	close conformity	-0.0046	—
icahn	2,501	0.0103	acceptable conformity	-0.0046	—
einhorn	6,759	0.0052	close conformity	-0.0047	—
sundheim	2,233	0.0107	acceptable conformity	-0.0050	—
buffett	10,033	0.0030	close conformity	-0.0055	—
akre	2,958	0.0083	acceptable conformity	-0.0056	—
altimeter	2,456	0.0094	acceptable conformity	-0.0057	—
klarman	3,603	0.0067	acceptable conformity	-0.0060	—
singer	2,461	0.0084	acceptable conformity	-0.0066	—
pabrai	454	0.0250	nonconforming	-0.0074	—
jana	2,331	0.0079	acceptable conformity	-0.0075	—
fairholme	1,428	0.0113	acceptable conformity	-0.0079	—
punchcard	356	0.0260	nonconforming	-0.0103	—
engaged	1,116	0.0086	acceptable conformity	-0.0128	—

First-digit Benford conformity of each tracked investor's reported 13F position values across all filed quarters (Nigrini MAD bands). Raw deviation mostly measures portfolio concentration (measured Spearman -0.79 between book size and deviation), so the screen adjusts for book size and flags only residual outliers. A statistical screen only: deviations have many benign causes and are never an accusation of misreporting.

Board names: financial-statement conformity

The classic forensic use of Benford: statement line items. Each board name’s income statement, balance sheet, and cash flow (annual and quarterly pooled), first digits against the curve.

Ticker	Line items	Benford MAD	Conformity
USFD	681	0.0300	well above the n-matched null
UNM	580	0.0291	well above the n-matched null
GWW	667	0.0280	well above the n-matched null
MTCH	937	0.0268	well above the n-matched null
ESS	887	0.0257	well above the n-matched null
EWTX	473	0.0254	above the n-matched null
TRGP	972	0.0253	well above the n-matched null
BNY	807	0.0238	above the n-matched null
BLDR	817	0.0237	above the n-matched null
KSS	587	0.0236	above the n-matched null
MKL	622	0.0231	above the n-matched null
MKSI	609	0.0229	above the n-matched null
HBAN	749	0.0229	above the n-matched null
OKE	755	0.0221	above the n-matched null
SPG	923	0.0217	above the n-matched null
GLW	875	0.0213	above the n-matched null
ELV	675	0.0211	above the n-matched null
BNS	848	0.0210	above the n-matched null
ACHC	957	0.0207	above the n-matched null
VNO	936	0.0206	above the n-matched null
SMG	890	0.0205	above the n-matched null
WCN	951	0.0204	above the n-matched null
PRU	659	0.0203	above the n-matched null
HUM	667	0.0201	above the n-matched null
L	585	0.0200	above the n-matched null
RTX	915	0.0199	above the n-matched null
MSCI	945	0.0199	above the n-matched null
MTN	1013	0.0199	above the n-matched null
PRMB	850	0.0197	above the n-matched null
SNDK	529	0.0197	above the n-matched null
BBIO	912	0.0196	above the n-matched null
ADP	955	0.0194	above the n-matched null
ON	953	0.0194	above the n-matched null
FITB	732	0.0192	above the n-matched null
FDS	877	0.0192	above the n-matched null
CM	834	0.0192	above the n-matched null
SPGI	814	0.0188	above the n-matched null
HRL	997	0.0187	above the n-matched null
SYF	529	0.0186	above the n-matched null
MU	893	0.0181	above the n-matched null

First-digit Benford conformity of each board name's financial statement line items (income, balance sheet, cash flow; annual and quarterly pooled, duplicate values removed), each judged against a simulated null of its own sample size. THE HEADLINE IS THE BASE RATE: 101 of 150 large, liquid, heavily audited names exceed the null, because single-company statement pools are structurally non-Benford (subtotals, repeated scale, correlated line items). So this test, at this granularity, has weak discriminative power for manipulation, and we publish it partly to show that limit honestly. Only the handful of names far above the null merit even a curious second read, and a deviation is never an accusation.