What does Five-Minute Leads and Leakage Audits conclude, in numbers, about “Sampling Audits, Buyer Confirmation and Locking In the Referral Share”?
Answer: Chapter 6 gives the operating characteristic curve of a sampling audit, the incentive conditions for buyer confirmation and the expected referral share under registration, a protection period and escrow; with illustrative parameters, three callbacks among forty files reported as not closed detect a single leak with probability only 0.0675, so it is the value of the relationship that deters.
Scope of the numbers: Parameters are illustrative and all calculations are generated by the book's programs. This is general analysis of law, tax, investment and business operations, not personalised advice.
Data table
The numbers below are printed verbatim by the chapter's Python program and can be reproduced by running it. standard-library Python onlyprinted values that match the answer: 0.0675
| A. probability the audit finds at least one leak | |
| D n | 2 4 6 10 16 |
| 1 | 0.0450 0.0900 0.1350 0.2250 0.3600 |
| 2 | 0.0890 0.1738 0.2544 0.4033 0.5954 |
| 4 | 0.1738 0.3238 0.4523 0.6535 0.8445 |
| 8 | 0.3309 0.5616 0.7192 0.8937 0.9808 |
| binomial check D | 4, n = 10: 0.6106 v exact 0.6535 |
| B. smallest n with expected leak gain below zero | |
| D | 1: n = 3 (share 0.075), detect 0.0675 |
| D | 2: n = 3 (share 0.075), detect 0.1319 |
| D | 4: n = 3 (share 0.075), detect 0.2516 |
| D | 8: n = 2 (share 0.050), detect 0.3309 |
| C. end game, future flow V | 0 |
| D | 1: n = 23 (share 0.575), detect 0.5175 |
| D | 4: n = 15 (share 0.375), detect 0.8203 |
| D | 8: n = 10 (share 0.250), detect 0.8937 |
Show the full program
# Chapter 6. p61: OC curve of a consented buyer-callback audit.
# Audit population: the N = 40 referred buyers a partner reported as
# "not closed" in a quarter. D of them in fact closed off the register.
# The referring agency calls back n of them, chosen at random, under a
# callback clause both sides signed and the buyer agreed to; a callback
# reveals a leak with probability 0.9 (the buyer answers and says so).
# Exact detection: 1 - sum over k of hypergeometric(k) * 0.1^k, with
# Fractions; the binomial line uses D / N as the leak rate. Part B: the
# smallest n that makes leaking D deals a losing bet, with G = RM 3,000
# per deal, damages L = RM 3,000 and future flow V = RM 54,000 (p52).
from fractions import Fraction
from math import comb
N = 40
HIT = Fraction(9, 10)
G, L, V = 3000, 3000, 54000
def detect_exact(d, n):
miss = Fraction(0)
for k in range(0, min(d, n) + 1):
pk = Fraction(comb(d, k) * comb(N - d, n - k), comb(N, n))
miss += pk * (1 - HIT) ** k
return 1 - miss
def smallest_n(d, future):
n = 0
while n < N:
p = detect_exact(d, n)
if d * G - p * (d * G + L + future) < 0:
return n
n += 1
return N
def detect_binom(d, n):
p = Fraction(d, N) * HIT
return 1 - (1 - p) ** n
if __name__ == "__main__":
print("A. probability the audit finds at least one leak")
print(" D n: 2 4 6 10 16")
for d in (1, 2, 4, 8):
cells = ["{:.4f}".format(float(detect_exact(d, n)))
for n in (2, 4, 6, 10, 16)]
print(" {:>2} ".format(d) + " ".join(cells))
print(" binomial check D = 4, n = 10: {:.4f} v exact {:.4f}".format(
float(detect_binom(4, 10)), float(detect_exact(4, 10))))
print("B. smallest n with expected leak gain below zero")
for d in (1, 2, 4, 8):
n = smallest_n(d, V)
print(" D = {}: n = {:>2} (share {:.3f}), detect {:.4f}".format(
d, n, n / N, float(detect_exact(d, n))))
print("C. end game, future flow V = 0")
for d in (1, 4, 8):
n = smallest_n(d, 0)
print(" D = {}: n = {:>2} (share {:.3f}), detect {:.4f}".format(
d, n, n / N, float(detect_exact(d, n))))Single source and citation
Fan, Y. (2026). Five-Minute High-Intent Lead Conversion, Offline Deal-Leakage Auditing and Referral Commission Lock-In (Version 1.0.0), Chapter 6: Sampling Audits, Buyer Confirmation and Locking In the Referral Share. 5D Library. DOI pending
DOI pending · monograph page goes live after publication · 5DL-B-348 · v1.0.0 · CC-BY-NC-ND-4.0
BibTeX
@book{fan2026348,
author = {Fan, Yafu},
title = {Five-Minute High-Intent Lead Conversion, Offline Deal-Leakage Auditing and Referral Commission Lock-In},
year = {2026},
publisher = {5D Library},
edition = {1.0.0},
note = {DOI pending}
}Other chapter answers in this book
- Chapter 1 · Where "a Hundred Times" Comes From: Hazard Functions of Lead Decay
- Chapter 2 · Fast Teams Are Better Teams: Confounding, Randomised Delays and a Shift Boundary
- Chapter 3 · How Many People Does Five Minutes Take? Queues, Triage and the Desk
- Chapter 4 · The First Message after Consent: Timing, the 24-Hour Window and Disclosed Automation
- Chapter 5 · The Arithmetic of Deal Leakage: Agency, Information and the Value of the Relationship
- Chapter 7 · Classical Sources: the Two Handles of the Han Feizi and Adam Smith on Other People's Money
- Chapter 8 · The Empirical Loop: the Lead and Hand-off Ledger, the Audit Sampler and Pre-registered Refutation