关于「口岸检查博弈:申报与不申报的混合均衡和风险画像」,《买手的背包、口岸博弈与报关反转点》给出的定量结论是什么?
结论:第三章把口岸查验写成检查博弈,示意参数下不申报的盈亏平衡查验率是 0.1852,而风险画像使查验率在每季度两到四趟之间从 0.0380 跳到 0.5035。
数据口径:书中参数为示意,各地法规不同;全部计算由书中程序生成;本书不是个人化的法律或税务建议。 第三章把口岸查验写成检查博弈,示意参数下不申报的盈亏平衡查验率是 0.1852,而风险画像使查验率在每季度两到四趟之间从 0.0380 跳到 0.5035。
对照数据表
下表数字由本章 Python 程序原样打印,可重新运行复现。 程序只用 Python 标准库与结论吻合的打印值: 0.0380, 0.5035
| trips/qtr | P(comm|k) | inspect p(k) | trips/yr | P(no insp) | E insp |
|---|---|---|---|---|---|
| 0 | 0.0002 | 0.0201 | 0 | 1.0000 | 0.00 |
| 1 | 0.0026 | 0.0215 | 4 | 0.9168 | 0.09 |
| 2 | 0.0311 | 0.0380 | 8 | 0.7334 | 0.30 |
| 3 | 0.2861 | 0.1859 | 12 | 0.0847 | 2.23 |
| 4 | 0.8336 | 0.5035 | 16 | 0.0000 | 8.06 |
| 5 | 0.9843 | 0.5909 | 20 | 0.0000 | 11.82 |
| 6 | 0.9987 | 0.5993 | 24 | 0.0000 | 14.38 |
| 7 | 0.9999 | 0.5999 | 28 | 0.0000 | 16.80 |
| 8 | 1.0000 | 0.6000 | 32 | 0.0000 | 19.20 |
| a flat rate with the same prior would be 0.0316 for everyone | |||||
| at 6 trips a quarter, a flat rule leaves P(no insp) 0.4627 |
查看完整验算程序
# Chapter 3. p32: risk profiling makes the inspection rate rise with trips.
# Among travellers on a route a share pi = 0.02 carry goods for resale.
# Ordinary travellers make Poisson(0.4) trips a quarter, commercial
# carriers Poisson(5). A risk engine that has seen k trips in a quarter
# holds the posterior P(commercial | k) by Bayes' rule and sets the
# inspection rate p(k) = 0.02 + 0.58 P(commercial | k). For a buyer who
# keeps k trips a quarter all year (4k trips), the table gives the chance
# of a year without any inspection and the expected inspections. The
# prior, the trip rates and the linear rule are illustrative.
import math
PI, LO, HI, BASE, SPAN = 0.02, 0.4, 5.0, 0.02, 0.58
def pois(k, lam):
return math.exp(-lam) * lam ** k / math.factorial(k)
print("trips/qtr P(comm|k) inspect p(k) trips/yr P(no insp) E insp")
for k in range(0, 9):
a = PI * pois(k, HI)
b = (1 - PI) * pois(k, LO)
post = a / (a + b)
p = BASE + SPAN * post
n = 4 * k
print("{:9d}{:11.4f}{:14.4f}{:10d}{:12.4f}{:8.2f}".format(
k, post, p, n, (1 - p) ** n, n * p))
flat = BASE + SPAN * PI
print("a flat rate with the same prior would be {:.4f} for everyone"
.format(flat))
print("at 6 trips a quarter, a flat rule leaves P(no insp) {:.4f}"
.format((1 - flat) ** 24))唯一数据源与引用
范雅福(Fan, Y.). (2026). 《跨国买手体积重量双维背包优化、口岸风险画像抽检博弈与正规报关规模反转点》第 3 章「口岸检查博弈:申报与不申报的混合均衡和风险画像」(版本 1.0.0). 5D Library. DOI 待发布
DOI 待发布 · 专著页正式发布后上线(本站暂无专著页) · 5DL-B-174 · v1.0.0 · CC-BY-NC-ND-4.0
BibTeX
@book{fan2026174,
author = {Fan, Yafu},
title = {Two-Dimensional Volume-Weight Knapsacks for Cross-Border Buyers, Port Risk-Profiling Inspection Games and the Scale Reversal Point to Formal Customs Clearance},
year = {2026},
publisher = {5D Library},
edition = {1.0.0},
note = {DOI pending}
}