关于「队列叠砖:移位贝塔几何模型与前两次续费」,《订阅叠砖、扣款挽回与年付拐点》给出的定量结论是什么?
结论:第一期留存率是 0.847,也就是首月流失 0.153。此后每一期都比上一期稳:第二期 0.870,第六期 0.917,第十二期 0.947,第二十四期 0.969,第三十六期 0.978。存活比例从 0.847 降到第十二个月的 0.330,第二十四个月的 0.204。逐期连乘与闭式解在三位小数上完全一致。
数据口径:书中的订阅数、客单、流失率、挽回率、折现率与价格均为示意参数,全部计算由书中程序生成,不对应任何真实客户或成交数据;本书是非法律、会计、税务或投资建议,不承诺任何收入水平,「稳定」只指收入可预期并写明前提与失效条件。 第一至三章说明,稳态收入等于每月新增乘以客单再除以月流失率,新增定斜率,流失率定天花板;订阅者异质时总体留存随月龄上升,移位贝塔几何模型用几个月的队列数据就能外推;前两次续费是筛子,单次干预回报是后段的 1.40 倍,三年总增益却在长尾,示意参数下是 18,598 对 4,760;订阅层只在刚需使用次数明显高于值回票价的门槛时成立。
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: 0.153, 0.204, 0.330, 0.847, 0.870, 0.917
| month | retention r(t) | survival S(t) | closed form | constant-churn S |
|---|---|---|---|---|
| 1 | 0.847 | 0.847 | 0.847 | 0.847 |
| 2 | 0.870 | 0.737 | 0.737 | 0.718 |
| 3 | 0.886 | 0.653 | 0.653 | 0.609 |
| 4 | 0.899 | 0.587 | 0.587 | 0.516 |
| 6 | 0.917 | 0.490 | 0.490 | 0.370 |
| 12 | 0.947 | 0.330 | 0.330 | 0.137 |
| 24 | 0.969 | 0.204 | 0.204 | 0.019 |
| 36 | 0.978 | 0.149 | 0.149 | 0.003 |
| first-month churn a/(a+b) | 0.153 | |||
| lost by month 2 / lost by month 24 | 0.331 | |||
| survival at 24: sBG / constant churn | 10.8 x |
查看完整验算程序
# Chapter 2. p21: shifted-beta-geometric (sBG) retention and survival.
# Each customer churns with a constant monthly probability theta, and
# theta ~ Beta(a, b) across customers (Fader and Hardie 2007 form).
# r(t) = (b + t - 1) / (a + b + t - 1); S(t) = B(a, b + t) / B(a, b).
# a = 0.90, b = 5.00 are illustrative, not fitted to any real base.
import math
A, B = 0.90, 5.00
def lbeta(x, y):
return math.lgamma(x) + math.lgamma(y) - math.lgamma(x + y)
def surv_closed(t):
return math.exp(lbeta(A, B + t) - lbeta(A, B))
def retention(t):
return (B + t - 1.0) / (A + B + t - 1.0)
s, rows = 1.0, {}
for t in range(1, 37):
s *= retention(t)
rows[t] = s
churn1 = A / (A + B)
print("month retention r(t) survival S(t) closed form constant-churn S")
for t in (1, 2, 3, 4, 6, 12, 24, 36):
print("%5d %14.3f %13.3f %11.3f %16.3f" % (
t, retention(t), rows[t], surv_closed(t), (1.0 - churn1) ** t))
lost2 = 1.0 - rows[2]
lost24 = 1.0 - rows[24]
print("first-month churn a/(a+b) %.3f" % churn1)
print("lost by month 2 / lost by month 24 %.3f" % (lost2 / lost24))
print("survival at 24: sBG / constant churn %.1f x" % (
rows[24] / (1.0 - churn1) ** 24))唯一数据源与引用
范雅福(Fan, Y.). (2026). 《月度经常性收入叠砖、扣款失败自动挽回与年付现金流锁定母典》第 2 章「队列叠砖:移位贝塔几何模型与前两次续费」(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-367 · v1.0.0 · CC-BY-NC-ND-4.0
BibTeX
@book{fan2026367,
author = {Fan, Yafu},
title = {Stacking Monthly Recurring Revenue, Involuntary-Churn Dunning Recovery and Upfront Annual Cash Lock-In},
year = {2026},
publisher = {5D Library},
edition = {1.0.0},
note = {DOI pending}
}