5D Library › Retrodictive Belief Locking, Sequential Pain-Point Agitation and Markovian Upsell Automata · 中文
Chapter 6. Cross-Module Transition Matrices: Estimation, Cannibalization and Heterogeneity
How many users does a rare cross-module transition need?
The parameters of a conversion chain are not written down; they are estimated. Let users move each month among the four modules C, A, M and B, or stop (X), and let the move from acoustic to business scripts (A to B) be rare (0.01 a month) but valuable. The maximum-likelihood estimate of a transition matrix is the row-normalised counts; its uncertainty can be estimated by resampling users with the bootstrap (Efron and Tibshirani 1993).
Calculation
# Chapter 6. [p11] How many users does it take to estimate a cross-module
# transition? Monthly moves among modules C, A, M, B and X (stopped).
# The true matrix below has one rare but valuable link, A -> B (0.01).
# For panels of n users followed 12 months from module C or A (seed
# 69), the maximum-likelihood estimate (row-normalised counts) of
# A -> B and its bootstrap 90% interval (200 resamples of users).
import random
S = ("C", "A", "M", "B", "X")
P = {"C": (0.60, 0.10, 0.08, 0.02, 0.20),
"A": (0.08, 0.62, 0.08, 0.01, 0.21),
"M": (0.06, 0.06, 0.66, 0.02, 0.20),
"B": (0.02, 0.02, 0.02, 0.84, 0.10)}
def step(s, rng):
u, acc = rng.random(), 0.0
for t, p in zip(S, P[s]):
acc += p
if u < acc:
return t
return "X"
def path(rng):
s = rng.choice(("C", "A"))
out = []
for _ in range(12):
if s == "X":
break
t = step(s, rng)
out.append((s, t))
s = t
return out
def est(paths):
n_a = sum(1 for p in paths for s, t in p if s == "A")
n_ab = sum(1 for p in paths for s, t in p if s == "A" and t == "B")
return n_ab / n_a if n_a else 0.0
if __name__ == "__main__":
rng = random.Random(69)
print(" users estimate A->B 90% bootstrap interval rel. width")
for n in (100, 1000, 10000):
paths = [path(rng) for _ in range(n)]
e = est(paths)
boots = sorted(est([paths[rng.randrange(n)] for _ in range(n)])
for _ in range(200))
lo, hi = boots[10], boots[189]
print(" {:6,d} {:13.4f} [{:.4f}, {:.4f}] {:16.2f}".format(
n, e, lo, hi, (hi - lo) / 0.01))
print(" true A->B = 0.0100")
print("\nReading: a rare cross-module link cannot be read off a few")
print("hundred users: at 1,000 users its interval is still three")
print("quarters as wide as the value itself.")
# users estimate A->B 90% bootstrap interval rel. width
# 100 0.0050 [0.0000, 0.0142] 1.42
# 1,000 0.0101 [0.0066, 0.0140] 0.74
# 10,000 0.0099 [0.0086, 0.0110] 0.23
# true A->B = 0.0100
#
# Reading: a rare cross-module link cannot be read off a few
# hundred users: at 1,000 users its interval is still three
# quarters as wide as the value itself.With 100 users the estimate of A to B is 0.0050 and its 90% bootstrap interval runs from 0 to 0.0142, 1.42 times as wide as the true value; with 1,000 users the interval is still 0.74 times as wide; only at 10,000 users does it shrink to 0.23. A claim that “a few per cent of acoustic users move on to business scripts”, based on a few hundred users, means almost nothing statistically.
Does “learning to read it yourself” cannibalize readings?
The academy teaches users to compute their own charts, and graduates stop buying readings. Does that cost more than it brings? The program rewrites the chain of Chapter 5: each month a reader enrols with probability 0.04 and pays a course fee of 360 on enrolment; graduates buy no more readings, take the licence with probability a month, and lapse at 0.10. Without an academy, that 0.04 of readers keep buying readings.
Calculation
# Chapter 6. [p12] "Learn to read it yourself": does the academy course
# cannibalize readings? A variant of the p09 chain, discounted at 0.99
# a month. A reader (25 a month in readings) enrols with probability
# 0.04 a month and pays the course, 360, on enrolment. Graduates
# compute their own charts and never buy a reading again; each month
# a share g of them takes the licence (12,537) and 0.10 lapse. Without
# a course, the 0.04 stay readers. Reported: a reader's discounted LTV
# with and without the course, and the break-even course fee.
ENTRY_L = 12537.0
def ltv_reader(course, g=0.01, months=900, COURSE=360.0):
vt, vg = 0.0, 0.0
for _ in range(months):
if course:
nt = 25 + 0.99 * (0.70 * vt + 0.04 * (COURSE + vg)
+ 0.002 * ENTRY_L)
ng = 0.99 * ((0.90 - g) * vg + g * ENTRY_L)
else:
nt = 25 + 0.99 * (0.74 * vt + 0.002 * ENTRY_L)
ng = 0.0
vt, vg = nt, ng
return vt
if __name__ == "__main__":
a = ltv_reader(False)
print(" reader LTV without a course: {:8.2f}".format(a))
for g in (0.0, 0.002, 0.005, 0.01, 0.02):
print(" with the course, g = {:.3f}: {:8.2f}".format(
g, ltv_reader(True, g)))
for g in (0.0, 0.005):
lo, hi = 0.0, 360.0
for _ in range(50):
mid = (lo + hi) / 2
if ltv_reader(True, g, COURSE=mid) > a:
hi = mid
else:
lo = mid
if hi < 0.01:
print(" at g = {:.3f} the course pays even if it is free"
.format(g))
else:
print(" break-even course fee at g = {:.3f}: {:.2f}".format(
g, hi))
print("\nReading: a graduate's lost readings are worth less than the")
print("fee, because a reader's remaining reading spend is short-lived;")
print("the fear of cannibalization matters only for a cheap course.")
# reader LTV without a course: 186.32
# with the course, g = 0.000: 208.73
# with the course, g = 0.002: 237.58
# with the course, g = 0.005: 278.98
# with the course, g = 0.010: 343.38
# with the course, g = 0.020: 457.33
# break-even course fee at g = 0.000: 186.32
# at g = 0.005 the course pays even if it is free
#
# Reading: a graduate's lost readings are worth less than the
# fee, because a reader's remaining reading spend is short-lived;
# the fear of cannibalization matters only for a cheap course.Without an academy a reader’s LTV is 186.32; with it, and with no graduate ever buying a licence (), it is 208.73, still higher; at it is 278.98. At the break-even course fee is 186.32; once five graduates in a thousand take the licence each month, the academy pays even if it is free. The reason is that a reader’s remaining reading spend is short-lived anyway: what “learning to read it yourself” cannibalizes is a small income that would soon have vanished.
One chain cannot hold two kinds of user
Chapter 5 described all readers with one chain. The program sets up two kinds: 20% are engaged (monthly retention 0.85, enrolment 0.08) and 80% casual (retention 0.50, enrolment 0.01). An analyst pools all moves observed over 24 months and fits a single chain. This is the classic “mover-stayer” problem (Blumen et al. 1955).
Calculation
# Chapter 6. [p13] One Markov chain for two kinds of reader (mover-
# stayer). 20% of readers are "engaged": monthly stay 0.85, to course
# 0.08, lapse 0.07; 80% are "casual": stay 0.50, to course 0.01, lapse
# 0.49. An analyst pools 24 months of observed moves (20,000 readers,
# seed 69) and fits one chain by maximum likelihood. Compared: the
# share of new readers who ever enrol, true versus predicted by the
# pooled chain, and the share still reading after 1 to 24 months.
import random
TYPES = ((0.2, 0.85, 0.08), (0.8, 0.50, 0.01)) # share, stay, course
def ever_enrol(stay, course):
return course / (1 - stay)
if __name__ == "__main__":
rng = random.Random(69)
n_stay = n_course = n_from = 0
for _ in range(20000):
share = rng.random()
stay, course = (TYPES[0][1:] if share < TYPES[0][0]
else TYPES[1][1:])
for _ in range(24):
n_from += 1
u = rng.random()
if u < stay:
n_stay += 1
elif u < stay + course:
n_course += 1
break
else:
break
ps, pc = n_stay / n_from, n_course / n_from
true = sum(w * ever_enrol(s, c) for w, s, c in TYPES)
pooled = ever_enrol(ps, pc)
print(" pooled chain: stay {:.4f}, to course {:.4f}".format(ps, pc))
print(" share of new readers who ever enrol: true {:.4f},"
" pooled chain {:.4f}".format(true, pooled))
print(" share still reading month: 1 3 6 12"
" 24")
tr = [sum(w * s ** m for w, s, c in TYPES) for m in (1, 3, 6, 12, 24)]
print(" true " + " ".join(
"{:7.4f}".format(x) for x in tr))
print(" pooled chain " + " ".join(
"{:7.4f}".format(ps ** m) for m in (1, 3, 6, 12, 24)))
print("\nReading: the pooled chain gets total conversion about right")
print("but the shape of survival wrong: too many readers kept early,")
print("far too few in the long tail, where the engaged readers who")
print("later buy the course and the licence are.")
# pooled chain: stay 0.6603, to course 0.0420
# share of new readers who ever enrol: true 0.1227, pooled chain 0.1236
# share still reading month: 1 3 6 12 24
# true 0.5700 0.2228 0.0879 0.0286 0.0040
# pooled chain 0.6603 0.2879 0.0829 0.0069 0.0000
#
# Reading: the pooled chain gets total conversion about right
# but the shape of survival wrong: too many readers kept early,
# far too few in the long tail, where the engaged readers who
# later buy the course and the licence are.The pooled chain gives almost the same total share who enrol (0.1236) as the truth (0.1227), but the shape of retention is quite wrong: too high in month 1 (0.6603 against 0.5700), and only about a quarter of the true value by month 12 (0.0069 against 0.0286). Those left in the long tail are exactly the engaged users, who later buy the course and the licence. Predicting long-run conversion with a single chain systematically underestimates them.
Hypothesis · not established
The author’s interpretation (not yet tested): the users of a reading business fall into at least two kinds, “engaged” and “casual”, and conversion analysis should segment them before building chains. What would show this wrong: if a two-type mixture fitted to real data describes retention no better than a single chain (by a likelihood-ratio test or cross-validated prediction error, for example), the distinction does not exist in this business.
Summary
A rare cross-module transition needs tens of thousands of users to estimate well. The reading income that “learning to read it yourself” cannibalizes is, with this book’s parameters, smaller than the course fee and much smaller than the value of the path to the licence. Pooling two kinds of user into one chain looks right on total conversion but badly distorts long-tail retention.
References
Fan, Y. (2026). Retrodictive Belief Locking, Sequential Pain-Point Agitation and Markovian Upsell Automata: Bayesian Trust Avalanches, Sunk-Cost Commitment Ratchets and Cross-Domain Transition Matrices [回溯信念锁定、序贯痛点唤醒与马尔可夫升单自动机] (Version 1.0.0). 5D Library. https://doi.org/10.5281/zenodo.24090186 · Licensed under Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0).