5D Library › Conversational Closing Automata, Objection-Handling Information Gain and High-Ticket Sales Kinetics · 中文
Chapter 2. Diagnostic Question Trees: Which Question, and How Many
More bits are not more value
A question is worth asking not because its answer carries many bits but because the answer may change the next action: which price to quote, or whether to quote yet. Decision theory calls this the value of information; it is related to the amount of information but is not the same. Below, an adaptive question tree is solved exactly by dynamic programming: at each node either stop and take the best plan for the current belief, or ask one of the questions not yet asked, choosing the one with the highest expected value.
Calculation
# Chapter 2. p03: Which question next? An adaptive question tree solved
# exactly by dynamic programming over the questions not yet asked: at each
# node either stop and take the best plan of p02, or ask the question
# whose answers lead to the most expected value (each question loses 2%
# of buyers). Compared with asking in the fixed S-P-I-N order and with
# always asking the question that carries the most bits.
import importlib.util
def load(name):
spec = importlib.util.spec_from_file_location(name, name + ".py")
m = importlib.util.module_from_spec(spec)
spec.loader.exec_module(m)
return m
p01 = load("p01_belief")
p02 = load("p02_pomdp")
QS = list(p01.Q)
def best(belief, left, depth=0, log=None):
stop = p02.value(belief)[1]
choice, val = None, stop
for q in left:
v = 0.0
for yes in (True, False):
post, pz = p01.posterior(belief, p01.Q[q], yes)
v += pz * best(post, [x for x in left if x != q], depth + 1)[1]
v *= 1 - p02.DROP
if v > val + 1e-9:
choice, val = q, v
return choice, val
def expected_questions(belief, left):
q, _ = best(belief, left)
if q is None:
return 0.0
n = 1.0
for yes in (True, False):
post, pz = p01.posterior(belief, p01.Q[q], yes)
n += pz * (1 - p02.DROP) * expected_questions(
post, [x for x in left if x != q])
return n
def by_bits(belief, left, k):
if k == 0 or not left:
return p02.value(belief)[1]
q = max(left, key=lambda x: p01.info(belief, p01.Q[x]))
v = 0.0
for yes in (True, False):
post, pz = p01.posterior(belief, p01.Q[q], yes)
v += pz * by_bits(post, [x for x in left if x != q], k - 1)
return v * (1 - p02.DROP)
if __name__ == "__main__":
prior = dict(p01.PRIOR)
q, v = best(prior, QS)
print(" pitch at once RM {:,.0f}".format(
p02.value(prior)[1]))
fixed = max(p02.ask_then_offer(k)[0] for k in range(5))
print(" fixed S-P-I-N, best k RM {:,.0f}".format(fixed))
bb = max(by_bits(prior, QS, k) for k in range(5))
print(" most bits first, best k RM {:,.0f}".format(bb))
print(" optimal tree RM {:,.0f}".format(v))
print(" first question: {}".format(q.split(" (")[0]))
print(" expected questions asked: {:.2f}".format(
expected_questions(prior, QS)))
for yes in (True, False):
post, pz = p01.posterior(prior, p01.Q[q], yes)
q2, _ = best(post, [x for x in QS if x != q])
print(" if {}: next {}".format("yes" if yes else "no",
q2.split(" (")[0] if q2 else "stop"))
# pitch at once RM 2,522
# fixed S-P-I-N, best k RM 2,671
# most bits first, best k RM 2,677
# optimal tree RM 2,748
# first question: S situation
# expected questions asked: 1.73
# if yes: next N need-payoff
# if no: next stopPitching at once is worth RM 2,522 in expectation. Asking in the fixed order S, P, I, N with the best number of questions is worth RM 2,671; always asking the question with the most bits, RM 2,677; the optimal question tree, RM 2,748, 9.0% more than pitching at once, with only 1.73 questions on average. The optimal tree asks the situation question first: if the answer is yes (a team of more than five, revenue the buyer can state), it asks the need-payoff question next; if no, it stops and asks nothing more.
Note
Ask until the answer can no longer change the decision. For a buyer who has answered “a small team, no revenue figure”, asking about pain and its implications will not make the seller quote the higher tier instead; those questions still carry bits, but their value is zero.
How many questions
Every further question costs some buyers their patience. Below, the optimal tree is solved again for different loss rates.
Calculation
# Chapter 2. p04: How many questions before the offer? The optimal tree of
# p03 is re-solved for different shares of buyers lost per question, from
# none (a patient buyer) to 15% (a buyer who came for a price). Reported:
# the value per lead, its gain over pitching at once, and the expected
# number of questions the optimal tree asks.
import importlib.util
def load(name):
spec = importlib.util.spec_from_file_location(name, name + ".py")
m = importlib.util.module_from_spec(spec)
spec.loader.exec_module(m)
return m
p03 = load("p03_question_tree")
p01, p02 = p03.p01, p03.p02 # the same module objects p03 uses
if __name__ == "__main__":
prior = dict(p01.PRIOR)
base = p02.value(prior)[1]
print(" lost per question RM per lead gain questions asked")
for d in (0.0, 0.02, 0.05, 0.10, 0.15):
p02.DROP = d
_, v = p03.best(prior, p03.QS)
n = p03.expected_questions(prior, p03.QS)
print(" {:17.0%} {:11,.0f} {:+5.1%} {:15.2f}".format(
d, v, v / base - 1, n))
# lost per question RM per lead gain questions asked
# 0% 2,894 +14.8% 3.26
# 2% 2,748 +9.0% 1.73
# 5% 2,584 +2.5% 1.00
# 10% 2,522 +0.0% 0.00
# 15% 2,522 +0.0% 0.00With a very patient buyer (no loss), the optimal tree asks 3.26 questions on average and is worth RM 2,894, 14.8% more than pitching at once; with 2% lost per question, 1.73 questions and 9.0% more; with 5% lost, only 1.00 question and 2.5% more; from 10% lost upward, the best course is to pitch at once. The value of diagnostic questioning depends on how much the buyer is willing to be asked.
Hypothesis · not established
The author’s hypothesis (not yet tested): for buyers who come asking for a price, opening with one situation question (team and revenue) before choosing which tier to quote yields at least 5% more six-month revenue per enquirer than quoting in the first message. What would show it wrong: in an experiment assigning the two openings at random by enquirer, the revenue gap is under 5%, or the former is lower.
Summary
The optimal question tree asks first the questions that can change the decision, and stops when no answer can. In the illustrative model it beats pitching at once by 9.0% with only 1.73 questions on average; the less patient the buyer, the fewer questions are worth asking, and at a loss of 10% per question none are.
Fan, Y. (2026). Conversational Closing Automata, Objection-Handling Information Gain and High-Ticket Sales Kinetics: Diagnostic Question Trees, Trust-Threshold Stopping Rules and AI Closer Escalation Protocols [对话式成交自动机、异议消解信息增益与高客单销售动力学] (Version 1.0.0). 5D Library. https://doi.org/10.5281/zenodo.24090221 · Licensed under Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0).