关于「72 小时联合快闪:真实库存、真实截止与退款准备金」,《异业联营拆账与频次保护》给出的定量结论是什么?

结论:第六章排一场 72 小时联合快闪:真实库存与真实截止下售罄概率 0.3195,退款准备金按 99% 分位计提为 1,656。

数据口径:纳什议价解先还双方的破裂点,再平分合作红利,五五分只是破裂点对称时的特例;示意参数下,渠道方单干 2,000、操盘方单干 6,000 时,渠道方份额是 0.433。 频次方面,示意名单推 8 次比推 3 次成交多不到一倍,流失成员却是 7.453 倍;一次性操盘方的最优推送会让十二个月联合价值损失 0.1468。

English version

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: 0.3195, 72

with deadline: orders p05 87 p50 105 p95 110
   mean orders by day 52.6 / 23.0 / 27.0
   P(sell out by hour 72) 0.3195; median sell-out hour 71.0
no deadline: orders p05 81 p50 97 p95 110
   mean orders by day 53.0 / 23.1 / 20.4
   P(sell out by hour 72) 0.1050; median sell-out hour 70.0
expected orders without stock limit: 104.9; last 6 h share 0.200
查看完整验算程序
# Chapter 6. p61: a 72-hour co-launch with real stock and a real deadline.
# Three pushes: launch at hour 0, reminder at hour 40, last notice at
# hour 66; the deadline at hour 72 is fixed and never reset. Each push
# p adds orders at rate A_p * exp(-(t - t_p) / TAU) per hour; the
# genuine deadline adds B * exp(-(72 - t) / 2) in the last hours
# (deadline effects: Roth et al. 1988; Kuppuswamy and Bayus 2017).
# Real stock K = 110 units (delivery capacity); orders stop at K.
# Hourly Poisson draws, fixed seed, 2,000 runs. Rates are illustrative.
# Pre-registered band for the last-6-hour share: 0.10 to 0.30.
import math
import random
import statistics

PUSHES = [(0, 9.0), (40, 5.0), (66, 3.5)]
TAU, B, K, HOURS, RUNS = 6.0, 4.0, 110, 72, 2000


def rate(t, deadline=True):
    terms = [a * math.exp(-(t - tp) / TAU) for tp, a in PUSHES if t >= tp]
    if deadline:
        terms.append(B * math.exp(-(HOURS - t) / 2.0))
    return math.fsum(terms)


def poisson(rng, lam):
    limit, k, p = math.exp(-lam), 0, 1.0
    while True:
        p *= rng.random()
        if p <= limit:
            return k
        k += 1


def one_run(rng, deadline=True):
    sold, by_day, sellout = 0, [0, 0, 0], None
    for h in range(HOURS):
        n = min(poisson(rng, rate(h + 0.5, deadline)), K - sold)
        sold += n
        by_day[h // 24] += n
        if sold >= K and sellout is None:
            sellout = h + 1
    return sold, by_day, sellout


if __name__ == "__main__":
    rng = random.Random(20261120)
    for label, flag in (("with deadline", True), ("no deadline", False)):
        res = [one_run(rng, flag) for _ in range(RUNS)]
        tot = sorted(r[0] for r in res)
        days = [statistics.fmean(r[1][d] for r in res) for d in range(3)]
        outs = [r[2] for r in res if r[2] is not None]
        print("{}: orders p05 {} p50 {} p95 {}".format(
            label, tot[100], tot[1000], tot[1899]))
        print("   mean orders by day {:.1f} / {:.1f} / {:.1f}".format(*days))
        med = statistics.median(outs) if outs else 0
        print("   P(sell out by hour 72) {:.4f}; median sell-out hour {:.1f}"
              .format(len(outs) / RUNS, float(med)))
    last6 = math.fsum(rate(h + 0.5) for h in range(66, 72))
    allh = math.fsum(rate(h + 0.5) for h in range(72))
    print("expected orders without stock limit: {:.1f}; last 6 h share "
          "{:.3f}".format(allh, last6 / allh))

唯一数据源与引用

范雅福(Fan, Y.). (2026). 《异业私域联营拆账、技术换流量零本金借船与联合发售脉冲母典》第 6 章「72 小时联合快闪:真实库存、真实截止与退款准备金」(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-371 · v1.0.0 · CC-BY-NC-ND-4.0

BibTeX
@book{fan2026371,
  author    = {Fan, Yafu},
  title     = {Joint-Venture Audience Monetisation, Tech-for-Traffic Barter Structures and Co-Launch Revenue Waterfalls},
  year      = {2026},
  publisher = {5D Library},
  edition   = {1.0.0},
  note      = {DOI pending}
}

本书其他章节结论