5D Library › Short-Video Completion Hazards, Recommender Exploration Loops and Automated Acquisition Funnels · 中文
Chapter 1. The Kinetics of Swiping: a Weibull Hazard
Swiping as a hazard
Once a short video starts, a viewer may swipe away at any moment. Let be the time a viewer stays; the retention function is the share still watching at second , and the hazard is the rate at which those who have reached second leave in the next instant. The standard practice of survival analysis is to choose a distribution for (Klein and Moeschberger 2003); the Weibull distribution (Weibull 1951) has retention and hazard
With shape the hazard falls over time: swipes cluster at the start, and those who stay become ever less likely to leave. This is the typical shape for short video. With it reduces to the exponential distribution with a constant hazard.
Calculation
# Chapter 1. p01: Weibull swipe-away kinetics and completion rates.
# The time a viewer stays on a short video is modelled as Weibull with
# shape k and scale L (seconds): survival S(t) = exp(-(t / L)^k),
# hazard h(t) = (k / L) (t / L)^(k - 1). With k < 1 the hazard falls
# over time: most swipes come in the first seconds, and those who stay
# become ever less likely to leave. For a video of length D:
# completion rate = S(D);
# mean watch time = integral of S(t) from 0 to D (midpoint rule);
# watch fraction = mean watch time / D.
# An exponential model (k = 1) tuned to the same 5-second retention is
# shown for contrast. Last, k and L are recovered from two retention
# readings, since ln(-ln S) = k ln t - k ln L is a straight line.
import math
def surv(t, k, L):
return math.exp(-(t / L) ** k)
def haz(t, k, L):
return (k / L) * (t / L) ** (k - 1)
def mean_watch(D, k, L, n=4000):
return sum(surv((i + 0.5) * D / n, k, L) for i in range(n)) * D / n
if __name__ == "__main__":
k, L = 0.6, 20.0
s5 = surv(5, k, L)
Le = -5 / math.log(s5)
print(" Weibull k = {}, L = {} s".format(k, L))
print(" retention at 3 s {:.3f}, at 5 s {:.3f}".format(
surv(3, k, L), s5))
print(" hazard per second at 1, 5, 20 s: {:.3f}, {:.3f}, {:.3f}".format(
haz(1, k, L), haz(5, k, L), haz(20, k, L)))
print(" exponential with the same 5 s retention: scale {:.2f} s"
.format(Le))
print("\n length D completion mean watch watch frac exp compl")
for D in (7, 15, 30, 60, 90):
mw = mean_watch(D, k, L)
print(" {:6d} s {:12.3f} {:10.1f} s {:12.3f} {:11.3f}".format(
D, surv(D, k, L), mw, mw / D, surv(D, 1.0, Le)))
t1, t2 = 3.0, 15.0
a1 = math.log(-math.log(surv(t1, k, L)))
a2 = math.log(-math.log(surv(t2, k, L)))
kk = (a2 - a1) / (math.log(t2) - math.log(t1))
LL = math.exp(math.log(t1) - a1 / kk)
print("\n recovered from retention at 3 s and 15 s:")
print(" k = {:.3f}, L = {:.2f}".format(kk, LL))
print("\nReading: with a falling hazard, a 60 s video keeps far more")
print("viewers to the end than an exponential model with the same")
print("first five seconds predicts. Completion rate punishes length,")
print("but much less than intuition suggests; two retention points")
print("are enough to fit both parameters.")
# Weibull k = 0.6, L = 20.0 s
# retention at 3 s 0.726, at 5 s 0.647
# hazard per second at 1, 5, 20 s: 0.099, 0.052, 0.030
# exponential with the same 5 s retention: scale 11.49 s
#
# length D completion mean watch watch frac exp compl
# 7 s 0.587 5.1 s 0.723 0.544
# 15 s 0.431 9.1 s 0.605 0.271
# 30 s 0.279 14.3 s 0.476 0.073
# 60 s 0.145 20.3 s 0.339 0.005
# 90 s 0.085 23.7 s 0.263 0.000
#
# recovered from retention at 3 s and 15 s:
# k = 0.600, L = 20.00
#
# Reading: with a falling hazard, a 60 s video keeps far more
# viewers to the end than an exponential model with the same
# first five seconds predicts. Completion rate punishes length,
# but much less than intuition suggests; two retention points
# are enough to fit both parameters.With and seconds, retention is 0.726 at 3 seconds and 0.647 at 5 seconds; the hazard is 0.099 per second at second 1 and 0.030 at second 20. A 15-second video has completion rate 0.431, a 60-second one 0.145; an exponential model with the same 5-second retention (scale 11.49 seconds) would give the 60-second video only 0.005. A falling hazard means that completion does punish length, but far less harshly than intuition suggests. Mean watch time grows with length: a 60-second video is watched for 20.3 seconds on average, though its watch fraction falls to 0.339. Finally, the program recovers and from just two retention readings, at 3 and 15 seconds, because is a straight line in .
Are mid-video re-hooks worth it?
“Re-hook every few seconds” is common editing advice. The program assumes each re-hook cuts the hazard by seventy percent for the 2 seconds that follow, but viewers learn and tire: re-hooks per minute raise the hazard of the whole video by a share .
Calculation
# Chapter 1. p02: Re-hook pulses: how often should a video re-hook?
# Baseline hazard: Weibull k = 0.6, L = 20 s, as in p01, for a 60 s
# video. A re-hook (a question, a cut, a promise of what comes next)
# placed every H seconds lowers the hazard by a factor (1 - r) for the
# w = 2 s that follow it. Re-hooks also wear: with n hooks per minute
# the whole hazard rises by a share c n^2 (viewers learn the trick and
# tire of it). With r = 0.7 and c = 0.002 the program integrates the
# cumulative hazard on a 0.01 s grid and reports completion and mean
# watch time.
import math
K, L, D = 0.6, 20.0, 60.0
def base(t):
return (K / L) * (t / L) ** (K - 1)
def run(H, r=0.7, w=2.0, c=0.002, dt=0.01):
per_min = 0.0 if H is None else 60.0 / H
lift = 1 + c * per_min ** 2
cum, watch, t = 0.0, 0.0, 0.0
while t < D:
tm = t + dt / 2
h = base(tm) * lift
if H is not None and tm >= H and (tm % H) < w:
h *= 1 - r
watch += math.exp(-cum - h * dt / 2) * dt
cum += h * dt
t += dt
return math.exp(-cum), watch
if __name__ == "__main__":
print(" hook every hooks/min completion mean watch (s)")
for H in (None, 30, 20, 15, 10, 6, 4, 3):
comp, mw = run(H)
print(" {:>10s} {:11.1f} {:12.3f} {:14.1f}".format(
"none" if H is None else "{} s".format(H),
0.0 if H is None else 60.0 / H, comp, mw))
print("\nReading: re-hooks after the opening buy only a little,")
print("because with a falling hazard most viewers who will swipe")
print("have already swiped before the first re-hook arrives. Hooks")
print("closer than every 10 s lose ground, and at every 4 s the")
print("video does worse than with none.")
print("The opening seconds, not the middle, decide completion.")
# hook every hooks/min completion mean watch (s)
# none 0.0 0.145 20.4
# 30 s 2.0 0.148 20.4
# 20 s 3.0 0.151 20.5
# 15 s 4.0 0.153 20.5
# 10 s 6.0 0.155 20.5
# 6 s 10.0 0.150 19.9
# 4 s 15.0 0.136 18.4
# 3 s 20.0 0.122 16.8
#
# Reading: re-hooks after the opening buy only a little,
# because with a falling hazard most viewers who will swipe
# have already swiped before the first re-hook arrives. Hooks
# closer than every 10 s lose ground, and at every 4 s the
# video does worse than with none.
# The opening seconds, not the middle, decide completion.Without re-hooks completion is 0.145; one every 10 seconds gives the best value, 0.155; packing them closer loses ground, and at one every 4 seconds completion is 0.136, worse than none. The gain is small for the same reason as above: under a falling hazard, most viewers who will swipe have already swiped before the first re-hook arrives. The opening seconds, not the middle, decide completion.
Hypothesis · not established
Testable consequence. If the swipe hazard really falls over time, the retention curves of one account’s videos should be close to straight lines in against , with slope below 1; improving the opening should clearly raise 5-second retention, while re-hooks added after second 20 should change completion only slightly. What would show this wrong: if the slopes are near or above 1, or mid-video re-hooks give gains comparable to a better opening, this chapter’s model does not fit that account.
Summary
Swiping can be written as a Weibull hazard; for short video the hazard falls over time, so the opening decides almost everything, and completion punishes length far more gently than an exponential model. Two retention readings fit both parameters. Mid-video re-hooks gain little, and too many do harm.
References
Fan, Y. (2026). Short-Video Completion Hazards, Recommender Exploration Loops and Automated Acquisition Funnels: Weibull Swipe-Away Kinetics, Multi-Stage Pool Promotion Thresholds and Traffic-to-Cashflow Conversion Bounds [短视频完播率风险函数、推荐反馈环与自动化获客漏斗] (Version 1.0.0). 5D Library. https://doi.org/10.5281/zenodo.24090213 · Licensed under Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0).