Startup Survival Prediction
Estimates the probability that a startup survives, from what is known at founding time.
model
LogisticRegression
version
1.0.0
ROC-AUC
0.7469
F1
0.7436
recall
0.6965
trained on
48000
startups
Circumstance and luck
macro climate
market size score
competition intensity
Founder background
founder prior exits
domain experience years
Founding team
cofounder conflict
team completeness
Execution
product market fit score
did customer validation
No
Yes
premature scaling
No
Yes
unit economics score
marketing effectiveness
Funding and cash
funding path
angel
bootstrapped
vc seed
vc series a plus
total raised usd
monthly burn rate
runway months
Context
industry
agriculture
biotech
consumer app
ecommerce
fintech
food bev
hardware
healthtech
marketplace
services
tech saas
departamento
Amazonas
Ancash
Apurimac
Arequipa
Ayacucho
Cajamarca
Callao
Cusco
Huancavelica
Huanuco
Ica
Junin
La Libertad
Lambayeque
Lima
Loreto
Madre de Dios
Moquegua
Pasco
Piura
Puno
San Martin
Tacna
Tumbes
Ucayali
Predict survival
What predicts survival
ROC-AUC of a model trained with each group of variables on its own, and how much is lost when that group is removed from the full model.
Group
Alone
Lost if removed
Execution
0.6465
-0.0449
Funding and cash
0.6420
-0.0470
Circumstance and luck
0.5974
-0.0187
Founding team
0.5702
-0.0112
Founder background
0.5430
-0.0039
Context
0.5347
-0.0030