Venture Capital Risk Scoring

Predict startup investment risk scores using panel data with 20 startups tracked over 18 time periods.

Dataset Exploration

The Venture Capital dataset contains investment data and startup performance metrics over time. Features include burn rate, revenue growth, customer churn, founder experience, and industry risk level.

Panel data structure: 20 startups tracked over 18 time periods (360 total rows, 9 columns).

Fit Data (first 5 rows)

Time	Individual	Burnrate	Revenue Growth	Customer Churn	Burnrate×Rev.Growth	Founder Exp.	Industry Risk	Risk Score
1	1	35	22.05	9	771.75	7	1	24.42
2	1	39	27.12	13	1057.68	7	1	24.63
3	1	41	25.14	17	1030.74	7	1	32.27
4	1	44	12.51	19	550.44	7	1	36.07
5	1	45	23.09	21	1039.05	7	1	31.46

Forecast Data (first 3 rows)

The forecast file covers future periods without the Risk Score target column.

Time	Individual	Burnrate	Revenue Growth	Customer Churn	Burnrate×Rev.Growth	Founder Exp.	Industry Risk
19	1	27	21.14	13	570.78	10	3
20	1	28	10.88	14	304.64	10	3
21	1	32	14.67	18	469.44	10	3

Download sample datasets from GitHub

Code Walkthrough

Step 1: Initialize

Python

import pandas as pd
from datfid import DATFIDClient

client = DATFIDClient(token="your_DATFID_token")

Step 2: Fit the Model

Python

url_fit = "https://raw.githubusercontent.com/datfid-valeriidashuk/sample-datasets/main/Venture_Capital.xlsx"
df = pd.read_excel(url_fit)

result = client.fit_model(
    df=df,
    id_col="Individual",
    time_col="Time",
    y="Risk Score",
    current_features="all",
    filter_by_significance=True
)

Step 3: Forecast

Python

url_forecast = "https://raw.githubusercontent.com/datfid-valeriidashuk/sample-datasets/main/Venture_Capital_forecast.xlsx"
df_forecast = pd.read_excel(url_forecast)

forecast = client.forecast_model(df_forecast=df_forecast)

Analysis Results (Model Fit)

Formula

Risk Score ~ α1*Intercept + α2*Industry Risk Level + α3*Founder Experience + β1*Burnrate + β2*Revenue Growth + β3*Customer Churn

Alpha Estimates (Time-Invariant)

Variable	Estimate	T-stat	Interpretation
Intercept	12.39	15.54	Baseline risk score
Founder Experience	-0.242	2.83	More experienced founders reduce risk score by ~0.24 per year
Industry Risk Level	+0.181	0.99	Not statistically significant (p=0.32)

Beta Estimates (Time-Varying)

Variable	Estimate	T-stat	Interpretation
Revenue Growth	-0.352	14.63	Higher revenue growth reduces risk score (strongest dynamic predictor)
Burnrate	+0.461	5.71	Higher burn rate increases risk score by ~0.46 per unit
Customer Churn	+0.422	5.22	Higher churn increases risk by ~0.42 per unit

Model Performance

0.847

R² Overall

0.944

R² Between

0.833

R² Within

3.89

MAE

22.93

MSE

Try it yourself: Select "Venture Capital" in the Free Playground.