entrepreneur-readiness-synthetic

Entrepreneur Readiness Regressor (Synthetic)

This is a synthetic RandomForest regression model trained to predict an entrepreneurial readiness score (1–10) based on financial, demographic, and skill-related features.

✨ Model Description

• Algorithm: RandomForestRegressor (scikit-learn)
• Input features:
  • savings_amount
  • monthly_income
  • monthly_expenses
  • monthly_entertainment
  • sales_skills_1to10
  • age
  • dependents
  • assets_count
  • risk_tolerance_1to10
  • confidence_1to10
  • business_idea_difficulty_1to10
  • disposable_income
  • runway_months
  • income_stability_1to10
  • prior_experience_years
  • credit_score
• Target: readiness_score_1to10 (continuous)

📊 Training

• Dataset: Entrepreneur Readiness (Synthetic)
• Rows: 500 (synthetic, no PII, generated programmatically)
• Split: 80% train, 20% test

✅ Performance

On held-out test set:

• Mean Absolute Error (MAE): ~0.7–1.0 (on 1–10 scale)
• R² score: ~0.8 (depends slightly on seed/training run)

⚠️ Note: This dataset is synthetic, so metrics are illustrative only.

🚀 Usage

import joblib, json
import numpy as np
from huggingface_hub import hf_hub_download

# Download artifacts
model_path = hf_hub_download("SpringyBon/entrepreneur-readiness-regressor", "model.joblib")
feat_path = hf_hub_download("SpringyBon/entrepreneur-readiness-regressor", "feature_names.json")

reg = joblib.load(model_path)
with open(feat_path) as f:
    FEATURES = json.load(f)

# Example prediction
sample = {
    "savings_amount": 25000,
    "monthly_income": 5000,
    "monthly_expenses": 3000,
    "monthly_entertainment": 200,
    "sales_skills_1to10": 7,
    "age": 32,
    "dependents": 1,
    "assets_count": 2,
    "risk_tolerance_1to10": 6,
    "confidence_1to10": 8,
    "business_idea_difficulty_1to10": 5,
    "disposable_income": 2000,
    "runway_months": 12,
    "income_stability_1to10": 7,
    "prior_experience_years": 4,
    "credit_score": 710
}

x = [sample[f] for f in FEATURES]
pred = reg.predict(np.array(x).reshape(1, -1))[0]
print("Predicted readiness score:", round(pred, 2))