Age/Gender Risk Adjustment Engine

python
# Age/Gender Risk Adjustment Model
age_gender_factors = {
    'M_0-4': 0.52, 'F_0-4': 0.48,
    'M_5-9': 0.28, 'F_5-9': 0.26,
    'M_10-14': 0.31, 'F_10-14': 0.35,
    'M_15-19': 0.42, 'F_15-19': 0.58,
    'M_20-24': 0.48, 'F_20-24': 0.91,  # Female pregnancy costs
    'M_25-29': 0.51, 'F_25-29': 1.12,
    'M_30-34': 0.58, 'F_30-34': 1.24,
    'M_35-39': 0.69, 'F_35-39': 1.18,
    'M_40-44': 0.84, 'F_40-44': 1.08,
    'M_45-49': 1.12, 'F_45-49': 1.22,
    'M_50-54': 1.48, 'F_50-54': 1.42,
    'M_55-59': 1.95, 'F_55-59': 1.78,
    'M_60-64': 2.58, 'F_60-64': 2.24,
    'M_65+': 3.12, 'F_65+': 2.88
}

def calculate_risk_adjusted_costs(population):
    # Calculate Population Risk Score
    total_risk = 0
    for member in population:
        age_band = get_age_band(member.age)
        gender = member.gender
        risk_factor = age_gender_factors[f'{gender}_{age_band}']
        total_risk += risk_factor
    
    avg_risk = total_risk / len(population)
    
    # Risk-Adjust Actual Costs
    actual_costs_pmpy = calculate_total_costs(population) / len(population)
    risk_adjusted_costs = actual_costs_pmpy / avg_risk
    
    return {
        'population_size': len(population),
        'avg_age': calculate_avg_age(population),
        'pct_female': calculate_female_pct(population),
        'population_risk_score': avg_risk,
        'actual_costs_pmpy': actual_costs_pmpy,
        'risk_adjusted_costs_pmpy': risk_adjusted_costs
    }

# Example: Two Populations
# Tech Startup:
#   - Avg age: 28, 45% female
#   - Population risk score: 0.72
#   - Actual PMPY: $6,000
#   - Risk-adjusted PMPY: $8,333 ($6K / 0.72)
#
# Manufacturing:
#   - Avg age: 52, 25% female
#   - Population risk score: 1.55
#   - Actual PMPY: $11,000
#   - Risk-adjusted PMPY: $7,097 ($11K / 1.55)
#
# Conclusion: Manufacturing is MORE efficient when adjusted
# for their older, higher-risk workforce