Forecast Workforce Needs with Data-Driven Models

This is a workforce-planning skill for modeling headcount demand, gaps, and scenarios data-drivenly, covering bottom-up capacity planning (workload hours divided by effective per-FTE capacity, with a 10% buffer for growth and variability), top-down ratio-based forecasting (headcount derived from revenue-to-FTE ratios that differ by role, e.g. $800K revenue per sales FTE versus $400K per engineering FTE), and gap analysis that nets current headcount against expected attrition to derive a hiring need or surplus:

def workforce_gap_analysis(current_inventory, future_demand, attrition_forecast):
    """
    Comprehensive gap analysis including attrition impact
    """
    analysis = {}
    
    for role in future_demand.keys():
        current_count = current_inventory.get(role, 0)
        projected_demand = future_demand[role]
        expected_attrition = current_count * attrition_forecast.get(role, 0.15)
        
        net_current = current_count - expected_attrition
        gap = projected_demand - net_current
        
        analysis[role] = {
            'current_headcount': current_count,
            'projected_demand': projected_demand,
            'expected_attrition': expected_attrition,
            'net_available': net_current,
            'hiring_need': max(0, gap),
            'surplus': max(0, -gap),
            'gap_percentage': (gap / projected_demand) * 100 if projected_demand > 0 else 0
        }
    
    return analysis

For uncertainty, it runs a Monte Carlo simulation that applies random market-volatility, product-uncertainty, and execution-risk factors to a base demand figure across, by default, 1,000 simulations, returning a planning range as the 10th-90th percentile of simulated demand rather than a single point estimate.

Use this skill when building a data-driven workforce plan tied to business objectives (revenue targets, productivity ratios) rather than an intuition-based headcount request - it explicitly links workforce planning to financial planning cycles and recommends monthly dashboards tracking actual versus planned headcount, leading indicators (offer-acceptance rate, time-to-fill, pipeline health), and quarterly stakeholder review sessions to validate assumptions. It also calls for sensitivity analysis on key assumptions like attrition rates and productivity metrics, and documenting all modeling assumptions for audit purposes. It is not a recruiting or ATS skill itself - it's scoped to the demand-forecasting and gap-analysis layer, so it isn't the right fit for the actual sourcing, screening, or hiring workflow, though it recommends integrating with HRIS and ATS systems for data.

Input is historical hiring, attrition, and performance data, revenue forecasts, current headcount by role, and named uncertainty factors; output is a required-FTE figure from either bottom-up workload or top-down revenue ratios, a per-role gap analysis (hiring need or surplus, with a gap percentage), and a Monte Carlo-derived planning range (mean, p10/p50/p90 percentiles, standard deviation) rather than a single deterministic forecast.

Designed to integrate with HRIS, ATS, and financial planning systems for real-time data, built on pandas/numpy for multi-year forecasting tables and statistical calculations, and using standard Monte Carlo simulation via Python's random module.

HR, finance, and workforce-planning teams building headcount forecasts and gap analyses tied to business metrics, who want bottom-up, top-down, and scenario-based models combined rather than a single deterministic headcount number.