AI 招募偏誤

# AI 招募工具之最低偏誤稽核
# 基於 NYC Local Law 144 與 EEOC 指引
 
def bias_audit(predictions: list[dict]) -> dict:
    """計算選擇率與不成比例影響比率。"""
    from collections import defaultdict
 
    groups = defaultdict(lambda: {"selected": 0, "total": 0})
    for pred in predictions:
        for attr in ["race", "gender", "age_group"]:
            group = pred.get(attr, "unknown")
            groups[f"{attr}:{group}"]["total"] += 1
            if pred["selected"]:
                groups[f"{attr}:{group}"]["selected"] += 1
 
    # 計算選擇率
    rates = {}
    for group, counts in groups.items():
        rates[group] = counts["selected"] / counts["total"] if counts["total"] > 0 else 0
 
    # 計算不成比例影響比率（four-fifths 法則）
    # 對每個受保護屬性，將每個群體與最高率比較
    disparate_impact = {}
    for attr in ["race", "gender", "age_group"]:
        attr_rates = {g: r for g, r in rates.items() if g.startswith(attr)}
        if attr_rates:
            max_rate = max(attr_rates.values())
            for group, rate in attr_rates.items():
                ratio = rate / max_rate if max_rate > 0 else 0
                disparate_impact[group] = {
                    "selection_rate": rate,
                    "ratio": ratio,
                    "four_fifths_violation": ratio < 0.8,
                }
 
    return disparate_impact