PROJECT 021 · PYTHON SOURCE

Call duration leakage audit

Study-specific code. Shared modules, dependency versions, and reproduction instructions are included in all project files.

from pathlib import Path
import sys
ROOT = Path(__file__).resolve().parents[2]
sys.path.insert(0, str(ROOT))
import numpy as np
import pandas as pd
from scipy.stats import spearmanr
from sklearn.decomposition import PCA
from sklearn.ensemble import IsolationForest
from sklearn.preprocessing import StandardScaler
from sklearn.metrics import confusion_matrix, precision_score, recall_score
from portfolio.data import load
from portfolio.constants import *
from portfolio.methods import result, sql, rates, associations, distribution, regression, classification, cluster
from portfolio.engine import execute

META = {'id': 21, 'dataset': 'bank', 'title': 'Call duration leakage audit', 'question': 'How much does unavailable call-duration information change retrospective model scores?', 'method': 'Paired comparison with identical chronological test rows and duration included only in the diagnostic variant.', 'action': 'Reject duration from any pre-call model even if the retrospective score rises.', 'limitations': 'Observational marketing records do not identify campaign uplift. Month and row order are not precise timestamps; repeated-client identifiers are unavailable. Models are research diagnostics, not financial eligibility or automated contact decisions. '}

def analyze():
    df = load('bank').copy()
    a,pa,ea=classification(df,BANK_FEATURES,'subscribed',split='ordered')
    b,pb,eb=classification(df,BANK_FEATURES+['duration'],'subscribed',split='ordered')
    assert pa.row_id.equals(pb.row_id)
    t=pd.concat([a.assign(information='Pre-call'),b.assign(information='Includes completed duration')])
    t['variant']=t.information+' / '+t.model
    out=result(t,'variant','average_precision','Average precision','The duration variant is intentionally invalid for pre-call use. Any score increase illustrates an information-timing problem.',extra={'comparison':t},evaluation=ea)
    return out

if __name__ == "__main__":
    execute(Path(__file__).parent, META, analyze)