PROJECT 023 · PYTHON SOURCE

Campaign ranking under capacity limits

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': 23, 'dataset': 'bank', 'title': 'Campaign ranking under capacity limits', 'question': 'What precision and recall would observed rankings yield when reviewing a fixed fraction of records?', 'method': 'Top-fraction lift curve using the fixed logistic model on later records.', 'action': 'Choose a review capacity using operational costs and validate that choice on a fresh period.', '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()
    scores,p,e=classification(df,BANK_FEATURES,'subscribed',split='ordered')
    p=p.sort_values('Logistic regression probability',ascending=False)
    rows=[]
    for fraction in [.05,.1,.2,.3,.5,1.]:
        n=max(1,int(np.ceil(len(p)*fraction)));head=p.head(n)
        rows.append({'review_fraction':fraction,'reviewed':n,'precision':head.actual.mean(),'recall':head.actual.sum()/p.actual.sum(),'lift':head.actual.mean()/p.actual.mean()})
    t=pd.DataFrame(rows)
    out=result(t,'review_fraction','lift','Lift versus random review','This does not estimate the causal benefit of calling; all records come from past campaigns.',evaluation=e)
    return out

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