{ "cells": [ { "cell_type": "markdown", "id": "b9ea3e61", "metadata": {}, "source": [ "**Author:** Dr. Mallarapu \n", "**Created:** 2026-07-27 \n", "**Course:** SEAS 8414 \u2014 Security Analytics\n", "\n", "---\n", "\n", "### Goal of this notebook\n", "\n", "Train and audit fraud detectors on real IEEE-CIS e-commerce transactions.\n", "\n", "### What you will learn\n", "\n", "1. Read a majority-class baseline before trusting any accuracy figure.\n", "2. Find the strongest single feature, then test it by dropping it and refitting.\n", "3. Tell duplicate inflation apart from genuine signal.\n", "4. Report per-group recall, because the rare classes carry the risk.\n", "5. Compare a realistic score against the near-perfect ones elsewhere in this series.\n", "\n", "### Where this connects to the course text\n", "\n", "The text builds a defence pipeline; this notebook trains a classifier and audits it. The links below are to specific chapter objectives that share an *analytic move*, not to matching subject matter.\n", "\n", "- **Chapter 4: Attack Graph Analytics** \u2014 Learning objective 5 (section 4.1) separates a **one-at-a-time** perturbation from the smallest perturbation that reverses a ranking, and warns the first **overstates stability**. Dropping only the top feature and refitting is exactly that weaker test, so read it as a floor.\n", "- **Chapter 11: Formal Protocol Verification** \u2014 Section **11.1.2**, titled *Proved, tested, and hoped*, asks you to separate exactly those three. (Chapter 11 lists its objectives in \u00a711.0, not \u00a711.1 as the other chapters do.) The ablation does that job here: it tests whether the headline survives.\n", "\n", "---" ] }, { "cell_type": "markdown", "id": "edfbf874", "metadata": {}, "source": [ "# Real E-Commerce Card-Fraud Detection on IEEE-CIS (Vesta)\n", "### Model comparison + per-product recall + validity audit (590k real transactions)\n", "\n", "**Abstract:** The IEEE-CIS Fraud Detection dataset (Vesta Corporation, 2019) is **real** e-commerce card-transaction data. It holds 590k labelled transactions with ~390 features, from card and address fields to anonymized Vesta engineered features. Unlike the synthetic PaySim (nb15) and Sparkov (nb16) sets, this is production fraud at a realistic ~3.5% base rate. We compare four learners, report recall **per product code**, and audit whether the score is genuine fraud signal or an artifact of the anonymized features." ] }, { "cell_type": "markdown", "id": "9e9ff91c", "metadata": {}, "source": [ "## 1. Research problem\n", "\n", "**Task:** Flag a transaction as fraud from card/address/email metadata and Vesta's engineered features. Fraud is rare (~3.5%), so accuracy is meaningless. The operative trade-off is catching fraud (recall) without swamping analysts or blocking legitimate customers (precision / false-positive rate). That trade-off varies sharply by product type." ] }, { "cell_type": "markdown", "id": "086120ed", "metadata": {}, "source": [ "## 2. Literature review\n", "\n", "- **Dal Pozzolo, Boracchi, Caelen, Alippi & Bontempi (2018)** \u2014 *Credit Card Fraud Detection: A Realistic Modeling and a Novel Learning Strategy* (IEEE TNNLS). Realistic evaluation under concept drift and extreme imbalance.\n", "- **Bahnsen et al. (2016)** \u2014 feature-engineering strategies for card fraud.\n", "- **IEEE-CIS / Vesta (2019)** \u2014 the Kaggle competition and dataset used here.\n", "- **Sommer & Paxson (2010)** \u2014 the closed-world ML critique.\n", "\n", "**Related approaches and their known caveats** \u2014 drawn from the wider literature; these are **not** measurements reproduced on this exact corpus:\n", "\n", "| Reported approach | Known caveat |\n", "|---|---|\n", "| IEEE-CIS competition leaders \u2014 gradient boosting (XGB/LightGBM) | heavy feature engineering + time-aware validation; leaderboard is AUC on a hidden split |\n", "| Realistic card-fraud modeling (Dal Pozzolo et al., 2018) | concept drift + imbalance make static splits optimistic |\n" ] }, { "cell_type": "markdown", "id": "ab12ba97", "metadata": {}, "source": [ "## 3. Dataset provenance & honesty caveats\n", "\n", "| Property | Value |\n", "|---|---|\n", "| Source | Kaggle `lnasiri007/ieeecis-fraud-detection` (Vesta data mirror) |\n", "| Rows | 590,540 labelled transactions (`train_transaction`) |\n", "| Label | `isFraud` 0/1 (~3.5% fraud) |\n", "| Grouping | `family` = `ProductCD` (W/C/H/R/S) \u2014 a product code, not an attack family |\n", "| Access | Kaggle API token required |\n", "\n", "**Honestly:** many features are **anonymized** (V1\u2013V339). So we can audit *whether* a single feature carries the score, but not always name the mechanism. `TransactionID` and the raw time offset are dropped as identifiers. A random split ignores the temporal concept drift that Dal Pozzolo et al. show dominates real card fraud \u2014 the honest generalization test is time-ordered, which we flag but do not run.\n", "\n", "### Before you run this: getting the data\n", "\n", "This notebook downloads its own data on the first run, then caches it. You do not fetch anything by hand.\n", "\n", "**Dataset:** Kaggle `lnasiri007/ieeecis-fraud-detection` -> `/tmp/kg_ieeecis`. It is about **1 GB** on disk.\n", "\n", "**One-time setup.** Sign in at kaggle.com, open **Settings**, and under **API** choose **Create New Token**. Kaggle hands you a `kaggle.json` file. This notebook does *not* read that file. It reads a plain key file, so convert it once:\n", "\n", "```bash\n", "mkdir -p ~/.kaggle\n", "python3 -c \"import json;print(json.load(open('kaggle.json'))['key'],end='')\" > ~/.kaggle/access_token\n", "chmod 600 ~/.kaggle/access_token\n", "```\n", "\n", "Never paste the token into a cell, a commit, or a screenshot. If it leaks, revoke it from the same Settings page.\n", "\n", "**If the loader fails:**\n", "\n", "- `FileNotFoundError: ~/.kaggle/access_token` - you created `kaggle.json` but not the key file. Run the command above.\n", "- `401 Unauthorized` - the key is wrong, or a trailing newline crept in.\n", "- `403 Forbidden` - open the dataset page on Kaggle while signed in, accept its terms, then re-run the cell.\n", "\n", "The cache sits under `/tmp`, which macOS clears on reboot. To keep it, move the folder somewhere durable and symlink it back. Do **not** edit the path in the code cell below: that changes a code cell and invalidates the stored outputs you are reviewing." ] }, { "cell_type": "markdown", "id": "0169cf87", "metadata": {}, "source": [ "## 4. Solution design\n", "\n", "The methodology is deliberately two-track. We *earn* a headline score with standard modelling, then *interrogate* it with a validity audit. Only a verdict that survives both is reported. The diagram below is the shape of every notebook in this series." ] }, { "cell_type": "markdown", "id": "996d4b40", "metadata": {}, "source": [ "**Figure 4.1 \u2014 Solution design (methodology).**\n", "\n", "\"Figure" ] }, { "cell_type": "markdown", "id": "75daae48", "metadata": {}, "source": [ "## 5. Implementation architecture\n", "\n", "Five stages \u2014 ingestion, preprocessing, modelling, evaluation, and a parallel validity-audit path \u2014 feed a single graded results ledger. Leakage defences (dropping label-derived and identifier columns) live in preprocessing, before any model sees the data." ] }, { "cell_type": "markdown", "id": "5a0d7470", "metadata": {}, "source": [ "**Figure 5.1 \u2014 Implementation architecture.**\n", "\n", "\"Figure" ] }, { "cell_type": "markdown", "id": "bea5695c", "metadata": {}, "source": [ "## 6. Data acquisition & preparation\n", "\n", "Every line below is commented so a student can re-run and modify each step. The cell ends by producing the standard analysis variables. These are `df`, `X` (clean numeric features), `y` (binary label), `feat` (feature names), and `family` (the per-group label used for the recall breakdown). On this corpus `family` is `ProductCD`, Vesta's product code (W/C/H/R/S). It labels a **product stratum**, not an attack family. The variable keeps the series-wide name so the shared plotting code works unchanged." ] }, { "cell_type": "code", "execution_count": 1, "id": "e412d1e0", "metadata": {}, "outputs": [], "source": [ "%matplotlib inline\n", "import time, warnings; warnings.filterwarnings('ignore') # keep output clean\n", "import numpy as np, pandas as pd # numerics + dataframes\n", "import matplotlib.pyplot as plt # static plots (embed in HTML+PDF)\n", "plt.rcParams['figure.dpi'] = 120 # crisp figures\n", "RANDOM_STATE = 0 # single seed used everywhere\n", "np.random.seed(RANDOM_STATE) # reproducible sampling\n", "NEG_WORD, POS_WORD = 'benign', 'attack' # class names (overridden by some loaders)" ] }, { "cell_type": "code", "execution_count": 2, "id": "ee560c46", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "loaded 590,540 transactions x 391 features; fraud rate 0.0350\n" ] } ], "source": [ "import os, glob\n", "# IEEE-CIS Fraud Detection (Vesta Corporation, 2019): REAL e-commerce card-transaction fraud \u2014\n", "# 590k labelled transactions with ~390 features (card/addr/email, counting C*, timedelta D*, match\n", "# M*, and anonymized Vesta engineered V* features). Distinct from the SYNTHETIC PaySim/Sparkov sets.\n", "os.environ.setdefault('KAGGLE_KEY', open(os.path.expanduser('~/.kaggle/access_token')).read().strip())\n", "DEST = '/tmp/kg_ieeecis'; os.makedirs(DEST, exist_ok=True)\n", "if not glob.glob(DEST + '/**/train_transaction.csv', recursive=True):\n", " import kaggle; kaggle.api.authenticate()\n", " print('downloading IEEE-CIS fraud (one-time)...')\n", " kaggle.api.dataset_download_files('lnasiri007/ieeecis-fraud-detection', path=DEST, unzip=True, quiet=True)\n", "f = [x for x in glob.glob(DEST + '/**/*.csv', recursive=True) if os.path.basename(x) == 'train_transaction.csv'][0]\n", "df = pd.read_csv(f, low_memory=False); df.columns = [str(c).strip() for c in df.columns]\n", "# Use ONLY the labelled training transactions; the competition 'test' split has no labels.\n", "assert len(df) >= 400_000, f'floor not met: {len(df):,}'\n", "df['y'] = df['isFraud'].astype(int)\n", "df['family'] = df['ProductCD'].astype(str) # product code W/C/H/R/S; fraud rate varies by product\n", "# Drop the label, the row id and the raw time offset (identifiers). ProductCD stays as a feature.\n", "DROP = ['isFraud', 'y', 'family', 'TransactionID', 'TransactionDT']\n", "feat = [c for c in df.columns if c not in DROP]\n", "from sklearn.preprocessing import LabelEncoder\n", "X = df[feat].copy()\n", "idlike = [c for c in X.select_dtypes(include='object').columns if X[c].nunique() > 0.5*len(X)]\n", "X = X.drop(columns=idlike) # drop id/timestamp-like leaky columns\n", "for c in X.select_dtypes(include='object').columns:\n", " X[c] = LabelEncoder().fit_transform(X[c].astype(str))\n", "X = X.apply(pd.to_numeric, errors='coerce').replace([np.inf,-np.inf],np.nan).fillna(0.0)\n", "X = X.clip(-1e15, 1e15); X = X.loc[:, X.nunique() > 1] # float32-safe; drop constants\n", "import re\n", "_seen, _cols = {}, []\n", "for _c in X.columns: # unique LightGBM-safe names\n", " _c = re.sub(r'[^0-9A-Za-z_]+', '_', str(_c)).strip('_') or 'f'\n", " _seen[_c] = _seen.get(_c, -1) + 1\n", " _cols.append(_c if _seen[_c] == 0 else f'{_c}_{_seen[_c]}')\n", "X.columns = _cols; feat = list(X.columns)\n", "y = df['y'].to_numpy(); family = df['family'].to_numpy()\n", "print(f'loaded {len(df):,} transactions x {len(feat)} features; fraud rate {y.mean():.4f}')" ] }, { "cell_type": "markdown", "id": "4c3bcedb", "metadata": {}, "source": [ "## 7. Exploratory data analysis\n", "\n", "Two panels: the class balance, and fraud counts per product code.\n", "\n", "**Figure labels are wrong \u2014 disclosed, not fixed:** the plotting cell uses the notebook's default class words, and this loader never overrides them. So the figure reads *Class balance (benign vs attack)* and *Top attack families*. Neither word fits here. The positive class is **fraud**, not attack. The bars are **`ProductCD` product codes**, not attack families. The plotted counts are correct; only the wording is wrong. The repair is code-level \u2014 set `NEG_WORD, POS_WORD = 'legitimate', 'fraud'` and retitle the right panel \u2014 so it is not applied to this frozen run.\n", "\n", "Read the right panel as: which product code carries the most fraudulent transactions. `W` and `C` carry most of them; `H`, `R` and `S` are much smaller. Hold that ordering for \u00a79, where the same strata come back as recall." ] }, { "cell_type": "code", "execution_count": 3, "id": "a338c331", "metadata": {}, "outputs": [ { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "# --- EDA 1: class balance and the attack-family mix ---\n", "fig, ax = plt.subplots(1, 2, figsize=(11, 4))\n", "df['y'].map({0:NEG_WORD,1:POS_WORD}).value_counts().plot.bar( # counts per class\n", " ax=ax[0], color=['#2a9d8f','#e76f51']); ax[0].set_yscale('log')\n", "ax[0].set_title(f'Class balance ({NEG_WORD} vs {POS_WORD})'); ax[0].set_ylabel('records (log)')\n", "df.loc[df.y==1,'family'].value_counts().head(8).plot.barh( # top attack families\n", " ax=ax[1], color='#e76f51'); ax[1].invert_yaxis(); ax[1].set_title('Top attack families')\n", "plt.tight_layout(); plt.show()" ] }, { "cell_type": "code", "execution_count": 4, "id": "913c0c26", "metadata": {}, "outputs": [ { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "# --- EDA 2: feature correlation + a 2-D PCA projection ---\n", "from sklearn.preprocessing import StandardScaler # scale before PCA\n", "from sklearn.decomposition import PCA\n", "fig, ax = plt.subplots(1, 2, figsize=(12, 5))\n", "topv = X[feat].var().sort_values().tail(12).index # 12 highest-variance features\n", "im = ax[0].imshow(X[topv].corr(), cmap='coolwarm', vmin=-1, vmax=1) # correlation heatmap\n", "ax[0].set_xticks(range(len(topv))); ax[0].set_xticklabels(topv, rotation=90, fontsize=7)\n", "ax[0].set_yticks(range(len(topv))); ax[0].set_yticklabels(topv, fontsize=7)\n", "ax[0].set_title('Feature correlation (top-variance)'); fig.colorbar(im, ax=ax[0], shrink=0.7)\n", "samp = X.sample(min(5000, len(X)), random_state=RANDOM_STATE) # subsample for a fast PCA\n", "pc = PCA(n_components=2).fit_transform(StandardScaler().fit_transform(samp))\n", "ys = y[samp.index] # aligned labels for coloring\n", "for lab,c in [(0,'#2a9d8f'),(1,'#e76f51')]:\n", " ax[1].scatter(pc[ys==lab,0], pc[ys==lab,1], s=4, alpha=0.4, color=c,\n", " label={0:NEG_WORD,1:POS_WORD}[lab])\n", "ax[1].set_title('PCA projection (2 components)'); ax[1].legend(); ax[1].set_xlabel('PC1'); ax[1].set_ylabel('PC2')\n", "plt.tight_layout(); plt.show()" ] }, { "cell_type": "markdown", "id": "17c963d5", "metadata": {}, "source": [ "## 8. Model comparison\n", "\n", "Four diverse learners share one held-out split, ranked by ROC-AUC.\n", "\n", "**Two honesty guards print with the table:**\n", "\n", "1. The models train on a *stratified subsample* of at most 120,000 rows. The full row count is printed above. So every score here is a subsample number, not a full-corpus claim.\n", "2. The **majority-class baseline accuracy** appears *inside* the ranking table. On imbalanced data, 0.99 accuracy can be worse than always guessing the majority class. Judge each model against that baseline, not against 0.5." ] }, { "cell_type": "code", "execution_count": 5, "id": "71c0e5fb", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "materialized 590,540 rows | trained on 120,000 (stratified subsample) | held-out 147,635\n", "MAJORITY-CLASS BASELINE accuracy = 0.9650 (any model must beat THIS, not 0.5, to be interesting)\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "best model: XGBoost\n" ] }, { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
modelaccuracyroc_auctrain_s
0XGBoost0.9778370.9193801.4
1LightGBM0.9766250.9119131.7
2RandomForest0.9760690.8879722.7
3LogisticRegression0.9711650.8478012.9
4MajorityBaseline0.9650000.5000000.0
\n", "
" ], "text/plain": [ " model accuracy roc_auc train_s\n", "0 XGBoost 0.977837 0.919380 1.4\n", "1 LightGBM 0.976625 0.911913 1.7\n", "2 RandomForest 0.976069 0.887972 2.7\n", "3 LogisticRegression 0.971165 0.847801 2.9\n", "4 MajorityBaseline 0.965000 0.500000 0.0" ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# --- Model comparison: four learners on the same held-out split ---\n", "from sklearn.model_selection import train_test_split\n", "from sklearn.linear_model import LogisticRegression\n", "from sklearn.ensemble import RandomForestClassifier\n", "from sklearn.metrics import accuracy_score, roc_auc_score\n", "import xgboost as xgb, lightgbm as lgb\n", "\n", "# Stratified split keeps the class ratio in both halves.\n", "Xtr, Xte, ytr, yte = train_test_split(X, y, test_size=0.25, random_state=RANDOM_STATE, stratify=y)\n", "from sklearn.pipeline import make_pipeline\n", "from sklearn.preprocessing import StandardScaler\n", "N_MATERIALIZED = len(y) # the full corpus we loaded (see printed count)\n", "# HONEST DISCLOSURE: we do NOT train on all N. We fit on a STRATIFIED subsample (<=120k) because\n", "# these learners saturate long before then on this data. Every headline below is a SUBSAMPLE\n", "# number, not a full-corpus number \u2014 saying otherwise would be the fabrication this course forbids.\n", "if len(Xtr) > 120_000:\n", " Xtr, _, ytr, _ = train_test_split(Xtr, ytr, train_size=120_000, random_state=RANDOM_STATE,\n", " stratify=ytr) # genuinely stratified, not random\n", "MAJORITY_BASELINE = max(np.mean(yte), 1 - np.mean(yte)) # accuracy of 'always predict majority'\n", "print(f'materialized {N_MATERIALIZED:,} rows | trained on {len(Xtr):,} (stratified subsample) | '\n", " f'held-out {len(yte):,}')\n", "print(f'MAJORITY-CLASS BASELINE accuracy = {MAJORITY_BASELINE:.4f} '\n", " f'(any model must beat THIS, not 0.5, to be interesting)')\n", "\n", "models = { # four standard, diverse learners\n", " 'LogisticRegression': make_pipeline(StandardScaler(), LogisticRegression(max_iter=300)), # scaled!\n", " 'RandomForest': RandomForestClassifier(n_estimators=60, n_jobs=-1, random_state=RANDOM_STATE),\n", " 'XGBoost': xgb.XGBClassifier(n_estimators=80, max_depth=6, tree_method='hist', n_jobs=-1,\n", " eval_metric='logloss', random_state=RANDOM_STATE),\n", " 'LightGBM': lgb.LGBMClassifier(n_estimators=80, n_jobs=-1, verbose=-1, random_state=RANDOM_STATE),\n", "}\n", "rows, fitted = [], {}\n", "for name, m in models.items(): # fit + score each model\n", " t = time.perf_counter(); m.fit(Xtr, ytr); fitted[name] = m\n", " p = m.predict_proba(Xte)[:, 1] # positive-class probability on held-out\n", " rows.append({'model': name, 'accuracy': round(accuracy_score(yte, (p>0.5).astype(int)), 6),\n", " 'roc_auc': round(roc_auc_score(yte, p), 6), # 6 dp: a 1.000000 is a red flag, not a win\n", " 'train_s': round(time.perf_counter()-t, 1)})\n", "rows.append({'model': 'MajorityBaseline', 'accuracy': round(MAJORITY_BASELINE, 4),\n", " 'roc_auc': 0.5, 'train_s': 0.0}) # show the baseline IN the ranking table\n", "comparison = pd.DataFrame(rows).sort_values('roc_auc', ascending=False).reset_index(drop=True)\n", "_ranked = comparison[comparison.model != 'MajorityBaseline']\n", "best_name = _ranked.iloc[0]['model']; best = fitted[best_name] # winner by ROC-AUC (excl. baseline)\n", "print('best model:', best_name); comparison" ] }, { "cell_type": "markdown", "id": "712787c9", "metadata": {}, "source": [ "## 9. Results\n", "\n", "Diagnostics for the winning model, including **per-group recall**.\n", "\n", "The group here is `family` = `ProductCD`, Vesta's product code (W/C/H/R/S). It is a **product stratum**, not an attack taxonomy. Each bar is recall on the fraudulent transactions of one product type. The panel is still titled *Per-family recall* by the shared plotting code; read *family* as *product code*.\n", "\n", "Read it accordingly. Fraud is spread unevenly across the strata, as the \u00a77 panel shows. Recall is uneven too. Compare the two: the product carrying the most fraud is also the one detected worst. A strong aggregate score hides exactly that. The weakest stratum, not the aggregate, is the operational result." ] }, { "cell_type": "code", "execution_count": 6, "id": "cec7d47f", "metadata": {}, "outputs": [ { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "operational FALSE-POSITIVE RATE @0.5 = 0.0024 (340 benign flagged of 142,469)\n", "worst per-family recalls: {'W': 0.177, 'H': 0.455, 'S': 0.47, 'R': 0.636, 'C': 0.677}\n" ] } ], "source": [ "# --- Results for the best model: confusion, ROC, PR, importances, per-family recall ---\n", "from sklearn.metrics import confusion_matrix, roc_curve, precision_recall_curve, recall_score\n", "pb = best.predict_proba(Xte)[:, 1]; pred = (pb > 0.5).astype(int)\n", "fig, ax = plt.subplots(1, 3, figsize=(15, 4))\n", "# (1) confusion matrix\n", "cm = confusion_matrix(yte, pred); ax[0].imshow(cm, cmap='Blues')\n", "ax[0].set_title(f'{best_name}: confusion'); ax[0].set_xticks([0,1]); ax[0].set_yticks([0,1])\n", "ax[0].set_xticklabels([NEG_WORD,POS_WORD]); ax[0].set_yticklabels([NEG_WORD,POS_WORD])\n", "for (i,j),v in np.ndenumerate(cm): ax[0].text(j,i,f'{v:,}',ha='center',va='center')\n", "# (2) ROC and PR curves\n", "fpr,tpr,_ = roc_curve(yte, pb); prec,rec,_ = precision_recall_curve(yte, pb)\n", "ax[1].plot(fpr,tpr,color='#264653'); ax[1].plot([0,1],[0,1],'--',c='grey')\n", "ax[1].set_title(f'ROC (AUC={roc_auc_score(yte,pb):.4f})'); ax[1].set_xlabel('FPR'); ax[1].set_ylabel('TPR')\n", "ax[2].plot(rec,prec,color='#e76f51'); ax[2].set_title('Precision-Recall'); ax[2].set_xlabel('recall'); ax[2].set_ylabel('precision')\n", "plt.tight_layout(); plt.show()\n", "\n", "# (3) feature importances + (4) per-attack-family recall\n", "fig, ax = plt.subplots(1, 2, figsize=(13, 5))\n", "imp, names = None, feat # importances, robust to the scaled-LR pipeline\n", "if hasattr(best, 'feature_importances_'): # tree models\n", " imp = best.feature_importances_; names = list(getattr(best, 'feature_names_in_', feat))[:len(imp)]\n", "elif hasattr(best, 'named_steps') and 'logisticregression' in getattr(best, 'named_steps', {}):\n", " imp = np.abs(best.named_steps['logisticregression'].coef_[0]); names = feat # LR pipeline\n", "elif hasattr(best, 'coef_'):\n", " imp = np.abs(best.coef_[0]); names = feat\n", "if imp is not None:\n", " pd.Series(imp, index=names[:len(imp)]).sort_values().tail(12).plot.barh(ax=ax[0], color='#264653')\n", "ax[0].set_title(f'{best_name}: top importances / |coef|')\n", "# Per-family recall, WORST-first so rare, hard classes are visible, not just the dominant floods.\n", "fam_te = df.loc[Xte.index, 'family']\n", "fr = {}\n", "for fam, cnt in fam_te[yte==1].value_counts().items():\n", " if cnt < 5: continue # need a few positives for a meaningful recall\n", " mask = (fam_te==fam).to_numpy(); fr[fam] = recall_score(yte[mask], pred[mask], zero_division=0)\n", "srt = pd.Series(fr).sort_values()\n", "show = pd.concat([srt.head(9), srt.tail(3)]) if len(srt) > 12 else srt # worst 9 + best 3\n", "show = show[~show.index.duplicated()]\n", "show.plot.barh(ax=ax[1], color=['#e76f51' if v < 0.5 else '#2a9d8f' for v in show]); ax[1].set_xlim(0,1)\n", "ax[1].set_title('Per-family recall (worst first; red < 0.5)')\n", "plt.tight_layout(); plt.show()\n", "# Operational numbers, not just figures: false-positive rate and the worst per-family recalls.\n", "tn, fp = int(cm[0,0]), int(cm[0,1])\n", "fpr_op = fp/(fp+tn) if (fp+tn) > 0 else float('nan') # benign wrongly flagged @0.5\n", "print(f'operational FALSE-POSITIVE RATE @0.5 = {fpr_op:.4f} ({fp:,} benign flagged of {fp+tn:,})')\n", "print('worst per-family recalls:', {k: round(v, 3) for k, v in srt.head(6).items()})" ] }, { "cell_type": "markdown", "id": "0f15133e", "metadata": {}, "source": [ "## 10. Validity audit \u2014 is the score real?\n", "\n", "Three diagnostics. **(a)** How well can the *single best feature*, alone, separate the classes? A near-1.0 single-feature AUC means that feature is *near-sufficient* \u2014 a shortcut (which may be legitimate signal or an artifact), not the same as target leakage. **(b)** The exact-duplicate row rate. **(c)** The **train/test exact-row contamination** \u2014 the fraction of held-out rows that are duplicates of training rows, which is what actually inflates a held-out score. The trust grade is the *worse* of the single-feature and contamination concerns." ] }, { "cell_type": "code", "execution_count": 7, "id": "f30bccd2", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "best single-feature AUC = 0.6882 (feature: C4)\n", " note: a near-1.0 single-feature AUC means this feature is *near-sufficient* (a shortcut),\n", " which may be legitimate signal OR an artifact \u2014 it is NOT the same as target leakage.\n", "exact-duplicate row rate (whole corpus) = 0.003\n", "TRAIN/TEST exact-row contamination = 0.002 (single-feat grade A, contam grade A)\n", "==> data trust grade: A (worse of the two; F = shortcut and/or heavy contamination)\n" ] }, { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "# --- Validity audit: is the score real detection, or a data shortcut? ---\n", "from sklearn.metrics import roc_auc_score\n", "samp = X.sample(min(60_000, len(X)), random_state=1); ysamp = y[samp.index]\n", "aucs = {}\n", "for c in feat: # AUC of EACH feature alone\n", " col = samp[c].to_numpy(float)\n", " if col.std()==0: continue\n", " a = roc_auc_score(ysamp, col); aucs[c] = max(a, 1-a) # direction-agnostic\n", "best_auc = max(aucs.values()); best_col = max(aucs, key=aucs.get)\n", "dup_rate = 1 - X.drop_duplicates().shape[0]/len(X) # exact-duplicate feature rows (whole set)\n", "# The statistic that actually inflates a held-out score is TRAIN/TEST CONTAMINATION: how many test\n", "# rows are exact duplicates of a training row. Measure it directly on the split used above.\n", "_trkeys = set(map(tuple, np.round(Xtr.to_numpy(), 6)))\n", "_te = np.round(Xte.to_numpy(), 6)[:50_000]\n", "contam = float(np.mean([tuple(r) in _trkeys for r in _te])) # fraction of test rows seen in train\n", "# Trust grade reflects BOTH failure modes and takes the WORSE of the two: a near-perfect single\n", "# feature (shortcut) OR heavy train/test contamination each independently invalidate the headline.\n", "_ga = 'F' if best_auc>=0.999 else 'D' if best_auc>=0.99 else 'C' if best_auc>=0.95 else 'B' if best_auc>=0.85 else 'A'\n", "_gc = 'F' if contam>=0.5 else 'D' if contam>=0.3 else 'C' if contam>=0.15 else 'B' if contam>=0.05 else 'A'\n", "grade = max(_ga, _gc) # 'max' letter = worse grade (A best, F worst)\n", "print(f'best single-feature AUC = {best_auc:.4f} (feature: {best_col})')\n", "print(f' note: a near-1.0 single-feature AUC means this feature is *near-sufficient* (a shortcut),\\n'\n", " f' which may be legitimate signal OR an artifact \u2014 it is NOT the same as target leakage.')\n", "print(f'exact-duplicate row rate (whole corpus) = {dup_rate:.3f}')\n", "print(f'TRAIN/TEST exact-row contamination = {contam:.3f} (single-feat grade {_ga}, contam grade {_gc})')\n", "print(f'==> data trust grade: {grade} (worse of the two; F = shortcut and/or heavy contamination)')\n", "s = pd.Series(aucs).sort_values().tail(15)\n", "fig, ax = plt.subplots(figsize=(8,5))\n", "s.plot.barh(ax=ax, color=['#e76f51' if v>=0.99 else '#457b9d' for v in s]); ax.axvline(0.5,ls='--',c='grey')\n", "ax.set_xlim(0.5,1.0); ax.set_title('Single-feature ROC-AUC (red = near-perfect shortcut)'); ax.set_xlabel('AUC alone')\n", "plt.tight_layout(); plt.show()" ] }, { "cell_type": "markdown", "id": "dbc9c9de", "metadata": {}, "source": [ "## 11. Ablation \u2014 does the headline survive removing the artifacts?\n", "\n", "Narrating a shortcut is not enough. We *retrain the winning model* after (1) de-duplicating the corpus (removing the train/test contamination) and (2) dropping the single strongest feature. We report the held-out AUC each time. **Read the result honestly, both ways:** if the AUC **collapses**, the headline was a contamination/shortcut artifact. If it **barely moves**, the signal sits in *many* columns rather than one. On a *simulated* corpus that flatness is itself a generation artifact: the two class distributions were built barely overlapping. This corpus is real Vesta transaction data, so read flatness differently here. It says no single column is load-bearing. It is **not vindication** \u2014 redundancy is not evidence of causal signal, and a random split still cannot see drift. The numbers below decide which story is true here, not the prose." ] }, { "cell_type": "code", "execution_count": 8, "id": "01a4474e", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Ablation \u2014 how much of the headline survives once each artifact is removed:\n" ] }, { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
settingheld_out_auc
0headline (as-is)0.919380
1de-duplicated (0% rows removed)0.917530
2shortcut feature dropped (C4)0.917591
\n", "
" ], "text/plain": [ " setting held_out_auc\n", "0 headline (as-is) 0.919380\n", "1 de-duplicated (0% rows removed) 0.917530\n", "2 shortcut feature dropped (C4) 0.917591" ] }, "execution_count": 8, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# --- Ablation: SHOW the inflation empirically, don't just narrate it ---\n", "from sklearn.base import clone\n", "def _retrain_auc(Xa, ya): # re-split, stratified-subsample, refit best family\n", " xtr, xte, ytr2, yte2 = train_test_split(Xa, ya, test_size=0.25, random_state=RANDOM_STATE, stratify=ya)\n", " if len(xtr) > 120_000:\n", " xtr, _, ytr2, _ = train_test_split(xtr, ytr2, train_size=120_000, random_state=RANDOM_STATE, stratify=ytr2)\n", " m = clone(best); m.fit(xtr, ytr2)\n", " return roc_auc_score(yte2, m.predict_proba(xte)[:, 1])\n", "base_auc = roc_auc_score(yte, best.predict_proba(Xte)[:, 1]) # (0) the headline held-out AUC\n", "Xdd = X.drop_duplicates(); ydd = y[Xdd.index] # (1) de-duplicated corpus\n", "auc_dedup = _retrain_auc(Xdd, ydd)\n", "auc_noshort = _retrain_auc(X.drop(columns=[best_col]), y) if best_col in X.columns else base_auc # (2) drop shortcut\n", "ablation = pd.DataFrame([\n", " {'setting': 'headline (as-is)', 'held_out_auc': round(base_auc, 6)},\n", " {'setting': f'de-duplicated ({1-len(Xdd)/len(X):.0%} rows removed)', 'held_out_auc': round(auc_dedup, 6)},\n", " {'setting': f'shortcut feature dropped ({best_col})', 'held_out_auc': round(auc_noshort, 6)},\n", "])\n", "print('Ablation \u2014 how much of the headline survives once each artifact is removed:')\n", "ablation" ] }, { "cell_type": "markdown", "id": "f9348df6", "metadata": {}, "source": [ "## 12. Reproducibility & robustness" ] }, { "cell_type": "code", "execution_count": 9, "id": "fdae669e", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "seed=0 | numpy 2.3.5 | sklearn 1.9.0 | xgboost 1.6.2 | lightgbm 4.7.0\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "XGBoost 3-fold CV ROC-AUC = 0.8779 +/- 0.0114 (mean +/- std across 3 stratified folds; a small std means a stable estimate on this split)\n" ] } ], "source": [ "# --- Reproducibility & robustness ---\n", "import sklearn\n", "from sklearn.model_selection import StratifiedKFold, cross_val_score\n", "print(f'seed={RANDOM_STATE} | numpy {np.__version__} | sklearn {sklearn.__version__} | '\n", " f'xgboost {xgb.__version__} | lightgbm {lgb.__version__}')\n", "# 3-fold cross-validated ROC-AUC of the winning model (fresh clone, bounded subsample) -> mean +/- std.\n", "from sklearn.base import clone\n", "cvX, cvy = Xtr.iloc[:40_000], ytr[:40_000]\n", "def _auc_scorer(est, Xv, yv): # robust to xgboost's 2-col predict_proba\n", " p = est.predict_proba(Xv)\n", " p = p[:, 1] if getattr(p, 'ndim', 1) == 2 else p\n", " return roc_auc_score(yv, p)\n", "try:\n", " cv = cross_val_score(clone(best), cvX, cvy,\n", " cv=StratifiedKFold(3, shuffle=True, random_state=RANDOM_STATE),\n", " scoring=_auc_scorer, error_score='raise')\n", " assert np.all(np.isfinite(cv)), 'non-finite CV folds' # FAIL CLOSED: never narrate a NaN as evidence\n", " print(f'{best_name} 3-fold CV ROC-AUC = {cv.mean():.4f} +/- {cv.std():.4f} '\n", " f'(mean +/- std across 3 stratified folds; a small std means a stable estimate on this split)')\n", "except Exception as e:\n", " print(f'CV UNAVAILABLE ({type(e).__name__}: {str(e)[:60]}); rely on the single held-out AUC above \u2014 '\n", " f'we do NOT report a CV number we could not compute')" ] }, { "cell_type": "markdown", "id": "64a3bf22", "metadata": {}, "source": [ "## 13. Scientific conclusion\n", "\n", "On real e-commerce data the learners separate fraud from legitimate transactions well above the majority baseline. But fraud is ~3.5%, so the honest metrics are per-product recall and the false-positive rate on legitimate customers \u2014 not accuracy. The limit a random split cannot show is **concept drift**. Fraud patterns shift over time. So a time-ordered evaluation (not run here) is the deployment-realistic test (Dal Pozzolo et al., 2018; Sommer & Paxson, 2010).\n", "\n", "**Validity ledger \u2014 read the headline against these printed numbers:** Majority-class baseline **accuracy**: **0.9650**. The accuracy column must clear that bar to mean anything. For ROC-AUC the trivial baseline is 0.5, not that figure. Winning learner: **XGBoost** (3-fold CV ROC-AUC **0.8779**). Strongest *single* feature: `C4` at AUC **0.6882**. The ablation refutes a single-feature story. Dropping that feature barely moves the AUC: **0.919380 \u2192 0.917591**. So the separability is **multi-feature**. The signal is spread across many features, not held in one leaky column. De-duplication changed almost nothing. The duplicate rate is **0.0030**, under 0.5%, which the table rounds to 0%. The 0.001850 difference is re-split noise, not a de-duplication effect. Data-trust grade: **A**. It is the worse of two independent sub-checks. Single-feature AUC 0.6882 scores **A**. Train/test exact-row overlap 0.002 scores **A**. Neither check flags a problem, so nothing here explains the score away. Operational false-positive rate at threshold 0.5: **0.0024**. Worst per-group recalls by product code, exactly as printed: {`W`: 0.177, `H`: 0.455, `S`: 0.47, `R`: 0.636, `C`: 0.677}. The weakest group sits at **0.177**, so the model misses most of it. That gap, not the aggregate score, is the operationally important result. **Disclosed limitation:** categorical columns are integer-encoded before the split. The encoder therefore sees the test set's category values. On an all-numeric corpus that step is a no-op. The mapping never consults the label, so no *label* information leaks. It is still transductive. A deployed system would need an unseen-category bucket. **How the audit numbers are computed:** overlap is measured on the first 50,000 held-out rows, so read it as a sampled estimate. Each ablation re-splits and refits, so tiny differences are re-split noise. The de-duplication variant keeps the first label when a feature vector appears twice. **Scope:** the split is random, not temporal or entity-grouped. Every number above therefore measures in-distribution separability only." ] }, { "cell_type": "markdown", "id": "6a682a13", "metadata": {}, "source": [ "## References\n", "\n", "1. Dal Pozzolo, A., Boracchi, G., Caelen, O., Alippi, C. & Bontempi, G. (2018). Credit Card Fraud Detection: A Realistic Modeling and a Novel Learning Strategy. *IEEE Transactions on Neural Networks and Learning Systems*, 29(8), 3784\u20133797.\n", "2. Bahnsen, A.C. et al. (2016). Feature Engineering Strategies for Credit Card Fraud Detection. *Expert Systems with Applications*.\n", "3. IEEE-CIS & Vesta Corporation (2019). IEEE-CIS Fraud Detection. *Kaggle*.\n", "4. Sommer, R. & Paxson, V. (2010). Outside the Closed World: On Using Machine Learning for Network Intrusion Detection. *IEEE S&P*." ] } ], "metadata": { "kernelspec": { "display_name": "seas8414-phase-notebooks", "language": "python", "name": "seas8414-phase-notebooks" } }, "nbformat": 4, "nbformat_minor": 5 }