{ "cells": [ { "cell_type": "markdown", "id": "53d28903", "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 the PaySim mobile-money simulation.\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 \u2014 and recognise the artifact a duplicate/single-feature audit cannot reach.\n", "4. Report per-group recall, because the rare classes carry the risk.\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", "\n", "---" ] }, { "cell_type": "markdown", "id": "8314c86f", "metadata": {}, "source": [ "# Mobile-Money Fraud Detection: the PaySim Simulator\n", "### Model comparison + validity audit on PaySim (\u22651M records, via Kaggle)\n", "\n", "**Abstract:** PaySim (Lopez-Rojas et al., 2016) is a **6,362,620-transaction** agent-based simulation of mobile money. It simulates mobile-money transfers seeded from a real African provider's aggregates, with a rare fraud class. This notebook analyses the **first 1,500,000 rows** of it. The loader prints the exact count, and every figure below refers to that slice, not the full corpus. We compare four learners and audit whether high scores reflect fraud detection or a trivial rule. We also disclose up front (\u00a73) that PaySim's balance columns are written by the same script that sets the fraud label. That is an artifact the audit in \u00a710 is structurally unable to detect." ] }, { "cell_type": "markdown", "id": "431ae985", "metadata": {}, "source": [ "## 1. Research problem\n", "\n", "**Task:** Flag fraudulent mobile-money transactions (fraud occurs only in TRANSFER and CASH_OUT flows) among an overwhelming majority of legitimate ones. Extreme class imbalance means accuracy is meaningless \u2014 recall on the rare fraud class is the real question." ] }, { "cell_type": "markdown", "id": "b1a1c57d", "metadata": {}, "source": [ "## 2. Literature review\n", "\n", "- **Lopez-Rojas, Elmir & Axelsson (2016)** \u2014 PaySim: a financial mobile-money simulator for fraud detection (EMSS).\n", "- **Dal Pozzolo et al. (2015)** \u2014 learning with imbalanced fraud data.\n", "- **Sommer & Paxson (2010)** \u2014 closed-world evaluation pitfalls (applies to fraud ML too).\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", "| Lopez-Rojas et al. (2016) \u2014 rule + ML | simulated data; fraud confined to 2 transaction types |\n", "| Imbalanced-learning studies | AUC flattered; PR-AUC and recall matter |\n" ] }, { "cell_type": "markdown", "id": "ed8a0df0", "metadata": {}, "source": [ "## 3. Dataset provenance & honesty caveats\n", "\n", "| Property | Value |\n", "|---|---|\n", "| Source | Kaggle `ealaxi/paysim1` (PaySim) |\n", "| Rows | 6,362,620 in the full file; **1,500,000 analysed here** (leading rows, per the loader read cap - every figure below describes that slice) |\n", "| Label | `isFraud` 0/1; family `type` (transaction type) |\n", "| Access | Kaggle API token required |\n", "\n", "**Honestly:** simulated (not real) transactions; account IDs (`nameOrig`/`nameDest`) and the leaky `isFlaggedFraud` rule flag are dropped from features.\n", "\n", "**Known generator coupling \u2014 the balance columns are written by the same script that sets the label.** PaySim's documented fraud mechanic is that a fraudulent agent takes over a customer account and *empties* it. The agent transfers the balance out and cashes it out. That is the dataset's own description of `isFraud`, and it is why fraud appears only in `TRANSFER` and `CASH_OUT`. The direct consequence is that on fraudulent rows the transferred `amount` is, with few exceptions, the origin account's whole prior balance. The post-transfer origin balance is driven to zero. So the retained columns `amount`, `oldbalanceOrg` and `newbalanceOrig` do not merely *correlate* with fraud. They re-encode the rule that generated it. They are kept because after the drop list only six features survive, and removing them would leave almost nothing. But the consequence must be stated plainly: **every score below should be read as \"how well does a learner recover PaySim's scripted account-emptying rule\". It should not be read as evidence about real mobile-money fraud.** This notebook does **not** run a test that measures that coupling \u2014 see \u00a710 for exactly why its audit cannot see it.\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 `ealaxi/paysim1` -> `/tmp/kg_paysim1`. It is about **471 MB** 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": "bda1472b", "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": "aa3af00b", "metadata": {}, "source": [ "**Figure 4.1 \u2014 Solution design (methodology).**\n", "\n", "\"Figure" ] }, { "cell_type": "markdown", "id": "8a1de95d", "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": "e27976c2", "metadata": {}, "source": [ "**Figure 5.1 \u2014 Implementation architecture.**\n", "\n", "\"Figure" ] }, { "cell_type": "markdown", "id": "11b1c5f5", "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: `df`, `X` (clean numeric features), `y` (binary label), `feat` (feature names), and `family`. `family` is the per-group label used for the recall breakdown. It is an attack family on the intrusion corpora, but a transaction type, merchant category or malware category on the fraud/malware ones." ] }, { "cell_type": "code", "execution_count": 1, "id": "9f7fa76b", "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": "50dcf49c", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "loaded 1,500,000 rows x 6 features; positive rate 0.0011\n" ] } ], "source": [ "import os, glob\n", "# Kaggle auth: token read from ~/.kaggle/access_token (students supply their own).\n", "os.environ.setdefault('KAGGLE_KEY', open(os.path.expanduser('~/.kaggle/access_token')).read().strip())\n", "import kaggle; kaggle.api.authenticate()\n", "REF = 'ealaxi/paysim1'; DEST = '/tmp/kg_' + REF.split('/')[-1]\n", "if not os.path.exists(DEST): # download + unzip once (cached)\n", " kaggle.api.dataset_download_files(REF, path=DEST, unzip=True, quiet=True)\n", "NROWS = 1_500_000 # per-file read cap (memory bound)\n", "files = sorted(glob.glob(DEST + '/**/*.csv', recursive=True))\n", "df = pd.concat([pd.read_csv(f, low_memory=False, nrows=NROWS) for f in files], ignore_index=True) # combine day/part files\n", "df.columns = [str(c).strip() for c in df.columns] # strip header whitespace\n", "LABEL = 'isFraud'; FAMILY = 'type'\n", "df['y'] = (df[LABEL].astype(str).str.strip().str.lower() != '0').astype(int) # benign=0\n", "df['family'] = df[FAMILY].astype(str).str.strip() # descriptive attack family\n", "df = df.reset_index(drop=True)\n", "assert len(df) >= 1_000_000, f'floor not met: {len(df):,}' # honesty gate: >= 1M rows\n", "DROP = list({LABEL, FAMILY, 'y', 'family'} | set(['nameOrig', 'nameDest', 'isFlaggedFraud'])) # never leak label cols\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: # encode remaining categoricals\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) # clip huge NetFlow counts (float32-safe)\n", "X = X.loc[:, X.nunique() > 1] # drop constants\n", "import re # LightGBM rejects special chars in names\n", "_seen, _cols = {}, []\n", "for _c in X.columns: # sanitize to unique, 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() # STANDARD CONTRACT\n", "NEG_WORD, POS_WORD = 'legitimate', 'fraud' # class names for plots\n", "print(f'loaded {len(df):,} rows x {len(feat)} features; positive rate {y.mean():.4f}')" ] }, { "cell_type": "markdown", "id": "47174914", "metadata": {}, "source": [ "## 7. Exploratory data analysis" ] }, { "cell_type": "code", "execution_count": 3, "id": "6325e089", "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": "fc9ea2cb", "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": "76f87865", "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": "e2b4684f", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "materialized 1,500,000 rows | trained on 120,000 (stratified subsample) | held-out 375,000\n", "MAJORITY-CLASS BASELINE accuracy = 0.9989 (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
0XGBoost0.9996190.9947310.5
1RandomForest0.9994770.9555910.9
2LogisticRegression0.9990530.8048410.1
3LightGBM0.9966320.6154631.4
4MajorityBaseline0.9989000.5000000.0
\n", "
" ], "text/plain": [ " model accuracy roc_auc train_s\n", "0 XGBoost 0.999619 0.994731 0.5\n", "1 RandomForest 0.999477 0.955591 0.9\n", "2 LogisticRegression 0.999053 0.804841 0.1\n", "3 LightGBM 0.996632 0.615463 1.4\n", "4 MajorityBaseline 0.998900 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": "45f825da", "metadata": {}, "source": [ "## 9. Results\n", "\n", "Diagnostics for the winning model, including **per-group recall**.\n", "\n", "The grouping comes from whatever the loader put in `family`. It is *not* always an attack taxonomy. On the intrusion corpora it is the attack family. On the fraud and malware corpora it is a transaction type, a merchant category or a malware category. On binary corpora it collapses to the positive class.\n", "\n", "Read it accordingly. Where the groups are genuinely rare classes, they reveal whether detection is real. The dominant flood classes do not." ] }, { "cell_type": "code", "execution_count": 6, "id": "9e850519", "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 = 0.0000 (14 benign flagged of 374,598)\n", "worst per-family recalls: {'CASH_OUT': 0.596, 'TRANSFER': 0.756}\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": "fef2e0ab", "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.\n", "\n", "**What this audit cannot see \u2014 read the grade narrowly:** (a) tests one column at a time and (b)/(c) test whole rows. A shortcut can live in the *relation between two columns* \u2014 \"the amount equals the account's prior balance\", \"the balance afterwards is zero\". Such a shortcut is invisible to both. Each column alone is only weakly predictive, and the rows are not (as the printed duplicate rate shows) copies of one another. On PaySim that is precisely the shape of the artifact (\u00a73). So a good grade here means *no single feature is near-sufficient and no held-out row was memorised from training*. It does **not** mean the score has been explained; the coupled balance columns remain an untested explanation for it." ] }, { "cell_type": "code", "execution_count": 7, "id": "249212b3", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "best single-feature AUC = 0.7846 (feature: oldbalanceOrg)\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) = 0.000\n", "TRAIN/TEST exact-row contamination = 0.000 (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": "71807b54", "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** \u2014 common on *simulated* corpora \u2014 that is **not vindication**. It means the classes are separable by *many* redundant features, because the attack and benign distributions barely overlap. That is its own generation artifact. The numbers below decide which story is true here, not the prose.\n", "\n", "**Ceiling on this test:** it removes only the *single* strongest column. PaySim's account-emptying rule is spread across `amount`, `oldbalanceOrg` and `newbalanceOrig` (\u00a73), so dropping one of the three leaves the rule reconstructible from the survivors. A partial, non-fatal drop is therefore the expected outcome whether or not the coupling is driving the score, and cannot be read as evidence against it." ] }, { "cell_type": "code", "execution_count": 8, "id": "39977082", "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)0.994731
1de-duplicated (0% rows removed)0.989154
2shortcut feature dropped (oldbalanceOrg)0.955019
\n", "
" ], "text/plain": [ " setting held_out_auc\n", "0 headline (as-is) 0.994731\n", "1 de-duplicated (0% rows removed) 0.989154\n", "2 shortcut feature dropped (oldbalanceOrg) 0.955019" ] }, "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": "8456d7f6", "metadata": {}, "source": [ "## 12. Reproducibility & robustness" ] }, { "cell_type": "code", "execution_count": 9, "id": "35ed492e", "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 = 0.9862 +/- 0.0089 (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": "fdf13ab3", "metadata": {}, "source": [ "## 13. Scientific conclusion\n", "\n", "The honest metric is rare-class recall, not the flattering ROC-AUC.\n", "\n", "**Validity ledger \u2014 read the headline against these printed numbers:** Majority-class baseline **accuracy**: **0.9989**. 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 **0.9862**). Strongest *single* feature: `oldbalanceOrg` at AUC **0.7846**. Dropping it costs a real but partial amount: **0.994731 \u2192 0.955019**. The feature carries some of the signal, not all of it. Note that this ablation removes one of the three coupled balance columns (\u00a73, \u00a711). So a partial drop is what it would show either way. De-duplication changed nothing. There are no exact duplicates to remove. The 0.005577 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 0.7846 scores **A**. Train/test exact-row overlap 0.000 scores **A**. **That grade is narrower than it looks, and it is not a clean bill of health here.** Both sub-checks are blind to a shortcut carried by a *pair* of columns, and PaySim has exactly that. The simulator's fraud script empties the victim account. So `amount`, `oldbalanceOrg` and `newbalanceOrig` are written by the same rule that sets the label (\u00a73). The retained balance columns therefore remain a live explanation for the headline, and this notebook runs no test that would rule it out. Read the A as \"no *single* feature is near-sufficient and no held-out row was memorised\" \u2014 not as \"nothing explains the score\". Operational false-positive rate at threshold 0.5: **0.0000**. Worst per-group recalls, exactly as printed: {`CASH_OUT`: 0.596, `TRANSFER`: 0.756}. The weakest group sits at **0.596**, which is where detection is thinnest. **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": "4571152b", "metadata": {}, "source": [ "## References\n", "\n", "1. Lopez-Rojas, E.A., Elmir, A. & Axelsson, S. (2016). PaySim: A financial mobile money simulator for fraud detection. *28th European Modeling and Simulation Symposium*.\n", "2. Dal Pozzolo, A. et al. (2015). Calibrating probability with undersampling for unbalanced classification. *IEEE SSCI*.\n", "3. 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 }