Credit Card Fraud Detection

Key Characteristics of Credit Card Fraud Detection

• Often formulated as a classification problem: fraud or no fraud.
• Highly imbalanced datasets, with very few fraudulent transactions compared to legitimate ones.
• Requires feature engineering, anomaly detection, and robust evaluation metrics to handle imbalance.
• Models include supervised learning (e.g., logistic regression, random forest) and unsupervised approaches (e.g., anomaly detection).

Python Example: Credit Card Fraud Detection using Logistic Regression

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import classification_report, confusion_matrix, roc_auc_score

# Load dataset (Credit Card Fraud Detection Dataset)
url = "https://storage.googleapis.com/download.tensorflow.org/data/creditcard.csv"
data = pd.read_csv(url)

# Check class distribution
print(data['Class'].value_counts())

# Features and target
X = data.drop('Class', axis=1)
y = data['Class']

# Scale features (important for many models)
scaler = StandardScaler()
X_scaled = scaler.fit_transform(X)

# Split data into train and test sets (stratify to maintain class distribution)
X_train, X_test, y_train, y_test = train_test_split(X_scaled, y, test_size=0.3, random_state=42, stratify=y)

# Train logistic regression model
model = LogisticRegression(max_iter=1000)
model.fit(X_train, y_train)

# Predict on test data
y_pred = model.predict(X_test)
y_prob = model.predict_proba(X_test)[:, 1]

# Evaluation
print("Confusion Matrix:")
print(confusion_matrix(y_test, y_pred))
print("\nClassification Report:")
print(classification_report(y_test, y_pred))
print(f"\nROC AUC Score: {roc_auc_score(y_test, y_prob):.4f}")