Payment card fraud - including both credit cards and debit cards - is forecast to grow by over ** billion U.S. dollars between 2022 and 2028. Especially outside the United States, the amount of fraudulent payments almost doubled from 2014 to 2021. In total, fraudulent card payments reached ** billion U.S. dollars in 2021. Card fraud losses across the world increased by more than ** percent between 2020 and 2021, the largest increase since 2018.

• Digital payments are evolving, but so are cyber criminals.

• According to the Data Breach Index, more than 5 million records are being stolen on a daily basis, a concerning statistic that shows - fraud is still very common both for Card-Present and Card-not Present type of payments.

• In today’s digital world where trillions of Card transaction happens per day, detection of fraud is challenging.

This Dataset sourced by some unnamed institute.

Feature Explanation:

distance_from_home - the distance from home where the transaction happened.

distance_from_last_transaction - the distance from last transaction happened.

ratio_to_median_purchase_price - Ratio of purchased price transaction to median purchase price.

repeat_retailer - Is the transaction happened from same retailer.

used_chip - Is the transaction through chip (credit card).

used_pin_number - Is the transaction happened by using PIN number.

online_order - Is the transaction an online order.

fraud - Is the transaction fraudulent.

Imagine this: you're sitting at a coffee shop, enjoying a latte, and casually checking your email. Suddenly, a notification pops up, your credit card has been charged $500 for something you didn’t buy. Scenarios like this are becoming alarmingly common. Credit card fraud is a modern menace, evolving with every...

Below is a draft DMP–style description of your credit‐card fraud detection experiment, modeled on the antiquities example:

1. Dataset Description

Research Domain
This work resides in the domain of financial fraud detection and applied machine learning. We focus on detecting anomalous credit‐card transactions in real time to reduce financial losses and improve trust in digital payment systems.

Purpose
The goal is to train and evaluate a binary classification model that flags potentially fraudulent transactions. By publishing both the code and data splits via FAIR repositories, we enable reproducible benchmarking of fraud‐detection algorithms and support future research on anomaly detection in transaction data.

Data Sources
We used the publicly available credit‐card transaction dataset from Kaggle (original source: https://www.kaggle.com/mlg-ulb/creditcardfraud), which contains anonymized transactions made by European cardholders over two days in September 2013. The dataset includes 284 807 transactions, of which 492 are fraudulent.

Method of Dataset Preparation

1. Schema validation: Renamed columns to snake_case (e.g. transaction_amount, is_declined) so they conform to DBRepo’s requirements.

2. Data import: Uploaded the full CSV into DBRepo, assigned persistent identifiers (PIDs).

3. Splitting: Programmatically derived three subsets—training (70%), validation (15%), test (15%)—using range‐based filters on the primary key actionnr. Each subset was materialized in DBRepo and assigned its own PID for precise citation.

4. Cleaning: Converted the categorical flags (is_declined, isforeigntransaction, ishighriskcountry, isfradulent) from “Y”/“N” to 1/0 and dropped non‐feature identifiers (actionnr, merchant_id).

5. Modeling: Trained a RandomForest classifier on the training split, tuned on validation, and evaluated on the held‐out test set.

2. Technical Details

Dataset Structure

• The raw data is a single CSV with columns:

  • actionnr (integer transaction ID)

  • merchant_id (string)

  • average_amount_transaction_day (float)

  • transaction_amount (float)

  • is_declined, isforeigntransaction, ishighriskcountry, isfradulent (binary flags)

  • total_number_of_declines_day, daily_chargeback_avg_amt, sixmonth_avg_chbk_amt, sixmonth_chbk_freq (numeric features)

Naming Conventions

• All columns use lowercase snake_case.

• Subsets are named creditcard_training, creditcard_validation, creditcard_test in DBRepo.

• Files in the code repo follow a clear structure:

  ├── data/         # local copies only; raw data lives in DBRepo 
  ├── notebooks/Task.ipynb 
  ├── models/rf_model_v1.joblib 
  ├── outputs/        # confusion_matrix.png, roc_curve.png, predictions.csv 
  ├── README.md 
  ├── requirements.txt 
  └── codemeta.json 
  

Required Software

• Python 3.9+

• pandas, numpy (data handling)

• scikit-learn (modeling, metrics)

• matplotlib (visualizations)

• dbrepo‐client.py (DBRepo API)

• requests (TU WRD API)

Additional Resources

• Original dataset: https://www.kaggle.com/mlg-ulb/creditcardfraud

• Scikit-learn docs: https://scikit-learn.org/stable

• DBRepo API guide: via the starter notebook’s dbrepo_client.py template

• TU WRD REST API spec: https://test.researchdata.tuwien.ac.at/api/docs

3. Further Details

Data Limitations

• Highly imbalanced: only ~0.17% of transactions are fraudulent.

• Anonymized PCA features (V1–V28) hidden; we extended with domain features but cannot reverse engineer raw variables.

• Time‐bounded: only covers two days of transactions, may not capture seasonal patterns.

Licensing and Attribution

• Raw data: CC-0 (per Kaggle terms)

• Code & notebooks: MIT License

• Model artifacts & outputs: CC-BY 4.0

• DUWRD records include ORCID identifiers for the author.

Recommended Uses

• Benchmarking new fraud‐detection algorithms on a standard imbalanced dataset.

• Educational purposes: demonstrating model‐training pipelines, FAIR data practices.

• Extension: adding time‐series or deep‐learning models.

Known Issues

• Possible temporal leakage if date/time features not handled correctly.

• Model performance may degrade on live data due to concept drift.

• Binary flags may oversimplify nuanced transaction outcomes.

Card fraud losses across the world increased by more than 10 percent between 2020 and 2021, the largest increase since 2018. It was estimated that merchants and card acquirers lost well over 30 billion U.S. dollars, with - so the source adds - roughly 12 billion U.S. dollar coming from the United States alone. Note that the figures provided here included both credit card fraud and debit card fraud. The source does not separate between the two, and also did not provide figures on the United States - a country known for its reliance on credit cards.

1) Data Introduction • The Credit Card Transactions Dataset includes more than 20 million credit card transactions over the decades of 2,000 U.S. resident consumers created by IBM's simulations, providing details of each transaction and fraudulent labels.

2) Data Utilization (1) Credit Card Transactions Dataset has characteristics that: • This dataset provides a variety of properties that are similar to real credit card transactions, including transaction amount, time, card information, purchase location, and store category (MCC). (2) Credit Card Transactions Dataset can be used to: • Development of Credit Card Fraud Detection Model: Using transaction history and properties, you can build a fraud (abnormal transaction) detection model based on machine learning. • Analysis of consumption patterns and risks: Long-term and diverse transaction data can be used to analyze customer consumption behavior and identify risk factors.

This dataset, commonly known as creditcard.csv, contains anonymized credit card transactions made by European cardholders in September 2013. It includes 284,807 transactions, with 492 labeled as fraudulent. Due to confidentiality constraints, features have been transformed using PCA, except for 'Time' and 'Amount'.

This dataset was used in the research article titled "A Hybrid Anomaly Detection Framework Combining Supervised and Unsupervised Learning for Credit Card Fraud Detection". The study proposes an ensemble model integrating techniques such as Autoencoders, Isolation Forest, Local Outlier Factor, and supervised classifiers including XGBoost and Random Forest, aiming to improve the detection of rare fraudulent patterns while maintaining efficiency and scalability.

Key Features:

30 numerical input features (V1–V28, Time, Amount) Class label indicating fraud (1) or normal (0) Imbalanced class distribution typical in real-world fraud detection Use Case: Ideal for benchmarking and evaluating anomaly detection and classification algorithms in highly imbalanced data scenarios.

Source: Originally published by the Machine Learning Group at Université Libre de Bruxelles.

Unlike many other countries, the United States did not see a surge in the “card-not-present” fraud rate immediately after migrating to chip-card technology. Instead, the U.S. card-not-present fraud rate of non-prepaid debit cards has increased gradually over the past decade. Merchants’ and cardholders’ card-not-present fraud loss rates have increased for both dual- and single-message networks, while issuers’ card-not-present fraud loss rate has increased for single-message networks.

The Credit Card Transactions Dataset provides detailed records of credit card transactions, including information about transaction times, amounts, and associated personal and merchant details. This dataset has over 1.85M rows.

How This Dataset Can Be Used:

Fraud Detection : Use machine learning models to identify fraudulent transactions by examining patterns in transaction amounts, locations, and user profiles. Enhancing fraud detection systems becomes feasible by analyzing behavioral patterns.

Customer Segmentation : Segment customers based on spending patterns, location, and demographics. Tailor marketing strategies and personalized offers to these different customer segments for better engagement.

Transaction Classification : Classify transactions into categories such as grocery or entertainment to understand spending behaviors. This helps in improving recommendation systems by identifying transaction categories and preferences.

Geospatial Analysis : Analyze transaction data geographically to map spending patterns and detect regional trends or anomalies based on latitude and longitude.

Predictive Modeling : Build models to forecast future spending behavior using historical transaction data. Predict potential fraudulent activities and financial trends.

Behavioral Analysis : Examine how factors like transaction amount, merchant type, and time influence spending behavior. Study the relationships between user demographics and transaction patterns.

Anomaly Detection : Identify unusual transaction patterns that deviate from normal behavior to detect potential fraud early. Employ anomaly detection techniques to spot outliers and suspicious activities.

The global credit card fraud detection platform market is experiencing robust growth, driven by the escalating volume of digital transactions and the increasing sophistication of fraud techniques. The market, valued at approximately $15 billion in 2025, is projected to exhibit a Compound Annual Growth Rate (CAGR) of 18% from 2025 to 2033. This substantial growth is fueled by several key factors. The rising adoption of e-commerce and mobile payments creates a larger attack surface for fraudsters, necessitating advanced detection solutions. Furthermore, the increasing prevalence of sophisticated fraud schemes, such as synthetic identity theft and account takeover, demands more intelligent and adaptive fraud detection systems. The market is segmented by screening type (manual and automatic) and application (personal and enterprise), with automatic screening and enterprise applications driving the majority of growth due to their scalability and efficiency. The competitive landscape is dynamic, with established players like FICO, Mastercard, and Visa competing alongside innovative startups such as Forter and Feedzai. These companies continuously develop AI-powered solutions leveraging machine learning and big data analytics to identify and prevent fraudulent transactions effectively. Regional growth varies, with North America and Europe currently holding significant market share, but Asia-Pacific is expected to experience rapid expansion in the coming years due to rising digital adoption and economic growth in countries like India and China. The continued growth of the credit card fraud detection platform market hinges on several factors. The increasing demand for real-time fraud detection capabilities is driving the adoption of cloud-based solutions and the integration of advanced analytics. Regulatory compliance requirements, particularly around data privacy and security, also contribute to market growth. However, challenges remain. The cost of implementing and maintaining these sophisticated systems can be prohibitive for smaller businesses. Moreover, the constant evolution of fraud techniques necessitates ongoing investment in research and development to stay ahead of emerging threats. The market’s future trajectory will depend on the continued innovation in fraud detection technologies, the ability to adapt to evolving fraud tactics, and the successful integration of these solutions across various industries and geographies.

In 2024, damage caused by credit card fraud reported by Japanese companies amounted to **** billion Japanese yen, reaching a new decade high. Losses caused by illegal credit card use increased from about **** billion yen in the previous year.

Data on the total annual value of fraud losses on debit and credit cards issued in the United Kingdom (UK) from 2002 to 2020, abroad and in the United Kingdom (UK) shows that the total value of annual fraud losses on UK issued debit and credit cards fluctuated overall during the period under observation, reaching a value of 574.2 million British pounds as of 2020. The smallest value of fraud losses on debit and credit cards occurred in 2011, when credit and debit card fraud losses amounting to *** million British pounds were recorded.

This statistic presents the value of losses due to synthetic credit card fraud in the United States from 2015 to 2017, with projections extending to 2020. Such fraud led to *** million U.S. dollars in damages in 2017, an amount which was expected to increase to nearly **** trillion U.S. dollars in 2020.

In 2024, damage caused by credit card fraud reported by Japanese companies amounted to **** billion Japanese yen. With about **** billion yen, fraudulent use of credit card numbers accounted for the largest amount of losses.

Financial transaction data, which is typically imbalanced. While most transactions are not fraudulent, there exist a small percentage that are fraudulent. These few fraudulent transactions usually incur costly monetary repercussions.

Dataset

This dataset was created by Dileep

Contents

Dataset

This dataset was created by Shubham Lipare

Contents

Overview

This dataset contains synthetic credit card transaction data designed for fraud detection and machine learning research. With over 6.3 million transactions, it provides a realistic simulation of financial transaction patterns including both legitimate and fraudulent activities.

Source

This is a synthetic dataset generated to simulate credit card transaction behavior. The data represents financial transactions over a 30-day period (743 hours) with various transaction types including payments, transfers, cash-outs, debits, and cash-ins.

Purpose

The dataset is specifically designed for: - Training and testing fraud detection models - Anomaly detection research - Binary classification tasks - Imbalanced learning scenarios - Financial machine learning applications

Column Descriptions

• step: Maps a unit of time in the real world. 1 step represents 1 hour of time. Range: 1 to 743
• type: Type of transaction (PAYMENT, TRANSFER, CASH_OUT, DEBIT, CASH_IN)
• amount: Amount of the transaction in local currency
• nameOrig: Customer ID who initiated the transaction
• oldbalanceOrg: Initial balance before the transaction (origin account)
• newbalanceOrig: New balance after the transaction (origin account)
• nameDest: Recipient ID of the transaction
• oldbalanceDest: Initial recipient balance before the transaction
• newbalanceDest: New recipient balance after the transaction
• isFraud: Binary flag indicating fraud (1 = fraud, 0 = legitimate)
• isFlaggedFraud: Flag for illegal attempts to transfer more than 200,000 in a single transaction

Dataset Statistics

• Total Transactions: 6,362,620
• Fraudulent Transactions: 8,213 (~0.13%)
• Legitimate Transactions: 6,354,407 (~99.87%)
• Time Period: 30 days (743 hours)
• File Size: 493.53 MB

Class Imbalance Note

This dataset exhibits significant class imbalance with only 0.13% fraudulent transactions. This mirrors real-world fraud detection scenarios where fraudulent transactions are rare. Consider using techniques such as: - SMOTE (Synthetic Minority Over-sampling Technique) - Undersampling of majority class - Cost-sensitive learning - Ensemble methods - Anomaly detection algorithms

Model Suitability

This dataset is well-suited for: - Logistic Regression - Random Forest - Gradient Boosting (XGBoost, LightGBM, CatBoost) - Neural Networks - Isolation Forest - Autoencoders - Support Vector Machines

Quick Start Example

import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns

# Load the dataset
df = pd.read_csv('/kaggle/input/credit-card-fraud-dataset/Fraud.csv')

# Display basic information
print(df.info())
print(df.head())

# Check fraud distribution
print(df['isFraud'].value_counts())

# Visualize fraud distribution
plt.figure(figsize=(8, 5))
sns.countplot(data=df, x='isFraud')
plt.title('Distribution of Fraud vs Legitimate Transactions')
plt.xlabel('Is Fraud (0=No, 1=Yes)')
plt.ylabel('Count')
plt.show()

# Transaction type distribution
plt.figure(figsize=(10, 6))
sns.countplot(data=df, x='type', hue='isFraud')
plt.title('Transaction Types by Fraud Status')
plt.xticks(rotation=45)
plt.show()

Usage Tips

1. Handle Class Imbalance: Use appropriate sampling techniques or algorithms designed for imbalanced data
2. Feature Engineering: Consider creating features like transaction velocity, time-based patterns, and balance differences
3. Evaluation Metrics: Use precision, recall, F1-score, and AUC-ROC rather than accuracy due to class imbalance
4. Cross-validation: Use stratified k-fold to maintain class distribution across folds
5. Transaction Patterns: Analyze transaction types - TRANSFER and CASH_OUT are more associated with fraud

Update Frequency

This is a static dataset with no planned future updates. It serves as a benchmark for fraud detection research and model development.

Acknowledgments

This dataset is made available under the MIT License for educational and research purposes in the field of fraud detection and financial machine learning.

Title: Credit Card Transactions Dataset for Fraud Detection (Used in: A Hybrid Anomaly Detection Framework Combining Supervised and Unsupervised Learning)Description:This dataset, commonly known as creditcard.csv, contains anonymized credit card transactions made by European cardholders in September 2013. It includes 284,807 transactions, with 492 labeled as fraudulent. Due to confidentiality constraints, features have been transformed using PCA, except for 'Time' and 'Amount'.This dataset was used in the research article titled "A Hybrid Anomaly Detection Framework Combining Supervised and Unsupervised Learning for Credit Card Fraud Detection". The study proposes an ensemble model integrating techniques such as Autoencoders, Isolation Forest, Local Outlier Factor, and supervised classifiers including XGBoost and Random Forest, aiming to improve the detection of rare fraudulent patterns while maintaining efficiency and scalability.Key Features:30 numerical input features (V1–V28, Time, Amount)Class label indicating fraud (1) or normal (0)Imbalanced class distribution typical in real-world fraud detectionUse Case:Ideal for benchmarking and evaluating anomaly detection and classification algorithms in highly imbalanced data scenarios.Source:Originally published by the Machine Learning Group at Université Libre de Bruxelles.https://www.kaggle.com/mlg-ulb/creditcardfraudLicense:This dataset is distributed for academic and research purposes only. Please cite the original source when using the dataset.

Malaysia Consumers: Security: Credit Card/Debit Card/Bank Fraud data was reported at 63.900 % in 2018. Malaysia Consumers: Security: Credit Card/Debit Card/Bank Fraud data is updated yearly, averaging 63.900 % from Dec 2018 (Median) to 2018, with 1 observations. Malaysia Consumers: Security: Credit Card/Debit Card/Bank Fraud data remains active status in CEIC and is reported by Malaysian Communications and Multimedia Commission. The data is categorized under Global Database’s Malaysia – Table MY.S026: E-Commerce Consumer Survey.