The Credit Card Agreements (CCA) database includes credit card agreements from more than 600 card issuers. These agreements include general terms and conditions, pricing, and fee information and are collected quarterly pursuant to requirements in the CARD Act. This dataset includes data for the years 2020-2024.

Download the Meat Freshness Image Dataset with 2,266 images labeled into Fresh, Half-Fresh, and Spoiled categories. Perfect for building AI models in food safety and quality control to detect meat freshness based on visual cues.

As required by the Credit CARD Act of 2009, we collect information annually from credit card issuers who have marketing agreements with universities, colleges, or affiliated organizations such as alumni associations, sororities, fraternities, and foundations.

Predict revenue surprises, track market share, and compare performance metrics for thousands of companies based on anonymized debit and credit card data of millions of US households. Orion data is sourced from a variety of US financial institutions with broad geographic and demographic representation, combined to create one of the most comprehensive and accurate views of the consumer economy. AI-powered earnings predictions available for over 450 tickers on this dataset through EarnestAI Reported Metric Predictions.

Credit Card Transaction: Quarterly: Volume data was reported at 9,502.716 Unit mn in Jun 2022. This records an increase from the previous number of 9,301.651 Unit mn for Mar 2022. Credit Card Transaction: Quarterly: Volume data is updated quarterly, averaging 6,627.430 Unit mn from Mar 2019 (Median) to Jun 2022, with 14 observations. The data reached an all-time high of 9,502.716 Unit mn in Jun 2022 and a record low of 4,705.638 Unit mn in Jun 2020. Credit Card Transaction: Quarterly: Volume data remains active status in CEIC and is reported by Central Bank of Brazil. The data is categorized under Global Database’s Brazil – Table BR.KAA001: Credit Card Statistics.

The Credit Card Statistics provide data in relation to monthly credit card transactions. A breakdown of the number of credit cards issued to Irish residents is also provided.

Credit risk assessment remains a critical function within financial services, influencing lending decisions, portfolio risk management, and regulatory compliance. It integrates multiple categories of financial, transactional, and behavioral data to enable advanced machine learning applications in the domain of financial risk modeling.

Data Composition and Structure

The dataset comprises a total of 1,212 distinct features, systematically grouped into four principal categories, alongside a binary target variable. Each feature category represents a specific dimension of credit risk assessment, reflecting both internal transactional data and externally sourced credit bureau information.

Target Variable

The dependent variable, denoted as bad_flag, represents a binary risk classification outcome associated with each customer account. The variable takes the following values:

• 0: Denotes a low-risk, creditworthy customer
• 1: Denotes a high-risk, default-prone customer

This variable serves as the target for binary classification models aimed at predicting credit risk propensity.

Feature Groups

Each feature within a category follows a systematic sequential naming convention (e.g., transaction_attribute_1, bureau_1), facilitating programmatic identification and group-level analysis.

Data Characteristics

The dataset exhibits several characteristics that mirror operational credit risk data environments:

• High Dimensionality: The feature space exceeds 1,200 variables
• Mixed Data Types: Numerical values (continuous and discrete), binary indicators
• High Sparsity: A substantial proportion of features contain zero values or missing entries
• Value Range Disparity: Feature values exhibit significant variance, with magnitudes ranging from small ratios (0.001) to large transaction amounts (288,500)

Methodological Rationale

The dataset was constructed by simulating data generation processes typical within financial services institutions. Transactional behaviors, bureau records, and inquiry histories were aggregated and engineered into derivative features.

Credit Card: Value of Fraudulent Transactions: Quarterly:Counterfeit data was reported at 0.420 JPY bn in Jun 2018. This records an increase from the previous number of 0.320 JPY bn for Mar 2018. Credit Card: Value of Fraudulent Transactions: Quarterly:Counterfeit data is updated quarterly, averaging 1.100 JPY bn from Mar 1999 (Median) to Jun 2018, with 78 observations. The data reached an all-time high of 4.730 JPY bn in Mar 2003 and a record low of 0.320 JPY bn in Mar 2018. Credit Card: Value of Fraudulent Transactions: Quarterly:Counterfeit data remains active status in CEIC and is reported by Japan Credit Card Industry Association. The data is categorized under Global Database’s Japan – Table JP.KA010: Credit Card.

China Credit Card Payable Credit data was reported at 8,710.000 RMB bn in Dec 2024. This records an increase from the previous number of 8,610.000 RMB bn for Sep 2024. China Credit Card Payable Credit data is updated quarterly, averaging 3,675.000 RMB bn from Mar 2008 (Median) to Dec 2024, with 68 observations. The data reached an all-time high of 8,760.000 RMB bn in Sep 2022 and a record low of 88.410 RMB bn in Mar 2008. China Credit Card Payable Credit data remains active status in CEIC and is reported by The People's Bank of China. The data is categorized under China Premium Database’s Money and Banking – Table CN.KC: Bank Card Statistics.

This dataset had adapted from 'Credit Card Churn Prediction: https://www.kaggle.com/datasets/anwarsan/credit-card-bank-churn ' for visualization in our university project. We have modified customer information, spending behavior, and also added revenue targets.

Scenario 🕶️ In 2019, the marketing team launched a campaign to attract millennial customers (born 1980-1996) with the goal of increasing revenue and enhancing the brand's appeal to a younger audience.
As the BI team, your task is to create a dashboard for users. 1. The Vice President of Sales wants to view the performance of the credit business. 2. The marketing team is interested in understanding customer segments and customer spending to measure Customer Lifetime Value (CLV) and Marketing Cost per Acquired Customer (MCAC).

⚠️Note: This is just a suggestion to guide the creation of the dashboard

Example in Tableau

Executive summary https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F10099382%2F508a2d2d89dabdfd368743f86c2a71e1%2Fexecutive%20overview.JPG?generation=1696110593484137&alt=media" alt=""> Customer behavior https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F10099382%2F1e4a1f62a25eab3c6707d002243894c7%2Fcustomer_behaviour.JPG?generation=1696110689732332&alt=media" alt="">

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.

See earnings predictions for hundreds of public companies, powered by Earnest AI solutions suite. Predict revenue surprises, track market share, and compare performance metrics for thousands of companies based on the anonymized aggregate credit and debit data of millions of US accounts. Vela data is sourced from a variety of US financial institutions with broad geographic and demographic representation, combined to create one of the most comprehensive and accurate views of the consumer economy. AI-powered earnings predictions available for over 450 tickers on this dataset through EarnestAI Reported Metric Predictions.

This dataset is designed to support research and model development in the area of fraud detection. It consists of real-world credit card transactions made by European cardholders over a two-day period in September 2013. Out of 284,807 transactions, 492 are labeled as fraudulent (positive class), making this a highly imbalanced classification problem.

Performance Note:

Due to the extreme class imbalance, standard accuracy metrics are not informative. We recommend using the Area Under the Precision-Recall Curve (AUPRC) or F1-score for model evaluation.

Features:

• Time Series Data: Each row represents a transaction, with the Time feature indicating the number of seconds elapsed since the first transaction.
• Dimensionality Reduction Applied: Features V1 through V28 are anonymized principal components derived from a PCA transformation due to confidentiality constraints.
• Raw Transaction Amount: The Amount field reflects the transaction value, useful for cost-sensitive modeling.
• Binary Classification Target: The Class label is 1 for fraud and 0 for legitimate transactions.

Usage:

• Machine learning model training for fraud detection.
• Evaluation of anomaly detection and imbalanced classification methods.
• Development of cost-sensitive learning approaches using the Amount variable.

Data Summary:

• Total Records: 284,807
• Fraud Cases: 492
• Imbalance Ratio: Fraudulent transactions account for just 0.172% of the dataset.
• Columns: 31 total (28 PCA features, plus Time, Amount, and Class)

License:

The dataset is provided under the CC0 (Public Domain) license, allowing users to freely use, modify, and distribute the data without any restrictions.

Acknowledgements

The dataset has been collected and analysed during a research collaboration of Worldline and the Machine Learning Group (http://mlg.ulb.ac.be) of ULB (Université Libre de Bruxelles) on big data mining and fraud detection. More details on current and past projects on related topics are available on https://www.researchgate.net/project/Fraud-detection-5 and the page of the DefeatFraud project

Please cite the following works:

Andrea Dal Pozzolo, Olivier Caelen, Reid A. Johnson and Gianluca Bontempi. Calibrating Probability with Undersampling for Unbalanced Classification. In Symposium on Computational Intelligence and Data Mining (CIDM), IEEE, 2015

Dal Pozzolo, Andrea; Caelen, Olivier; Le Borgne, Yann-Ael; Waterschoot, Serge; Bontempi, Gianluca. Learned lessons in credit card fraud detection from a practitioner perspective, Expert systems with applications,41,10,4915-4928,2014, Pergamon

Dal Pozzolo, Andrea; Boracchi, Giacomo; Caelen, Olivier; Alippi, Cesare; Bontempi, Gianluca. Credit card fraud detection: a realistic modeling and a novel learning strategy, IEEE transactions on neural networks and learning systems,29,8,3784-3797,2018,IEEE

Dal Pozzolo, Andrea Adaptive Machine learning for credit card fraud detection ULB MLG PhD thesis (supervised by G. Bontempi)

Carcillo, Fabrizio; Dal Pozzolo, Andrea; Le Borgne, Yann-Aël; Caelen, Olivier; Mazzer, Yannis; Bontempi, Gianluca. Scarff: a scalable framework for streaming credit card fraud detection with Spark, Information fusion,41, 182-194,2018,Elsevier

Carcillo, Fabrizio; Le Borgne, Yann-Aël; Caelen, Olivier; Bontempi, Gianluca. Streaming active learning strategies for real-life credit card fraud detection: assessment and visualization, International Journal of Data Science and Analytics, 5,4,285-300,2018,Springer International Publishing

Bertrand Lebichot, Yann-Aël Le Borgne, Liyun He, Frederic Oblé, Gianluca Bontempi Deep-Learning Domain Adaptation Techniques for Credit Cards Fraud Detection, INNSBDDL 2019: Recent Advances in Big Data and Deep Learning, pp 78-88, 2019

Fabrizio Carcillo, Yann-Aël Le Borgne, Olivier Caelen, Frederic Oblé, Gianluca Bontempi Combining Unsupervised and Supervised Learning in Credit Card Fraud Detection Information Sciences, 2019

Yann-Aël Le Borgne, Gianluca Bontempi Reproducible machine Learning for Credit Card Fraud Detection - Practical Handbook

Bertrand Lebichot, Gianmarco Paldino, Wissam Siblini, Liyun He, Frederic Oblé, Gianluca Bontempi Incremental learning strategies for credit cards fraud detection, IInternational Journal of Data Science and Analytics

Graph and download economic data for Commercial Bank Interest Rate on Credit Card Plans, All Accounts (TERMCBCCALLNS) from Nov 1994 to May 2025 about consumer credit, credit cards, loans, consumer, interest rate, banks, interest, depository institutions, rate, and USA.

This data set provides charges for all executive credit cards.

This research aimed at the case of customers default payments in Taiwan and compares the predictive accuracy of probability of default among six data mining methods. From the perspective of risk management, the result of predictive accuracy of the estimated probability of default will be more valuable than the binary result of classification - credible or not credible clients. Because the real probability of default is unknown, this study presented the novel Sorting Smoothing Method to estimate the real probability of default. With the real probability of default as the response variable (Y), and the predictive probability of default as the independent variable (X), the simple linear regression result (Y = A + BX) shows that the forecasting model produced by artificial neural network has the highest coefficient of determination; its regression intercept (A) is close to zero, and regression coefficient (B) to one. Therefore, among the six data mining techniques, artificial neural network is the only one that can accurately estimate the real probability of default.

Envestnet®| Yodlee®'s Credit Card Data (Aggregate/Row) Panels consist of de-identified, near-real time (T+1) USA credit/debit/ACH transaction level data – offering a wide view of the consumer activity ecosystem. The underlying data is sourced from end users leveraging the aggregation portion of the Envestnet®| Yodlee®'s financial technology platform.

Envestnet | Yodlee Consumer Panels (Aggregate/Row) include data relating to millions of transactions, including ticket size and merchant location. The dataset includes de-identified credit/debit card and bank transactions (such as a payroll deposit, account transfer, or mortgage payment). Our coverage offers insights into areas such as consumer, TMT, energy, REITs, internet, utilities, ecommerce, MBS, CMBS, equities, credit, commodities, FX, and corporate activity. We apply rigorous data science practices to deliver key KPIs daily that are focused, relevant, and ready to put into production.

We offer free trials. Our team is available to provide support for loading, validation, sample scripts, or other services you may need to generate insights from our data.

Investors, corporate researchers, and corporates can use our data to answer some key business questions such as: - How much are consumers spending with specific merchants/brands and how is that changing over time? - Is the share of consumer spend at a specific merchant increasing or decreasing? - How are consumers reacting to new products or services launched by merchants? - For loyal customers, how is the share of spend changing over time? - What is the company’s market share in a region for similar customers? - Is the company’s loyal user base increasing or decreasing? - Is the lifetime customer value increasing or decreasing?

Additional Use Cases: - Use spending data to analyze sales/revenue broadly (sector-wide) or granular (company-specific). Historically, our tracked consumer spend has correlated above 85% with company-reported data from thousands of firms. Users can sort and filter by many metrics and KPIs, such as sales and transaction growth rates and online or offline transactions, as well as view customer behavior within a geographic market at a state or city level. - Reveal cohort consumer behavior to decipher long-term behavioral consumer spending shifts. Measure market share, wallet share, loyalty, consumer lifetime value, retention, demographics, and more.) - Study the effects of inflation rates via such metrics as increased total spend, ticket size, and number of transactions. - Seek out alpha-generating signals or manage your business strategically with essential, aggregated transaction and spending data analytics.

Use Cases Categories (Our data provides an innumerable amount of use cases, and we look forward to working with new ones): 1. Market Research: Company Analysis, Company Valuation, Competitive Intelligence, Competitor Analysis, Competitor Analytics, Competitor Insights, Customer Data Enrichment, Customer Data Insights, Customer Data Intelligence, Demand Forecasting, Ecommerce Intelligence, Employee Pay Strategy, Employment Analytics, Job Income Analysis, Job Market Pricing, Marketing, Marketing Data Enrichment, Marketing Intelligence, Marketing Strategy, Payment History Analytics, Price Analysis, Pricing Analytics, Retail, Retail Analytics, Retail Intelligence, Retail POS Data Analysis, and Salary Benchmarking

1. Investment Research: Financial Services, Hedge Funds, Investing, Mergers & Acquisitions (M&A), Stock Picking, Venture Capital (VC)

2. Consumer Analysis: Consumer Data Enrichment, Consumer Intelligence

3. Market Data: AnalyticsB2C Data Enrichment, Bank Data Enrichment, Behavioral Analytics, Benchmarking, Customer Insights, Customer Intelligence, Data Enhancement, Data Enrichment, Data Intelligence, Data Modeling, Ecommerce Analysis, Ecommerce Data Enrichment, Economic Analysis, Financial Data Enrichment, Financial Intelligence, Local Economic Forecasting, Location-based Analytics, Market Analysis, Market Analytics, Market Intelligence, Market Potential Analysis, Market Research, Market Share Analysis, Sales, Sales Data Enrichment, Sales Enablement, Sales Insights, Sales Intelligence, Spending Analytics, Stock Market Predictions, and Trend Analysis

Turkey Transaction Value: Credit Card Issued by BKM Member Bank: Purchase data was reported at 606,478.650 TRY mn in 2017. This records an increase from the previous number of 536,501.350 TRY mn for 2016. Turkey Transaction Value: Credit Card Issued by BKM Member Bank: Purchase data is updated yearly, averaging 174,663.000 TRY mn from Dec 2000 (Median) to 2017, with 18 observations. The data reached an all-time high of 606,478.650 TRY mn in 2017 and a record low of 762.000 TRY mn in 2000. Turkey Transaction Value: Credit Card Issued by BKM Member Bank: Purchase data remains active status in CEIC and is reported by The Interbank Card Center. The data is categorized under Global Database’s Turkey – Table TR.KA013: Credit and Debit Cards Statistics: Annual.

Kazakhstan Payment Cards: Number of Cards in Circulation: ow Visa International: Credit Card data was reported at 3,083.600 Unit th in Jun 2018. This records an increase from the previous number of 2,991.400 Unit th for May 2018. Kazakhstan Payment Cards: Number of Cards in Circulation: ow Visa International: Credit Card data is updated monthly, averaging 2,228.400 Unit th from Feb 2011 (Median) to Jun 2018, with 89 observations. The data reached an all-time high of 3,601.000 Unit th in May 2014 and a record low of 616.300 Unit th in Feb 2011. Kazakhstan Payment Cards: Number of Cards in Circulation: ow Visa International: Credit Card data remains active status in CEIC and is reported by The National Bank of the Republic of Kazakhstan. The data is categorized under Global Database’s Kazakhstan – Table KZ.KA010: Payment Cards Statistics.

Credit Card Accounts in the United States increased to 631.39 Million in the first quarter of 2025 from 617.41 Million in the fourth quarter of 2024. This dataset includes a chart with historical data for the United States Credit Card Accounts.