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.

Context

BankSim is an agent-based simulator of bank payments based on a sample of aggregated transactional data provided by a bank in Spain. The main purpose of BankSim is the generation of synthetic data that can be used for fraud detection research. Statistical and a Social Network Analysis (SNA) of relations between merchants and customers were used to develop and calibrate the model. Our ultimate goal is for BankSim to be usable to model relevant scenarios that combine normal payments and injected known fraud signatures. The data sets generated by BankSim contain no personal information or disclosure of legal and private customer transactions. Therefore, it can be shared by academia, and others, to develop and reason about fraud detection methods. Synthetic data has the added benefit of being easier to acquire, faster and at less cost, for experimentation even for those that have access to their own data. We argue that BankSim generates data that usefully approximates the relevant aspects of the real data.

Content

We ran BankSim for 180 steps (approx. six months), several times and calibrated the parameters in order to obtain a distribution that get close enough to be reliable for testing. We collected several log files and selected the most accurate. We injected thieves that aim to steal an average of three cards per step and perform about two fraudulent transactions per day. We produced 594643 records in total. Where 587443 are normal payments and 7200 fraudulent transactions. Since this is a randomised simulation the values are of course not identical to original data.

Acknowledgements

This research was conducted during my PhD studies in Sweden at Blekinge Institute of Technology (BTH ww.bth.se). More about it: http://edgarlopez.net

Original paper

Please refer to this dataset using the following citations:

Lopez-Rojas, Edgar Alonso ; Axelsson, Stefan Banksim: A bank payments simulator for fraud detection research Inproceedings 26th European Modeling and Simulation Symposium, EMSS 2014, Bordeaux, France, pp. 144–152, Dime University of Genoa, 2014, ISBN: 9788897999324. https://www.researchgate.net/publication/265736405_BankSim_A_Bank_Payment_Simulation_for_Fraud_Detection_Research

Credit Card Fraud: Analysis and Prevention Overview Credit card fraud represents a significant threat to the integrity of financial transactions and consumer trust in digital commerce. As the reliance on credit cards for everyday purchases continues to grow, so does the sophistication of fraudsters exploiting vulnerabilities in the system. This project aims to analyze patterns of credit card fraud, understand the factors contributing to fraudulent activities, and explore effective methods for detection and prevention.

Dataset Description The dataset comprises 100,000 transactions generated to simulate real-world credit card activity. Each entry includes the following features:

TransactionID: A unique identifier for each transaction, ensuring traceability. TransactionDate: The date and time when the transaction occurred, allowing for temporal analysis. Amount: The monetary value of the transaction, which can help identify unusually large transactions that may indicate fraud. MerchantID: An identifier for the merchant involved in the transaction, useful for assessing merchant-related fraud patterns. TransactionType: Indicates whether the transaction was a purchase or a refund, providing context for the activity. Location: The geographic location of the transaction, facilitating analysis of fraud trends by region. IsFraud: A binary target variable indicating whether the transaction is fraudulent (1) or legitimate (0), essential for supervised learning models. Analysis Objectives Exploratory Data Analysis (EDA):

Examine the distribution of transaction amounts and types. Identify trends in transaction dates and locations. Analyze the ratio of fraudulent to legitimate transactions. Pattern Recognition:

Use clustering techniques to group transactions and identify unusual patterns. Explore correlations between transaction features and the occurrence of fraud. Fraud Detection Modeling:

Implement machine learning algorithms (e.g., logistic regression, decision trees, random forests) to build predictive models that can classify transactions as fraudulent or legitimate. Evaluate model performance using metrics such as accuracy, precision, recall, and the F1 score. Feature Importance Analysis:

Determine which features contribute most significantly to the detection of fraud, aiding in the refinement of fraud detection systems. Potential Solutions Real-time Monitoring Systems: Develop systems capable of analyzing transactions in real-time, flagging suspicious activities based on learned patterns and thresholds. Consumer Education: Promote awareness among consumers about the signs of credit card fraud and best practices for safeguarding personal information. Collaboration with Merchants: Work closely with merchants to implement better security measures, such as enhanced verification processes for high-risk transactions. Regulatory Compliance: Ensure compliance with regulations and standards (e.g., PCI DSS) to enhance security protocols across the payment ecosystem. Conclusion Understanding and addressing credit card fraud is vital for maintaining consumer confidence and the overall health of the financial system. Through rigorous analysis and the application of advanced machine learning techniques, this project aims to contribute valuable insights and practical solutions for combating credit card fraud effectively.

Dataset Card for Financial Fraud Labeled Dataset

  Dataset Details

This dataset collects financial filings from various companies submitted to the U.S. Securities and Exchange Commission (SEC). The dataset consists of 85 companies involved in fraudulent cases and an equal number of companies not involved in fraudulent activities. The Fillings column includes information such as the company's MD&A, and financial statement over the years the company stated on the SEC… See the full description on the dataset page: https://huggingface.co/datasets/amitkedia/Financial-Fraud-Dataset.

Context

Due to rapid growth in field of cashless or digital transactions, credit cards are widely used in all around the world. Credit cards providers are issuing thousands of cards to their customers. Providers have to ensure all the credit card users should be genuine and real. Any mistake in issuing a card can be reason of financial crises. Due to rapid growth in cashless transaction, the chances of number of fraudulent transactions can also increasing. A Fraud transaction can be identified by analyzing various behaviors of credit card customers from previous transaction history datasets. If any deviation is noticed in spending behavior from available patterns, it is possibly of fraudulent transaction. Data mining and machine learning techniques are widely used in credit card fraud detection. In those notebooks we are presenting review of various data mining and machine learning methods which are widely used for credit card fraud detections and complete this project end to end from Data Understanding to deploy Model via API .

Content

You are provided a synthetic dataset for a mobile payments application. In this dataset, you are provided the sender and recipient of a transaction as well as whether transactions are tagged as fraud or not fraud.

Acknowledgements

This work is part of the research project ”Scalable resource-efficient systems for big data analytics” funded by the Knowledge Foundation (grant: 20140032) in Sweden.

Please refer to this dataset using the following citations:

PaySim first paper of the simulator:

E. A. Lopez-Rojas , A. Elmir, and S. Axelsson. "PaySim: A financial mobile money simulator for fraud detection". In: The 28th European Modeling and Simulation Symposium-EMSS, Larnaca, Cyprus. 2016Acknowledgements

This work is part of the research project ”Scalable resource-efficient systems for big data analytics” funded by the Knowledge Foundation (grant: 20140032) in Sweden.

Please refer to this dataset using the following citations:

PaySim first paper of the simulator:

E. A. Lopez-Rojas , A. Elmir, and S. Axelsson. "PaySim: A financial mobile money simulator for fraud detection". In: The 28th European Modeling and Simulation Symposium-EMSS, Larnaca, Cyprus. 2016

Context

There is a lack of public available datasets on financial services and specially in the emerging mobile money transactions domain. Financial datasets are important to many researchers and in particular to us performing research in the domain of fraud detection. Part of the problem is the intrinsically private nature of financial transactions, that leads to no publicly available datasets.

We present a synthetic dataset generated using the simulator called PaySim as an approach to such a problem. PaySim uses aggregated data from the private dataset to generate a synthetic dataset that resembles the normal operation of transactions and injects malicious behaviour to later evaluate the performance of fraud detection methods.

Content

PaySim simulates mobile money transactions based on a sample of real transactions extracted from one month of financial logs from a mobile money service implemented in an African country. The original logs were provided by a multinational company, who is the provider of the mobile financial service which is currently running in more than 14 countries all around the world.

This synthetic dataset is scaled down 1/4 of the original dataset and it is created just for Kaggle.

Headers

This is a sample of 1 row with headers explanation:

1,PAYMENT,1060.31,C429214117,1089.0,28.69,M1591654462,0.0,0.0,0,0

step - maps a unit of time in the real world. In this case 1 step is 1 hour of time. Total steps 744 (30 days simulation).

type - CASH-IN, CASH-OUT, DEBIT, PAYMENT and TRANSFER.

amount - amount of the transaction in local currency.

nameOrig - customer who started the transaction

oldbalanceOrg - initial balance before the transaction

newbalanceOrig - new balance after the transaction

nameDest - customer who is the recipient of the transaction

oldbalanceDest - initial balance recipient before the transaction. Note that there is not information for customers that start with M (Merchants).

newbalanceDest - new balance recipient after the transaction. Note that there is not information for customers that start with M (Merchants).

isFraud - This is the transactions made by the fraudulent agents inside the simulation. In this specific dataset the fraudulent behavior of the agents aims to profit by taking control or customers accounts and try to empty the funds by transferring to another account and then cashing out of the system.

isFlaggedFraud - The business model aims to control massive transfers from one account to another and flags illegal attempts. An illegal attempt in this dataset is an attempt to transfer more than 200.000 in a single transaction.

Past Research

There are 5 similar files that contain the run of 5 different scenarios. These files are better explained at my PhD thesis chapter 7 (PhD Thesis Available here http://urn.kb.se/resolve?urn=urn:nbn:se:bth-12932).

We ran PaySim several times using random seeds for 744 steps, representing each hour of one month of real time, which matches the original logs. Each run took around 45 minutes on an i7 intel processor with 16GB of RAM. The final result of a run contains approximately 24 million of financial records divided into the 5 types of categories: CASH-IN, CASH-OUT, DEBIT, PAYMENT and TRANSFER.

Acknowledgements

This work is part of the research project ”Scalable resource-efficient systems for big data analytics” funded by the Knowledge Foundation (grant: 20140032) in Sweden.

Please refer to this dataset using the following citations:

PaySim first paper of the simulator:

E. A. Lopez-Rojas , A. Elmir, and S. Axelsson. "PaySim: A financial mobile money simulator for fraud detection". In: The 28th European Modeling and Simulation Symposium-EMSS, Larnaca, Cyprus. 2016

Some of the applications are as follows :

1)Credit Risk Assessment: Banks and financial institutions can leverage the dataset to develop models for assessing the credit risk associated with loan applicants. This involves predicting the likelihood of loan default based on various features.

2)Loan Portfolio Management: Financial organizations can use the dataset to manage and optimize their loan portfolios. This includes diversifying risk, setting interest rates, and making informed decisions about loan approval or denial.

3)Market Trend Analysis: By analyzing the dataset, researchers and analysts can identify trends in borrower behavior, regional variations, and shifts in loan purposes. This information can be valuable for making data-driven market predictions.

4)Customer Segmentation: Understanding the characteristics of different borrower segments can help banks tailor their services and products. This dataset can be used for clustering customers based on attributes like income, employment length, and loan history.

5)Regulatory Compliance: Financial institutions can use the dataset to ensure compliance with regulations. For example, assessing whether loans are being offered fairly across different demographics and regions.

6)Machine Learning Model Development: Data scientists can use this dataset to develop and test machine learning models for predicting loan outcomes. This can include classification tasks such as predicting loan approval or denial.

7)Lending Strategy Optimization: Banks can optimize their lending strategies by analyzing patterns in loan amounts, interest rates, and repayment behavior. This could involve adjusting lending criteria to attract desirable borrowers.

8)Fraud Detection: The dataset may be used to identify patterns indicative of fraudulent loan applications. Unusual patterns in borrower information could be flagged for further investigation.