Bank Transaction Fraud Detection

Dataset Overview
Data Type Multivariate Default Task Classification, Regression, Clustering
Attribute Type Real Published Year 2024
Area of Dataset Finance, Banking, Crime Missing Values No
No. of Instances 200000 No. of Attribute 24

Dataset Description:

At LOL Bank Pvt. Ltd., ensuring the safety and integrity of economic transactions is a top priority. With increasingly more on line transactions and digital banking activities, fraudulent transactions have end up a good sized danger to both the financial institution and its customers. Fraudulent activities, along with unauthorized account get right of entry to, identification robbery, and suspicious transaction patterns, bring about economic losses and harm to patron agree with.

To cope with this developing subject, LOL Bank Pvt. Ltd. Is in search of a strategy to stumble on and save you fraudulent transactions in real time. This includes analyzing ancient transaction records, consisting of account info, transaction quantities, service provider records, and time stamps, to pick out patterns indicative of fraudulent conduct. The intention is to construct a robust fraud detection gadget that may distinguish among legitimate transactions and probably fraudulent ones, with minimal fake positives.

The answer must incorporate device learning algorithms to study from transaction history, allowing the machine to become aware of rising fraud strategies and adapt to evolving threats. The gadget must be able to flag suspicious transactions in real time, providing bank employees with actionable insights to take activate action. By enhancing fraud detection abilities, LOL Bank Pvt. Ltd. Objectives to shield patron belongings, lessen financial losses, and keep its reputation as a secure and honest economic organization.

Here are the information of the columns:

  1. Customer_ID: A particular identifier for every customer within the bank's system.
  2. Customer_Name: The name of the consumer making the transaction.
  3. Gender: The gender of the consumer (e.G., Male, Female, Other).
    Four. Age: The age of the consumer at the time of the transaction.
  4. State: The nation in which the patron resides.
  5. City: The metropolis wherein the client is living.
  6. Bank_Branch: The specific financial institution branch wherein the consumer holds their account.
    Eight. Account_Type: The kind of account held with the aid of the customer (e.G., Savings, Checking).
    Nine. Transaction_ID: A particular identifier for each transaction.
  7. Transaction_Date: The date on which the transaction passed off.
    Eleven. Transaction_Time: The specific time the transaction became initiated.
  8. Transaction_Amount: The financial value of the transaction.
  9. Merchant_ID: A particular identifier for the merchant worried within the transaction.
  10. Transaction_Type: The nature of the transaction (e.G., Withdrawal, Deposit, Transfer).
  11. Merchant_Category: The class of the merchant (e.G., Retail, Online, Travel).
  12. Account_Balance: The balance of the customer's account after the transaction.
  13. Transaction_Device: The tool utilized by the consumer to perform the transaction (e.G., Mobile, Desktop).
  14. Transaction_Location: The geographical vicinity (e.G., latitude, longitude) of the transaction.
  15. Device_Type: The kind of device used for the transaction (e.G., Smartphone, Laptop).
  16. Is_Fraud: A binary indicator (1 or zero) indicating whether or not the transaction is fraudulent or now not.
  17. Transaction_Currency: The currency used for the transaction (e.G., USD, EUR).
  18. Customer_Contact: The contact variety of the client.
  19. Transaction_Description: A brief description of the transaction (e.G., buy, switch).
  20. Customer_Email: The e-mail cope with related to the consumer's account.

These column descriptions give a clear expertise of the facts as a way to be used for fraud detection analysis.

Download Dataset

Share   Share