Credit card fraud identification method

Abstract

The invention discloses a credit card fraud identification method, and relates to the technical field of credit cards. The identification method comprises the following steps: after desensitizing acquired data, dividing the acquired data into a training set and a test set; adding part of noise to the fraudulent data in the training set, generating new fraudulent data, adding the new fraudulent data into the training set, and solving the problem of imbalance of the training set; a PCA method is adopted to perform feature extraction on the training set and the test set, and after feature vectorsare obtained, adopting an RF algorithm to construct a classifier according to feature data of the training set; importing the test set feature data into an RF classifier to identify and classify fraudulent transactions; and finally, evaluating the classification result by using a cost evaluation method to obtain the performance of the fraud identification method. According to the method, information can be quickly collected and preprocessed, and meanwhile, new fraud data is generated and added into a training set; modeling and classification are convenient to achieve, meanwhile, data evaluation can be achieved, and efficiency is improved.

Description

technical field [0001] The invention belongs to the technical field of credit cards, and in particular relates to a credit card fraud identification method. Background technique [0002] Credit cards are also called debit cards. It is a non-cash transaction payment method and a simple credit service. The credit card is issued to the cardholder by the bank or credit card company according to the credit and financial resources of the user. The cardholder does not need to pay cash when using the credit card, and the repayment will be made on the bill date. [0003] There are fraudulent behaviors in existing credit cards, and there are often loopholes in the identification, which makes it impossible to detect, and at the same time, the efficiency is low. Contents of the invention [0004] In order to solve the existing fraudulent behaviors of credit cards, loopholes often appear during recognition, resulting in the problems of undetectability and low efficiency; the purpose ...

AI Technical Summary

Problems solved by technology

[0004] In order to solve the fraudulent behavior of existing credit cards, there are often loopholes in the identification, resulting in undetectable and low efficiency problems; the purpose of the present invention is to provide a credit card fraud identification method

Images