Financial time series classification method for abnormal financial account detection, and application thereof

A technology of financial time series and classification methods, applied in neural learning methods, special data processing applications, structured data retrieval, etc., can solve problems such as abnormal financial account detection needs to be improved, single extraction of local information and global information, etc.

Pending Publication Date: 2020-10-20
HARBIN INST OF TECH AT WEIHAI +1
View PDF3 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] However, most of these methods only extract local information or global information, and are used for the detection of abnormal financial accounts.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Financial time series classification method for abnormal financial account detection, and application thereof
  • Financial time series classification method for abnormal financial account detection, and application thereof
  • Financial time series classification method for abnormal financial account detection, and application thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0072] This embodiment provides a financial time series classification method for abnormal financial account detection, including the following steps:

[0073] Step 1. Data set construction for financial time series classification:

[0074] The data set is constructed based on the original data. The original data includes the transaction flow data of abnormal financial accounts and normal financial accounts. The transaction flow data includes the transaction account card number, transaction time, transaction amount, counterparty account number and summary description. The transaction account card number has been obtained by Economic Investigation Whether the personnel mark is an abnormal financial account, the data set has the following definition;

[0075] (1)CB={(C 1 , Y 1 ),..., (C i , Y i ),..., (C n , Y n )}, 1≤i≤n

[0076] CB represents the label corresponding to n transaction account card numbers, Y i The value is 0 or 1, where 1 represents an abnormal financial...

Embodiment 2

[0118] Utilize a kind of financial time series classification method for abnormal financial account number detection described in embodiment 1, be used for detecting whether financial account number is abnormal, comprise the following steps:

[0119] When it is necessary to detect whether a transaction account card number containing L pieces of transaction flow data is an abnormal financial account number, assuming that the length of the financial time series in the training data set is n, the transaction flow data of the transaction account card number is processed as follows:

[0120] (1) Sort all the transaction flow data according to the transaction time, and the data with the early transaction time is arranged before the data with the late transaction time, so as to obtain the original financial time series [x 1 ,...,x L ];

[0121] (2) If L0 In the original financial time series [x 1 ,...,x L ] to get the input sequence [x 1 ,...,x L , x 0 ,...,x 0 ];

[0122] (3) ...

Embodiment 3

[0127] The present invention also provides a device for implementing a financial time series classification method for abnormal financial account detection, including:

[0128] A memory for storing computer programs and a financial time series classification method for detecting abnormal financial account numbers;

[0129] The processor is used to execute the computer program and the financial time series classification method for abnormal financial account number detection, so as to realize the steps of the financial time series classification method for abnormal financial account number detection.

[0130] The present invention also provides a computer-readable storage medium with a method for classifying financial time series for detecting abnormal financial account numbers, where a computer program is stored on the computer-readable storage medium, and the computer program is executed by a processor to implement Steps of a financial time series classification method for ab...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention relates to a financial time series classification method for abnormal financial account detection, and application thereof. According to the method, a financial time sequence data set ofa financial account can be constructed and expanded from transaction flow data of an abnormal financial account and a normal financial account; a neural network model with a plurality of stacked Blocks (wherein each Block contains Local BiLSTM, Self-Attention, residual connection, Layer Normalization, Position-wise Feed-Forward Networks) is used to simultaneously extract local and global mode characteristics of a sequence from a financial time sequence; and finally, a softmax classification layer is used to classify the financial time sequence to achieve the detection function of abnormal financial accounts.

Description

technical field [0001] The invention relates to a financial time series classification method and application for detecting abnormal financial account numbers, belonging to the technical field of financial transaction security. Background technique [0002] Abnormal financial account numbers refer to transaction account numbers that involve illegal financial activities. These accounts are usually different from the real economic activities of ordinary accounts, and thus exhibit various abnormal behavior characteristics, including abnormal capital flows, abnormal transaction partners, and abnormal transactions. transaction mode and so on. These illegal financial behaviors have brought huge losses to the society and the people. Timely and effective detection and identification of abnormal financial transaction accounts will help to stop such economic crimes in a timely manner, avoid economic losses, and maintain the security of the financial market. . The anomaly detection o...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06F16/28G06F16/2458G06N3/04G06N3/08
CPCG06F16/285G06F16/2474G06N3/08G06N3/044G06N3/045
Inventor 施莹王巍王佰玲李斌辛国栋黄俊恒
Owner HARBIN INST OF TECH AT WEIHAI
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap