Unlock instant, AI-driven research and patent intelligence for your innovation.

User-financial product selection tendency high-speed prediction method and device based on momentum acceleration stochastic gradient descent

A stochastic gradient descent, financial product technology, applied in finance, data processing applications, instruments, etc.

Active Publication Date: 2019-10-29
壹融站信息技术(深圳)有限公司
View PDF6 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, the existing methods have great disadvantages in real financial-related e-commerce platform applications

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
  • User-financial product selection tendency high-speed prediction method and device based on momentum acceleration stochastic gradient descent
  • User-financial product selection tendency high-speed prediction method and device based on momentum acceleration stochastic gradient descent
  • User-financial product selection tendency high-speed prediction method and device based on momentum acceleration stochastic gradient descent

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0088] see figure 1 , figure 1 It shows the user-financial product selection tendency high-speed prediction device based on the momentum-accelerated stochastic gradient descent of the present invention, the device includes:

[0089] The data preprocessing module 510 is used to receive global user-household financial product scoring data, process the data into a data format that can be directly used in model training, and put the processed data into the data storage module 520 .

[0090] The data storage module 520 is used to store preprocessed input data, temporary variables generated during model prediction, values ​​corresponding to initialization units, and latent feature matrices obtained from final training.

[0091] The data initialization module 530 is used to initialize the latent feature matrix for model training.

[0092] The high-speed convergence direction selection module 540 is configured to receive the initialized latent feature matrix, and determine the high-...

Embodiment 2

[0128] see figure 2 , figure 2 It shows the user-financial product selection tendency high-speed prediction method based on momentum-accelerated stochastic gradient descent of the present invention, the method includes the following steps:

[0129] S1: The server collects user-financial product rating data. The user set on the platform is denoted as M, and the product set is denoted as N. Create a matrix of |M| rows and |N| columns as the user-financial product rating matrix R. Sent to users based on momentum-accelerated stochastic gradient descent-financial product selection tendency high-speed prediction device.

[0130] S2: Use the user-financial product rating data to initialize the corresponding latent feature matrix, and construct the objective function through known rating data and corresponding predicted values.

[0131] S3: Solve the objective function according to the established objective function, and find the gradient corresponding to the decision parameter to...

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 discloses a user-financial product selection tendency high-speed prediction method and device based on momentum acceleration stochastic gradient descent. The prediction method comprisesthe steps: collecting user-financial product scoring data and constructing the scoring data into a scoring matrix of | M | rows and | N | columns;; constructing and initializing an implicit feature matrix, and constructing and solving a target function; determining the decision parameter gradient with the highest current updating convergence speed; judging whether the limit parameters of the prediction model on the gradient meet conditions or not; judging whether the prediction model achieves convergence or not; after the prediction model reaches convergence, outputting a hidden feature matrixobtained by training; and using the obtained implicit feature matrix to predict missing values in a scoring matrix. According to the method, a user-financial product selection tendency high-speed prediction result of momentum acceleration stochastic gradient descent can provide personalized services for users, and provide safe, reliable and rigorous financial services for potential users in a family financial e-commerce platform.

Description

technical field [0001] The invention relates to the technical field of computer data processing, in particular to a method and device for high-speed prediction of user-financial product selection tendency based on momentum-accelerated stochastic gradient descent. Background technique [0002] With the rapid development of computer technology and the active development of social economy, financial e-commerce platforms have penetrated into our lives. More and more users choose different financial products for investment through the financial e-commerce platform. Usually, users will make corresponding evaluations through investment reports and personal experience after purchasing products on the financial platform. Therefore, a user-oriented e-commerce consumption model has been formed. However, with the increasing maturity of financial platforms and the sharp increase in the number of financial products, users cannot choose their favorite products among the many financial pro...

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): G06Q30/02G06Q40/00G06F17/15G06F17/16
CPCG06Q30/0202G06Q40/00G06F17/16G06F17/15
Inventor 冯锦刚秦雯罗辛廖殷
Owner 壹融站信息技术(深圳)有限公司