Method and system for establishing user behavior periodic model based on transverse federated learning

Abstract

The invention provides a method and system for establishing a user behavior period model based on transverse federated learning. The method comprises steps of collecting the historical behavior data of a user, and carrying out the preprocessing of the historical behavior data of the user; dividing the preprocessed data according to user IDs, and constructing time series data; performing vectorization processing on the time series data; transverse federation learning being carried out according to the user feature vectors, each participant training a local model locally by using a long-term andshort-term memory artificial neural network, and trained model parameters being uploaded to a model aggregation server; updating and aggregating the model parameters to obtain aggregated model parameters; detecting whether the aggregation model is converged or not, and if not, returning aggregation model parameters to the participant to continue iterative training until the detected aggregation model is in a convergence state; and establishing a user behavior period prediction model according to the aggregation model parameters of the aggregation model in the convergence state, and downloading the user behavior period prediction model to the participant.

Description

technical field [0001] The invention relates to the technical field of data processing, in particular to a method and system for establishing a user behavior cycle model based on horizontal federated learning. Background technique [0002] With the development of computer technology, more and more technologies are applied in the financial field, and the traditional financial industry is gradually transforming into Finteh. Due to the security and real-time requirements of the financial industry, higher requirements are put forward for technology. . [0003] In the current information age, users will have a variety of behaviors when they perform operations related to the financial field on the mobile terminal. Some behaviors have a certain periodicity. Mining the user's behavioral rules and applying them can greatly improve the user's mobile terminal experience. In the prior art, due to issues such as privacy of user data, only simple statistical calculations can be performed...

AI Technical Summary

Problems solved by technology

[0006] In order to solve the problems existing in the existing technology, the present invention proposes a method and system for establishing a user behavior cycle model based on horizontal federated learning, which can share data on the premise of ensuring the privacy of user data and break the dilemma of "data islands" , so that user behavior data between different commercial banks (participants) can be shared under the premise of safety, and joint modeling can be realized; to overcome the extreme imbalance in the sample data of the internal training model of commercial banks, and to provide applicable data through horizontal federated learning technology The joint modeling scheme of behavioral cycle mining between mobile terminals of commercial banks realizes joint modeling while ensuring the privacy of user behavior data of all parties, enriches sample data (especially negative sample data), and improves the accuracy of model prediction sex

Images