Advertisement recommendation prediction system and method

Abstract

The invention discloses an advertisement recommendation prediction system and method. The advertisement recommendation prediction system comprises a data acquisition module, a feature extraction and preprocessing module, a model construction and training module and a prediction recommendation module. The data acquisition module is used for acquiring user log data and advertisement information data; the feature extraction and preprocessing module is used for obtaining user effective click data according to the user log data and the advertisement information data, analyzing according to the effective click data of the user to obtain a corresponding characteristic spectrum; the model construction and training module is used for constructing a GRU neural network model through a recurrent neural network algorithm according to the characteristic spectrum, establishing a positive and negative sample training set according to the advertisement information data, constructing a binary classification model according to the positive and negative sample training set, and obtaining a prediction model through the binary classification model and the GRU neural network model; and the prediction recommendation module is used for obtaining an advertisement prediction click rate according to the prediction model and the test data, and obtaining advertisement prediction data according to the advertisement prediction click rate.

Description

technical field [0001] The invention relates to the field of data analysis, in particular to a CNN+GRU-based advertising recommendation and prediction system and method. Background technique [0002] The emergence and popularization of the Internet has brought a large amount of information to users, which has met the needs of users for information in the information age. Sometimes you can't get the part of the information that is really useful to you, and the efficiency of using the information is reduced. This process of browsing a large amount of irrelevant information and products will undoubtedly lead to the continuous loss of users who are submerged in the problem of information overload. [0003] In order to provide better services to users and earn more profits while providing services to users, more and more companies use personalized recommendation technology to help users find what they like faster. Based on the user's behavior records on the product, combined wi...

AI Technical Summary

Problems solved by technology

A typical model based on Long Short Term Memory (LSTM) is used to predict and recommend advertisements, but the model of this method is less likely to converge during training, and it takes a long time and is difficult to train the model

Images