Click rate prediction model training method, recommendation method, device and electronic equipment

Abstract

The invention provides a click rate prediction model training method, a recommendation method, a device, electronic equipment and a storage medium. The click rate prediction model training method comprises the steps of acquiring sample features and click results, corresponding to users, of the sample features; initializing a click rate prediction model according to set weight parameters; processing the sample features through the click rate prediction model to obtain a predicted click rate; constructing a target function according to an error between the click result and the predicted click rate and a zero norm regular term; and reversely propagating the error in the click rate prediction model through the target function, and updating a weight parameter of the click rate prediction modelin a propagation process. Through the click rate prediction method and device, the sparsity of the weight parameters can be improved. The file size of the generated click rate prediction model is reduced, and the click rate prediction accuracy is improved.

Description

Technical field [0001] The invention relates to artificial intelligence technology, in particular to a training method, a recommendation method, a device, an electronic device and a storage medium of a click rate prediction model. Background technique [0002] Artificial Intelligence (AI) is a theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge, and use knowledge to obtain the best results. Machine Learning (ML, Machine Learning) is a multi-field cross-discipline. It is the core of artificial intelligence and the fundamental way to make computers intelligent. Its applications are in various fields. [0003] Click-through rate prediction is an important application branch of machine learning. For content data providers, click-through rate predictions are usually made on various content data, so that the pushed content da...

AI Technical Summary

Problems solved by technology

[0004] In the click-through rate prediction model solution provided by related technologies, the sparsity of the weight parameters obtained through training is poor, and the size of the model file is relatively large. When the memory of the device where the model is deployed is limited, the performance of the model may be limited or even unusable. Low Applicability of CTR Prediction

Images