Smart community big data-based commodity recommendation method

Abstract

The invention discloses a smart community big data-based commodity recommendation method, and relates to the technical field of internet information processing. The method comprises the following steps of: firstly, carrying out data pre-processing; secondly, building a sample set; carrying out feature engineering processing; carrying out model fusion; and finally recommending individualized commodity information for users, wherein the step of building sample set comprises sub-steps of extracting primary interactive behavior samples and secondary behavior samples in the last n days, extracting primary behavior samples in the last n+m days, and forming sampling samples; and features of sample set data comprise fundamental features and intersectional features. The method disclosed by the invention has the beneficial effects of reducing the content of negative samples in the sample set, improving the forecast accuracy of commodity purchase and providing more accurate and credible commodity recommendation services for the users. Meanwhile, the intersectional features are adopted to describe the data features of the sample set and forecast the user behaviors with specific meanings.

Description

technical field [0001] The present invention relates to the technical field of Internet information processing, in particular to a product recommendation method based on smart community big data. Background technique [0002] With the rapid development of computer technology and e-commerce, the number and types of commodities increase rapidly, and users are more and more keen on online shopping. In the process of urbanization, the development of smart cities has gradually become the mainstream trend of urban construction. In the process, as an important part of smart cities, smart communities have also been vigorously developed. Therefore, as the proportion of users shopping on the Internet increases year by year, how to quickly, conveniently and accurately recommend products to users in the smart community has become the focus of attention of industry insiders and experts. [0003] Faced with a dazzling array of products, users need to spend a lot of time to find the produ...

AI Technical Summary

Problems solved by technology

Based on content recommendation, its recommendation results are intuitive, easy to analyze, and do not require domain knowledge, but it is not easy to handle complex attributes, and it needs enough data to construct a classifier; based on collaborative filtering recommendation, it has personalized recommendations, a high degree of automation, and can handle complex non- Structured objects and other advantages, but can not solve new user problems, new project problems, sparsity problems, and system extension problems; knowledge-based recommendation can be regarded as a kind of reasoning technology to some extent, it is not a Recommended based on user needs and preferences

Images