Resource recommendation method, device and equipment based on XGBoost model
A recommendation method and model technology, applied in the computer field, can solve the problem of low accuracy of resource recommendation, and achieve the effect of promoting the transaction rate, improving the customer experience, and shortening the screening time.
Pending Publication Date: 2022-04-29
深圳壹账通创配科技有限公司
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] In view of this, this application provides a resource recommendation method, device and equipment based on the XGBoost model, which relates to the field of computer technology and can solve the problem of low accuracy in resource recommendation
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment approach
[0040] As another implementation manner, the feature evaluation index may further include: a variance evaluation index, and the first preset index threshold further includes a minimum variance threshold and a maximum variance threshold. Obtaining the second feature set from the first feature set includes: eliminating the preset feature items whose corresponding feature weights are less than the preset weight threshold in the first feature set to obtain the second feature set, and eliminating feature evaluation indicators that are less than the minimum variance threshold or feature evaluation indicators that are greater than The preset feature items with the maximum variance threshold obtain the second feature set.
[0041] Among them, the setting of the variance threshold should be based on the business meaning of each preset feature item, select a reasonable range of values, each preset feature item contains a large amount of feature data, calculate the variance of each preset...
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
Login to View More Abstract
The invention discloses a resource recommendation method, device and equipment based on an XGBoost model, relates to the technical field of computers, and can solve the problem of low accuracy of resource recommendation. Comprising the following steps: training an XGBoost model by using a first feature set constructed by historical inquiry data, and determining feature important weights of the first feature set by using the trained XGBoost model; removing preset feature items with feature important weights smaller than a preset weight threshold value and / or feature evaluation indexes smaller than a first preset index threshold value from the first feature set to obtain a second feature set; iteratively training the XGBoost model by using the second feature set until the model evaluation index of the XGBoost model is greater than a second preset index threshold, and determining the XGBoost model as a transaction prediction model; inputting the real-time resource data into the transaction prediction model, and determining the transaction prediction probability of the real-time resource data; and generating ordering resource recommendation for the target subject according to the transaction prediction probability.
Description
technical field [0001] The present application relates to the field of computer technology, in particular to a resource recommendation method, device and equipment based on an XGBoost model. Background technique [0002] Users of the trading platform include resource demanders and resource suppliers. Resource demanders can upload resource requirements in the trading platform, and the trading platform will screen relevant resource suppliers and related resource data, and push the screened content to resource demanders. However, due to the large amount of matching related resource suppliers and related resource data, it is easy to cause resource demanders to spend a lot of time selecting resources. In order to create a good user experience, it is necessary to combine the actual needs of resource demanders to generate accurate resource recommendations for resource demanders. [0003] At present, when generating resource screening for resource demanders, it is mainly through ma...
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
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06Q30/06G06Q10/04G06F16/9035G06N20/00
CPCG06Q30/0631G06Q10/04G06F16/9035G06N20/00
Inventor 卢晓萍
Owner 深圳壹账通创配科技有限公司