An intelligent prediction method of search advertisement conversion based on big data
A search advertisement and intelligent prediction technology, applied in the fields of artificial intelligence, big data processing, and machine learning, can solve problems such as paying for nothing, achieve the effects of reducing data redundancy, accurate prediction, and improving user experience
Inactive Publication Date: 2019-01-22
CHONGQING UNIV OF POSTS & TELECOMM
View PDF3 Cites 19 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
On the one hand, every time the advertisement is clicked by the user, the merchant has to pay a certain cost. If the advertisement is clicked but not sold, the advertiser will pay the cost in vain. Pay the cost but still get the benefits from the transaction
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 Construction
[0046] The technical solutions in the embodiments of the present invention will be described clearly and in detail below with reference to the drawings in the embodiments of the present invention. The described embodiments are only some of the embodiments of the invention.
[0047] see figure 1 The present invention comprises the following steps:
[0048] 101. Data preprocessing operation, data preprocessing operation is performed according to the basic data of search advertisements, users, and shops;
[0049] 102. Divide the data according to the behavior time, and divide the historical data into a training set and a test set;
[0050] 103. Perform feature engineering construction operations based on historical data of search advertisements, users, and shops;
[0051] 104. Perform feature adjustment operations according to feature engineering feature distribution;
[0052] 105. Establish multiple machine learning models and perform model fusion operations;
[0053] 106. ...
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 an intelligent prediction method of search advertisement conversion based on big data, which comprises the following steps: data preprocessing; dividing the data according to the behavior time; according to the history data of search advertisement, user and store, the feature engineering construction operation is carried out, feature adjustment operation is carried out according to the feature distribution of feature engineering; multiple machine learning models are established and model fusion is performed, through the established model, the advertisement conversion rate is predicted according to the data of search advertisement, user and store. The invention mainly pretreats the search advertisement, the user and the store data, analyzes and extracts the characteristics, establishes a plurality of machine learning models and performs stacking model fusion, thereby accurately predicting the conversion rate of the advertisement and enabling the advertiser to match the user who is most likely to purchase his own goods. On the other hand, the method can also enable users to quickly find the goods with the strongest desire to buy, thus improving the user experience in the e-commerce platform.
Description
technical field [0001] The present invention relates to the technical fields of machine learning, big data processing, and artificial intelligence, especially the data division method, feature construction, model design, and predicted conversion rate prediction of advertising conversion rates on special dates. Background technique [0002] With the rapid development of the Internet, search advertising and e-commerce advertising account for an increasing proportion of Internet advertising, becoming one of the most important business models in the Internet industry. At the same time, search advertising has attracted a large number of experts and scholars because of its huge commercial value and research value, and has been extensively studied in the academic circle. The conversion rate of search advertisements, as an indicator to measure the conversion effect of advertisements, comprehensively describes users' purchase intentions for advertised products from multiple perspecti...
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): G06Q30/02G06N20/20
CPCG06Q30/0242G06Q30/0245
Inventor 王进赵金阳孙开伟欧阳卫华邓欣陈乔松李智星胡峰雷大江
Owner CHONGQING UNIV OF POSTS & TELECOMM