Method for predicting number-carrying transfer-out of telecommunication user based on machine learning
A technology of machine learning and telecommunications industry, applied in the field of telecommunications, can solve problems such as early warning of difficult user porting out, low prediction accuracy of network transfer users, etc., and achieve the effect of improving prediction efficiency
Pending Publication Date: 2020-12-29
ZHEJIANG HONGCHENG COMP SYST
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
The problem with this method is that it is easy to generalize and there are many uncertain factors. Therefore, the prediction accuracy of network transfer users is not high, and it is difficult to achieve early warning when users transfer out with their numbers.
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
[0025] Example: such as figure 1 As shown, a method based on machine learning to predict the number portability of users in the telecommunications industry includes the following steps:
[0026] 1) Collect characteristic variable data and perform data preprocessing and save it in the database. Sample samples are taken in the database, and the ratio of positive samples to negative samples is controlled at 1:10. The number is transferred out to the user.
[0027] Define the target variable to port the number and transfer the caliber, that is, the positive sample:
[0028] The user's actual number portability transfer caliber:
[0029] Taking the target user in the nth month as an example, one of the following is enough:
[0030] (n + 1 month) or (n + 2 months) or (n + 3 months) users who port their numbers out.
[0031] Such as figure 2 As shown, the characteristic variables include the characteristics of the existing existing users in various dimensions, mainly starting f...
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 relates to the technical field of telecommunication, in particular to a method for predicting number-carrying transfer-out of telecommunication users based on machine learning. The method comprises the following steps of: 1) acquiring characteristic variable data, preprocessing the data, storing the data into a database, sampling samples in the database, and controlling the ratio ofpositive samples to negative samples to be 1: 10; 2) randomly dividing the samples into a training set and a test set; 3) selecting an XGBoost algorithm as a basis to construct a prediction model, andinputting the prediction model into the training set to train the prediction model to obtain a prediction probability value and an importance degree of features; and 4) carrying out data prediction on the test set by utilizing the trained model, evaluating the prediction model according to a prediction result, and if the evaluation result is lower than a threshold value, carrying out optimizationiteration on the prediction model. The method has the beneficial effects that the prediction efficiency is improved, early warning and timely system maintenance are realized, and the prediction modelcan dynamically perform optimization iteration.
Description
technical field [0001] The invention relates to the technical field of telecommunication, in particular to a method for predicting number portability of users in the telecommunication industry based on machine learning. Background technique [0002] At the request of the Ministry of Industry and Information Technology, the number portability service will be fully implemented in November 2019. The main content is that users can choose a suitable telecom operator according to their own wishes. change number. [0003] For operators, number portability transfer is actually divided into two parts: number portability transfer out and number portability transfer in. Number porting refers to the transfer of the user's original number from the local network operator to another network operator. It can be regarded as a situation where high-risk users leave the network. Number porting is the opposite. [0004] Customer resources are the core competitiveness of telecom operators. How...
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 IPC IPC(8): H04W8/28G06N20/00
CPCH04W8/28G06N20/00
Inventor 吴勇严伟强钟宏泽王凯李纺梁建斌陈一蕾
Owner ZHEJIANG HONGCHENG COMP SYST