Customer classification method and device based on cost sensitivity and semi-supervised classification

A cost-sensitive, classification method technology, applied in the field of customer classification methods and devices based on cost-sensitive and semi-supervised classification, can solve problems such as inability to mark categories, inability to determine whether to respond, overfitting, etc., to improve target customer selection performance , Good target customers choose the performance effect

Inactive Publication Date: 2018-08-10
SICHUAN UNIV
View PDF3 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

And there is a large number of customers who do not make marketing communications, because they cannot be judged whether they respond, so their categories cannot be tagged
At this time, if the research paradigm of supervised customer cl

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Customer classification method and device based on cost sensitivity and semi-supervised classification
  • Customer classification method and device based on cost sensitivity and semi-supervised classification
  • Customer classification method and device based on cost sensitivity and semi-supervised classification

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0054] Such as figure 1 As shown, customer classification methods based on cost-sensitive and semi-supervised classification include:

[0055] S1. Obtain a dataset L with category labels, a dataset U without category labels, and a test set Test, and the number of initial samples in the dataset U without category labels is m.

[0056] S2. Using the random subspace method to train N basic classification models CS for the dataset L with category labels and the dataset U without category labels.

[0057] Described step S2 comprises:

[0058] S21. Selectively mark some samples from the unlabeled dataset U and add them to the labeled dataset L, and remove these samples from the unlabeled dataset U.

[0059] Described step S21 comprises:

[0060] S211. Set the threshold k, the threshold k represents the percentage of samples that you want to mark from the unclassified data set U in the unclassified data set U; calculate the samples of the selectively labeled sample set Q and the u...

Embodiment 2

[0071] Such as figure 2 As shown, the customer classification device based on cost-sensitive and semi-supervised classification includes data acquisition module, random subspace module, classification module and voting integration module.

[0072] The data acquisition module is used to obtain a data set L with class labels, a data set U without class labels and a test set Test, and the number of initial samples in the data set U without class labels is m.

[0073] The random subspace module is used to train N basic classification models CS by using the random subspace method on the dataset L with category labels and the dataset U without category labels.

[0074]The random subspace module includes a sample selective marker submodule and a random subspace submodule. The sample selective labeling submodule is used to selectively mark some samples from the unlabeled data set U and add them to the labeled data set L, and remove these samples from the unlabeled data set U. The r...

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

No PUM Login to view more

Abstract

The invention discloses a customer classification method and device based on cost sensitivity and semi-supervised classification, and the method comprises the steps: obtaining a data set L with a class label, a data set U without class label, and a test set Test; employing a random subspace method for the data set L with the class label and the data set U without class label, and training N basicclassification models CS; employing the N basic classification models CS for the classification of the samples in the test set Test, and obtaining N intermediate classification results R1, R2,..., RN;carrying out the majority voting integration of N intermediate classification results R1, R2,..., RN, and obtaining a final classification result. The method combines cost sensitivity learning, semi-supervised classification and random subspace, can achieve the processing of data of the imbalanced types in a better way through the cost sensitivity learning, also can achieve the utilization of a large amount of information in the samples without the class label through semi-supervised learning, also can improve the target customer selection performance of a model through the random subspace, and obtains the better target customer selection performance.

Description

technical field [0001] The invention relates to the technical field of customer classification, in particular to a method and device for customer classification based on cost-sensitive and semi-supervised classification. Background technique [0002] With the advent of the era of big data, enterprises have more and more customer data, and at the same time, the marketing concept of enterprises has also changed from the past "product-centric" to "customer-centric". Due to the disadvantages of low efficiency and high cost of traditional marketing methods, the customer response rate continues to decline, and the company's capital recovery rate also decreases. Therefore, whether it has efficient marketing methods and can quickly dig out customer diversification and The ability to personalize needs has become a magic weapon for enterprises to win. In order to achieve this goal, some companies began to use database marketing as a powerful means to improve the effectiveness and per...

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
no application Login to view more
IPC IPC(8): G06K9/62G06Q30/02
CPCG06Q30/02G06F18/2411G06F18/241
Inventor 肖进刘潇潇
Owner SICHUAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap