Marketing method and device based on artificial intelligence decision tree

Abstract

The invention relates to a marketing method and device based on an artificial intelligence decision tree, and the method comprises the steps: obtaining training sample data, enabling the training sample data to comprise a plurality of pieces of potential user sample data, and enabling each piece of potential user sample data to comprise potential user feature data which comprise current account balance data, annual average account balance data, account balance average growth rate data, account activeness data, enterprise operation age limit data, tax credit rating data, tax amount average growth rate data, and the customer category are one of important value customers, important retention customers, important development customers and low value customers; based on the training sample data,obtaining a decision tree customer category prediction model through training; obtaining target user feature data; obtaining a customer category to which the target user belongs according to the target user feature data; and displaying the customer category to which the target user belongs so as to facilitate a customer manager to make a corresponding offline marketing plan, or marketing a product corresponding to the customer category.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to a marketing method and device based on an artificial intelligence decision tree. Background technique [0002] With the rapid development of big data technology, the huge data owned by banks and the massive data on the Internet have become treasures that need to be mined urgently. At the same time, user marketing has high requirements for data accuracy, and high-quality customer data can greatly improve the success rate of marketing. [0003] At present, the credit department of the banking industry mainly adopts the "flood irrigation" method of mining target customers, that is, through simple screening, proofreading, and splicing of bank user data and external data, a marketing white list with rough quality and huge data volume is formed. Then the account manager will sell all the products one by one to the users in the list. This method cannot customize personalized data for...

AI Technical Summary

Problems solved by technology

[0003] At present, the credit department of the banking industry mainly adopts the "flood irrigation" method of mining target customers, that is, through simple screening, proofreading, and splicing of bank user data and external data, a marketing white list with rough quality and huge data volume is formed. Then the account manager will sell all the products to the users in the list one by one. This method cannot customize personalized data for different users. The user groups are not very targeted and the marketing success rate is low.

Images