Improved Lasso+RBF neural network combined prediction model

Abstract

The invention relates to an improved Lasso+RBF neural network combined prediction model, and belongs to the field of big data analysis and processing. A prediction process of the model comprises the following steps of: defining life cycle features of a customer relationship so as to divide a customer life cycle into an obtaining stage, a lifting stage, a mature stage, a decline stage and a loss stage; taking customers in the loss stage as a training set and a test set of the model, taking customers in the other four stages as prediction customers, and subdividing the customers in the loss stage into the former four stages; respectively extracting features by using Lasso regression and respectively training an RBF neural network model corresponding to each stage; respectively substituting the customers in the former four non-loss stages into the trained models corresponding to the stages to carry out prediction; and finally combining the obtained prediction results to obtain a to-be-lost customer set. According to the method provided by the invention, the extracted features are more correct, the unbalance of data is decreased and the prediction accuracy is improved.

Description

technical field [0001] The invention belongs to the field of big data analysis and processing, and relates to a method based on dividing customers according to their life cycle and adopting an improved Lasso+RBF neural network combination forecasting model to predict the loss of telecom customers. Background technique [0002] Today, with the popularity of smart phones and the rapid development of the mobile Internet, telecom companies have accumulated unprecedented data resources, and the corresponding data storage capacity is hundreds of terabytes per day. Massive data has the typical characteristics of big data, so it is called "telecom big data", which includes call detailed records, traffic and phone bill consumption, business processing information, basic user information, etc. Because traditional methods are not suitable for large-scale, dynamic and unstructured data types, this part of data implies a large number of possibilities to improve the stability and performa...

AI Technical Summary

Problems solved by technology

Because traditional methods are not suitable for dealing with large, dynamic and unstructured data types, traditional analysis methods are more likely to encounter performance bottlenecks in customer churn analysis, and because many existing analysis and prediction models are based on the entire data set Extract features, so it is not accurate enough when analyzing

Images