Multi-Tenant Churn Prediction Using Native Billing Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Predicting churn in multi-tenant systems is computationally intensive due to the need to process large amounts of behavioral data, which is typically stored in service-provider-managed data warehouses that are not easily accessible by external systems.
Innovation Solution
A multi-tenant system stores billing data in a native format common across all tenants, generating churn prediction models using this data without integrating external behavioral data, thereby reducing computing resource requirements and processing time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If behavioral data is used to predict churn, then prediction accuracy is improved, but computing resource requirements and processing time increase
Solution Approach 1:
The patent extracts and uses only billing data from the multi-tenant system rather than processing complete behavioral datasets. By taking out the essential billing information needed for churn prediction and excluding unnecessary behavioral data, the system achieves acceptable prediction accuracy while dramatically reducing computing resource requirements and processing time.
2Loss of information
If behavioral data from external systems is integrated, then prediction completeness is improved, but data integration complexity increases
Solution Approach 1:
The patent makes the multi-tenant system store billing data in a universal native format that is common across all tenants. This universal data format eliminates the need for complex data integration from external systems, as the billing data is already available in a standardized, accessible format within the system, reducing both integration complexity and administrative overhead.
3Productivity
If billing data in native format is used, then processing efficiency is improved, but data availability for analysis is reduced
Solution Approach 1:
The patent enables the multi-tenant system to serve its own billing data needs by storing data in a native format that is directly accessible for churn prediction. The system self-provides the necessary billing information without requiring external data sources or complex integrations, thereby improving processing efficiency while maintaining sufficient data availability for effective churn analysis.
Data Source
AI summary
Store a subscription dataset for each tenant of a multi-tenant system, each of the subscription datasets having a common data format native to the system, the subscription datasets including billing data and not behavioral data. Determine primary features from a particular subscription dataset. Derive secondary features from the primary features. Generate a churn prediction model based on the primary features and the secondary features. Obtain a second subscription dataset, the second subscription dataset comprising billing data that is more recent than the particular subscription dataset. Identify, using the particular churn prediction model and the second subscription dataset, one or more subscribers as a churn-risk. Report the one or more subscribers identified as a churn-risk.