Predictive Model Execution Engine for Marketing Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems face inefficiencies in model development, deployment, and execution for direct marketing campaigns, leading to increased time and costs due to disparate data sources, language conversion requirements, and outdated customer scores caused by billing cycle-based scoring.
Innovation Solution
An integrated infrastructure and architecture for rapid development and execution of predictive models, including a centralized data management system, data extraction tool, model validation tool, and model execution tool, which enables seamless data standardization, validation, and dynamic scoring using current customer data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If data is stored in multiple disparate sources with unique definitions and access requirements, then data availability is improved, but data standardization complexity increases and results reliability decreases
Solution Approach 1:
The patent introduces a centralized data management system as an intermediary layer between disparate data sources and modelers. This system provides a unified interface that standardizes data definitions and access methods, allowing multiple data sources to be accessed consistently without increasing modeler complexity. The intermediary handles the transformation and standardization of data from various sources.
Solution Approach 2:
The centralized data management system serves multiple functions: it stores data from diverse sources, standardizes data definitions, manages access requirements, and provides consistent data output. This multi-functional approach eliminates the need for separate standardization processes for each data source, reducing overall system complexity while maintaining data availability.
2Adaptability or versatility
If models are developed in one programming language and deployed in another, then model versatility is improved, but deployment time increases due to code conversion requirements
Solution Approach 1:
The patent employs a model execution engine that creates a virtual copy or abstraction layer between the model developer's programming language and the deployment environment. This allows models to be developed in preferred languages (Python, R, SQL) while the execution engine translates or adapts the logic to the target deployment environment, eliminating manual code conversion and reducing deployment time.
Solution Approach 2:
The patent replaces the manual mechanical process of code conversion with an automated execution engine that handles language translation and system compatibility. This substitution eliminates the need for skilled translators to manually convert model code, significantly reducing deployment time while maintaining model versatility across different programming languages.
3Device complexity
If customer scoring is based on billing cycles, then system simplicity is improved, but score freshness deteriorates and customer behavior changes are not captured timely
Solution Approach 1:
The patent transitions from a static billing-cycle-based scoring system to a dynamic real-time scoring system. The execution engine can trigger model scoring at any time based on current customer data, behavior changes, or marketing campaign needs. This dynamic approach maintains simplicity by using the same core modeling logic while enabling flexible, timely scoring that adapts to changing customer behavior and business requirements.
Data Source
AI summary
A system that enables development and execution of predictive models comprises a centralized data management system, a data extraction tool a model validation tool and a model execution tool. In embodiments, a data management system includes a data management server that can be accessed via a web browser that stores data in the form of a flat file. An extraction tool extracts data. A model validation tool validates a model by scoring an analytical environment data set and a production environment data set. A model execution tool allows a user to select when and how often a model is scored.