Predictive Model Decomposition for Parallel Processing

Solution Overview

Problem

Large and complex predictive models require significant time to load and parse, consuming substantial computing resources, making them inefficient for real-time predictions in big data environments.

Innovation Solution

The method involves decomposing predictive models into smaller sub-models, which are easier to load and parse, allowing for parallel processing across multiple computing facilities and combining results for overall predictions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If large and complex predictive models are used for predictive analytics, then prediction accuracy is improved, but processing time and resource consumption increase significantly

Engineering Contradiction:

Improveprediction accuracyVSAvoidprocessing time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent applies segmentation by decomposing a large predictive model into multiple smaller sub-models. Each sub-model processes a specific portion of the input data or predicts a specific outcome, allowing parallel processing that reduces overall processing time while maintaining the predictive accuracy of the original large model.

Inventive Principle:

Principle #1Segmentation

2Measurement precision

If large and complex predictive models are used for predictive analytics, then prediction accuracy is improved, but computing resource consumption increases substantially

Engineering Contradiction:

Improveprediction accuracyVSAvoidcomputing resource consumption

Core Design Contradiction:

Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The patent applies segmentation by decomposing a large predictive model into multiple smaller sub-models. Each sub-model processes a specific portion of the input data or predicts a specific outcome, allowing parallel processing that reduces overall processing time while maintaining the predictive accuracy of the original large model.

Inventive Principle:

Principle #1Segmentation

3Adaptability or versatility

If large and complex predictive models are used for predictive analytics, then model comprehensiveness is improved, but ease of operation deteriorates

Engineering Contradiction:

Improvemodel comprehensivenessVSAvoidease of loading and parsing

Core Design Contradiction:

Adaptability or versatilityVSEase of operation

Solution Approach 1:

The patent applies segmentation by decomposing a large predictive model into multiple smaller sub-models. Each sub-model processes a specific portion of the input data or predicts a specific outcome, allowing parallel processing that reduces overall processing time while maintaining the predictive accuracy of the original large model.

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS10558919B2Predictive analysis with large predictive models

Publication Date: 2020.02.11 INTERNATIONAL BUSINESS MACHINE CORPORATION

AI summary

An approach to optimizing predictive model analysis, comprising creating one or more model templates, decomposing a predictive model, wherein model information is extracted from the predictive model, storing the model information in the one or more model templates, creating a plurality of sub-models, associated with the predictive model, using the stored model information, sending the plurality of sub-models to a scoring engine, receiving results based on the plurality of sub-models from the scoring engine and generating predictions based on combining the results received from the scoring engine. The generated predictions can be sent to one or more analytic applications for further processing.