Machine Learning Lead-Time Clustering for Supply Chain Correction

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing supply chain management systems fail to accurately measure and correct discrepancies between designed and actual operations, leading to inefficiencies and revenue loss due to chronic supplier issues and inaccurate lead time planning.

Innovation Solution

A dynamic supply chain planning system utilizing machine learning algorithms to analyze historical lead time data, forecast future lead times, and cluster similar deviations, enabling systematic corrections and adjustments.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional supply chain management systems are used to track and measure operations, then system simplicity is maintained, but measurement precision of actual capabilities versus design is insufficient

Engineering Contradiction:

Improvemeasurement precisionVSAvoiddevice complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent replaces traditional mechanical tracking systems with machine learning algorithms that automatically analyze historical data and predict supply chain performance. The ML system processes unstructured data from multiple sources to generate predictions about lead times, delivery performance, and potential disruptions, eliminating the need for complex manual measurement systems while improving precision.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent introduces machine learning models as intermediaries between raw supply chain data and decision-making processes. These ML models act as mediators that translate historical operational data into actionable insights about future performance, enabling accurate measurement of supply chain capabilities without requiring direct complex measurement infrastructure.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Reliability

If historical data analysis is performed to identify root causes of deviations, then reliability of supply chain planning is improved, but loss of time for data processing and analysis increases

Engineering Contradiction:

ImprovereliabilityVSAvoidloss of time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The patent performs preliminary analysis by continuously training machine learning models on historical supply chain data to establish baseline performance patterns and root cause relationships before actual planning decisions are needed. This pre-computed knowledge enables rapid, reliable predictions during actual supply chain operations without requiring time-consuming ad-hoc analysis.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent implements continuous learning systems that constantly process historical data and update predictive models in real-time. This continuous analysis maintains up-to-date knowledge of supply chain patterns and root causes, enabling reliable predictions without intermittent time-consuming batch processing, as the system learns continuously from incoming data streams.

Inventive Principle:

Principle #20Continuity of useful action

3Productivity

If machine learning algorithms are deployed to forecast lead times and cluster deviations, then productivity of supply chain planning is improved, but device complexity of the system increases

Engineering Contradiction:

ImproveproductivityVSAvoiddevice complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The patent segments the supply chain planning system into distinct functional modules: data collection components, machine learning model training modules, prediction generation components, and result visualization interfaces. This segmentation allows each component to be independently optimized and managed, improving overall productivity while making the complex system more controllable and maintainable through modular architecture.

Inventive Principle:

Principle #1Segmentation

4Loss of energy

If systematic corrections are made based on ML predictions, then loss of energy for manual adjustments is reduced, but measurement precision requirements increase

Engineering Contradiction:

Improveloss of energyVSAvoidmeasurement precision

Core Design Contradiction:

Loss of energyVSMeasurement precision

Solution Approach 1:

The patent implements feedback loops where machine learning predictions about lead times and performance deviations automatically trigger corrective actions in supply chain operations. The system continuously monitors actual outcomes versus predictions, uses this feedback to refine ML models, and adjusts planning decisions in real-time, reducing manual intervention while maintaining high measurement precision through automated closed-loop control.

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS12412137B2Analysis and correction of supply chain design through machine learning

Publication Date: 2025.09.09 KINAXIS INC

AI summary

A method and system for a machine learning duster analysis of historical lead time data, which is augmented by one or more features. The data can also be divided into groups, based on time-density of the data, with clustering performed on each group. Furthermore, clustering can also be projected onto two dimensions. In addition, the historical lead time data is separated into a plurality of tolerance zones based on tolerance criteria. The clusters are separated in accordance with a tolerance zone of each group; and further separated according to one or more lead time identifiers to provide one or more separated clusters.