ML Contract Prediction Using Supply Data for Dynamic Adjustments

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing contract management systems lack the ability to accurately predict and respond to changes in market conditions and material costs, leading to inefficiencies and inaccuracies in contract adjustments.

Innovation Solution

An automated contract manager using machine learning and web scraping techniques to predict contract data, enabling automated adjustments based on historical data and supply data, and implementing these changes through smart contracts on a distributed ledger.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual contract validation and adjustment processes are used, then contract changes can be reviewed for accuracy, but the process is time-consuming and prone to human error

Engineering Contradiction:

Improvecontract validation accuracyVSAvoidcontract adjustment time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system enables self-service through automated machine learning models that independently predict contract data and generate adjustments without human intervention. The ML model automatically analyzes supply data, historical contract information, and market conditions to produce validated contract adjustments, eliminating the need for manual review while maintaining high accuracy.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces manual mechanical review processes with automated computational systems. Machine learning algorithms substitute human analysts, automatically processing supply data and generating contract adjustments with consistent accuracy and significantly reduced time requirements.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Adaptability or versatility

If contract terms are fixed after bidding, then contract stability is maintained, but the contract cannot adapt to changing market conditions or unexpected costs

Engineering Contradiction:

Improvecontract flexibilityVSAvoidcontract stability

Core Design Contradiction:

Adaptability or versatilityVSReliability

Solution Approach 1:

The system transforms static contract terms into dynamic adjustments by continuously monitoring supply data and market conditions. The machine learning model generates real-time predictions that automatically adapt contract parameters such as pricing and delivery schedules to changing conditions while maintaining overall contract stability through validated adjustment processes.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The patent implements feedback loops where supply data and market conditions are continuously fed into the machine learning model, which generates contract adjustments based on detected changes. This feedback mechanism enables the contract to adapt to new information while maintaining reliability through systematic validation of adjustments against original contract terms and business rules.

Inventive Principle:

Principle #23Feedback

3Measurement precision

If comprehensive supply data collection is performed using web scraping, then prediction accuracy is improved, but system complexity and data processing requirements increase

Engineering Contradiction:

Improveprediction accuracyVSAvoidsystem complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The system employs a multi-functional automated contract manager that integrates web scraping, data cleaning, machine learning model execution, and contract adjustment generation into a single unified platform. This universal system handles multiple tasks sequentially, from collecting supply data across multiple sources to generating validated contract adjustments, reducing the need for separate specialized systems.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The patent introduces an intermediary automated contract manager system that mediates between raw supply data and the machine learning model. This intermediary layer performs data cleaning, validation, and preprocessing, transforming unstructured web-scraped data into a format suitable for ML analysis, thereby simplifying the overall system architecture and reducing complexity.

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS12524821B2Method and system for determining predicted contract data using machine learning

Publication Date: 2026.01.13 SAUDI ARABIAN OIL CO

AI summary

A method may include obtaining historical contract data regarding various contracts for various service operations. The method may further include extracting, from various servers, supply data regarding various material components using a web scraping process. The method may further include identifying a contract among the contracts that is associated with a service operation. The method may further include determining predicted contract data for the contract using a machine-learning model, the supply data, and the historical contract data. The method further includes determining whether the predicted contract data satisfies a predetermined criterion. The method may further include determining, in response to the predicted contract data failing to satisfy the predetermined criterion, a contract adjustment based on the predicted contract data. The method may further include transmitting a command that adjusts the contract based on the contract adjustment.