Procurement Modeling System for Price Reasonableness Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current procurement systems rely on incomplete or nonspecific transaction data for price reasonableness analyses, often leading to delayed and aggregated price evaluations, which can hinder the purchaser's ability to ensure cost-effectiveness in procurement decisions.
Innovation Solution
A procurement modeling system utilizing machine-learning models, such as gradient boosting or AdaBoost, to predict price reasonableness by analyzing historical transaction data, providing line-item breakdowns and real-time price quotations, and recommending procurement processes to ensure reasonable pricing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual price reasonableness analysis using complex spreadsheets is used, then price evaluation can be performed, but the analysis is based on incomplete or nonspecific transaction data and requires manual effort
Solution Approach 1:
The system performs preliminary actions by collecting and storing comprehensive transaction data from multiple sources (internal ERP systems, market databases, supplier information) before the actual procurement decision. This pre-collection of data ensures that when price reasonableness analysis is needed, complete and specific transaction information is already available, eliminating the need to rely on incomplete manual data gathering.
Solution Approach 2:
The patent introduces an intermediary procurement management system that acts as a mediator between raw transaction data and price reasonableness analysis. This intermediary system automatically aggregates, validates, and structures data from multiple sources into a comprehensive transaction database, providing complete and standardized data to the analysis engine without requiring manual spreadsheet compilation.
2Quantity of substance
If aggregate price reports are generated from completed procurements, then overall spending information is available, but line-item breakdown and real-time pricing information is lost
Solution Approach 1:
The system applies segmentation by maintaining transaction data at the finest granular level (individual line-items) rather than aggregating it. Each line-item transaction is stored separately with complete details including product specifications, quantities, prices, and supplier information. This segmented data structure enables both aggregate analysis and detailed line-item examination without loss of precision.
Solution Approach 2:
The patent adds another dimension to data storage by maintaining both aggregated views and detailed line-item views simultaneously through a multi-level data structure. The system organizes data hierarchically, allowing users to drill down from aggregate procurement totals to specific line-item details, effectively adding a dimensional layer that preserves both summary and detailed information.
3Ease of operation
If manual spreadsheet analysis is used for price evaluation, then price reasonableness can be assessed, but processing speed and real-time decision-making capability are reduced
Solution Approach 1:
The system implements self-service by automatically performing price reasonableness analysis without requiring manual spreadsheet operations. The procurement management system autonomously collects transaction data, compares prices against historical and market data, validates information completeness, and generates analysis results automatically. This eliminates manual effort while maintaining ease of operation through automated workflows.
Solution Approach 2:
The patent replaces the mechanical manual spreadsheet analysis system with an automated electronic procurement management system. The manual process of gathering data, comparing prices, and generating reports is substituted with automated data collection from integrated systems, algorithmic price comparison, and automated report generation, dramatically increasing processing speed while maintaining analytical capability.
4Measurement precision
If comprehensive transaction data collection is implemented, then price reasonableness analysis accuracy improves, but system complexity and data processing requirements increase
Solution Approach 1:
The system applies universality by designing a multi-functional procurement management platform that handles multiple tasks within a single integrated architecture. The system simultaneously performs data collection from various sources, data validation, aggregation, analysis, reporting, and decision support functions. This universal platform approach consolidates what would otherwise require multiple separate systems, managing complexity through integration rather than proliferation of components.
Solution Approach 2:
The patent merges multiple data collection and processing functions into a unified procurement management system. Instead of separate systems for internal data management, market data collection, supplier information storage, and price analysis, the patent combines these functions into an integrated platform that handles all tasks through coordinated modules, reducing overall system complexity while maintaining comprehensive data collection capabilities.
Data Source
AI summary
A method implemented by computer servers associated with a procurement services platform includes accessing data for a set of transactions associated with a potential procurement transaction between a purchaser entity and a plurality of supplier entities. The transactions include a line-item. The method includes inputting the data for the set of transactions into a machine-learning model trained to generate a prediction of a price quotation for each of the plurality of supplier entities based on the line-item. The prediction of the price quotation includes an estimated reasonable price for a supplier entity to supply a product or service to the purchaser entity. The method includes generating, by the machine-learning model, the prediction of the price quotation for each of the plurality of supplier entities and generating a recommendation for each of the plurality of supplier entities based on the prediction of the price quotation.