ML Customer-Business Pairing via Pattern Detection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Enterprise organizations face challenges in efficiently detecting customer needs and optimizing resource utilization to connect customers and businesses, particularly in situations where customers may require specific resources due to events like natural disasters or changes in income, and existing technologies struggle to provide timely and effective solutions.

Innovation Solution

A computing platform using machine learning to analyze historical user activity, identify anticipated purchase patterns, match them with vendor offerings, and trigger actions based on user-defined preferences, including automatic purchases and resource allocation, while considering external events that impact purchase activities.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If machine learning systems are used to detect customer needs and match them with businesses, then the effectiveness of connecting customers and businesses is improved, but the complexity of the computing infrastructure increases

Engineering Contradiction:

Improveeffectiveness of connecting customers and businessesVSAvoidcomplexity of computing infrastructure

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The system segments the complex task of customer-business matching into distinct functional modules: a pattern detection engine that analyzes purchase activities, a machine learning model that identifies needs, and a matching engine that connects customers with businesses. This modular architecture reduces overall system complexity while maintaining high effectiveness.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The computing platform acts as an intermediary between customers and businesses, mediating the matching process. The platform receives purchase activity data, processes it through multiple engines, and generates connections without requiring direct integration between customer and business systems, thereby simplifying the infrastructure.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Measurement precision

If the system analyzes historical user activity and external events to predict customer needs, then the precision of need detection is improved, but the amount of data processing and time required increases

Engineering Contradiction:

Improveprecision of need detectionVSAvoidtime required for data processing

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system performs preliminary actions by continuously analyzing historical user activity and detecting patterns in advance. The pattern detection engine processes purchase activities and builds customer profiles proactively, so when a matching opportunity arises, the system can quickly connect customers with businesses without extensive real-time processing.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system maintains continuous analysis of user activity through the pattern detection engine, which constantly processes purchase data and updates customer profiles. This continuous operation eliminates the need for intensive batch processing, reducing time delays while maintaining high detection precision.

Inventive Principle:

Principle #20Continuity of useful action

3Productivity

If the computing platform optimizes resource utilization and bandwidth utilization, then the efficiency of operations is improved, but the complexity of managing the computing infrastructure increases

Engineering Contradiction:

Improveefficiency of operationsVSAvoidcomplexity of managing computing infrastructure

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The computing platform is designed as a universal system that handles multiple functions: pattern detection, machine learning inference, matching operations, and resource management. This multi-functional architecture consolidates infrastructure requirements and simplifies management while optimizing resource utilization across all operations.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS12001970B2Machine learning based automated pairing of individual customers and small businesses

Publication Date: 2024.06.04 BANK OF AMERICA CORP

AI summary

Aspects of the disclosure relate to automated pairing of customers and businesses. A computing platform may determine, based on historical user activity of a user, a pattern of the user activity, and may identify, based on the pattern of the user activity, an anticipated purchase activity of the user. Then, the computing platform may determine a sales offering by a vendor. Then, the computing platform may match the anticipated purchase activity with the sales offering. Then, the computing platform may retrieve user-defined preference rules associated with the anticipated purchase activity. Then, the computing platform may determine whether the preference rules apply to one or more attributes of the anticipated purchase activity. Subsequently, the computing platform may trigger, based on a determination that the preference rules apply to the one or more attributes of the anticipated purchase activity, an action associated with the anticipated purchase activity.