Explainable AI Risk Model for Dynamic XaaS Pricing

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current Anything as a Service (XaaS) models face challenges in accurately predicting maintenance costs for users, leading to potential undercharging of high-risk users and overcharging of low-risk users, due to flat pricing that disregards unique user characteristics.

Innovation Solution

An explainable artificial intelligence (AI) risk model is implemented to determine predicted maintenance costs based on user-specific features, providing actionable recommendations to reduce costs and improve pricing accuracy, using machine learning models like decision trees and uplift trees to differentiate between risk types and provide transparent risk reductions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Device complexity

If flat pricing is used for XaaS models, then pricing simplicity is maintained, but pricing accuracy and fairness deteriorate due to inability to differentiate between user risk levels

Engineering Contradiction:

Improvepricing model complexityVSAvoidmaintenance cost prediction accuracy

Core Design Contradiction:

Device complexityVSMeasurement precision

Solution Approach 1:

The patent applies local quality by transitioning from uniform flat pricing to differentiated pricing tiers based on user-specific risk profiles. The system segments users into different risk categories (low, medium, high risk) and assigns appropriate pricing levels, allowing each user segment to receive pricing tailored to their specific characteristics and maintenance needs.

Inventive Principle:

Principle #3Local quality

Solution Approach 2:

The system changes the pricing parameter from a static flat rate to a dynamic parameter that varies based on predicted maintenance costs and risk assessments. By introducing risk-based pricing as a variable parameter, the system can accurately reflect different user needs while maintaining computational simplicity through automated risk evaluation.

Inventive Principle:

Principle #35Parameter changes

2Measurement precision

If risk-based pricing is implemented, then pricing accuracy improves, but system complexity increases due to need for AI models and risk assessment mechanisms

Engineering Contradiction:

Improvemaintenance cost prediction accuracyVSAvoidpricing system complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The system implements self-service by having the AI risk assessment model automatically evaluate user characteristics and determine pricing tiers without manual intervention. The process is autonomous, where the system independently analyzes user data, predicts maintenance costs, and applies appropriate pricing, reducing the need for complex manual pricing committees or adjustments.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces complex manual pricing mechanisms with automated AI/ML-based risk assessment models. Instead of requiring complicated human decision-making processes for pricing, the system uses machine learning algorithms that automatically process user data and determine appropriate pricing levels, simplifying the overall system architecture despite the introduction of AI components.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Measurement precision

If AI risk models are used to predict maintenance costs, then cost prediction accuracy improves, but computational resources and processing time increase

Engineering Contradiction:

Improvepredicted maintenance cost accuracyVSAvoidcomputational resource consumption

Core Design Contradiction:

Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The system applies partial action by using AI risk models only for initial risk assessment and pricing determination, rather than continuously running complex computations for all operations. The AI model provides a preliminary risk evaluation that guides subsequent simpler processing steps, reducing overall computational burden while maintaining accuracy for critical pricing decisions.

Inventive Principle:

Principle #16Partial or excessive action

Data Source

PatentUS20240126670A1Identifying technology refresh through explainable risk reductions

Publication Date: 2024.04.18 DELL PROD LP

AI summary

A system can determine a first output from an explainable artificial intelligence risk model based on a first input, wherein the first input indicates a first computing configuration, and wherein the first output indicates a first predicted maintenance cost of the first computing configuration during a time period. The system can determine a second output from the explainable artificial intelligence risk model based on a second input, wherein the second input indicates a second computing configuration that differs from the first computing configuration, and wherein the second output indicates a second predicted maintenance cost of the second computing configuration during the time period. The system can, in response to determining that the second predicted maintenance cost is less than the first predicted maintenance cost, saving an indication of a difference between the second predicted maintenance cost and the first predicted maintenance cost.