<- References Go to ToC AI Modules ->

1        Functions 2        Reference Model 3        CAV Input/Output Data
4       Functions of AI Workflows 5        I/O Data of AI Workflows 6        AIWs and JSON Metadata
7.      Reference Software 8.       Conformance Testing 9.       Performance Assessment

1       Functions

CUI-CPP responds to queries about the future performance of a company in terms of the following predictions:

  1. Default of the company.
  2. Interruption of the business Continuity.
  3. Impact of the governance.

This information is supplemented by data about the importance of the various Statement provided as input, i.e., the weighted impact of each element of the Governance, Financial and Risk Data on the above-defined predictions.

Risks are subdivided into Primary, i.e., Risks for which an AIM is available and Secondary, i.e., Risks for which an AIM is not available. The impact of the latter is evaluated by a sensitivity analysis.

2       Reference Architecture

Technical Specification: Compression and Understanding of Industrial Data (MPAI-CUI) – Company Performance Prediction (CUI-CPP) V2.0 assumes that workflows are based on Technical Specification: AI Framework (MPAI-AIF) V2.1 specifying the standard AI Framework (AIF) that enables initialisation, dynamic configuration, execution, and control of AI Workflows (AIW) composed of interconnected AI Modules (AIM).

The CUI-CPP V2.0 AI-Workflow supersedes those specified by previous MPAI-CUI specifications. These can still be used if their version is explicitly indicated.

Figure 1 – Company Performance Prediction V2.0 Reference Model

3       I/O Data

Table 2 gives the input/output data of the CUI-CPP V2.0 AIW.

Table 1 – I/O data of CUI-CPP V2.0 AIW

Input data From Description
Prediction Horizon CUI-CPP user Prediction time in months.
Primary Risk Statements External source Statements by the Company being assessed about the Risks for which compliant Machine Learning Modules are available in the CUI-CAP.
Governance Statements Company Statements by the Company being assessed about Company governance.
Financial Statements Company Statements by the Company being assessed about Company financial data.
Secondary Risk Statements Company Statements by the Company being assessed about the Company-perceived first level Risks of the Risk Taxonomy.
Output data To Description
Organisation Descriptors User or App A number and a vector of the most relevant elements of the Governance Statements affecting the assessment.
Primary Default Descriptors User or App The Primary Default Probability and a vector of the most relevant elements affecting the Primary Default Probability.
Primary Discontinuity Descriptors User or App A number and a vector of the most relevant elements affecting the Primary Discontinuity Probability.
Secondary Risk Probability User or App A number representing the probability the company is affected by a business discontinuity.

4     Functions of AI Modules

Table 2 gives the functions of all CUI-CPP V2.0 AIMs. Each link provides the AIM function, reference model, Input/Output Data, and JSON metadata.

Table 2 – Functions of CUI-CPP V2.0 AIMs

AIMs Function
Governance Assessment Processes Governance Statements and Financial Statements.
Provide Governance Descriptors to Company Assessment and Prediction AIM.
Financial Assessment Processes Financial Statements.
Provides Financial Descriptors to Company Assessment and Prediction AIM.
Risk Matrix Generation Processes Secondary Risk Statements.
Provide the Secondary Risk Matrix.
Company Assessment and Prediction Processes Prediction Horizon, Primary Risk Statements, Governance Descriptors, and Financial Descriptors.
Provide Organisation Descriptors, Primary Default Descriptors, and Primary Discontinuity Descriptors.
Prediction Result Perturbation Processes Governance Descriptors, Financial Descriptors, Primary Default Descriptors, Secondary Risk Matrix, and Prediction Horizon.
Produces Secondary Business Discontinuity Probability by perturbing the Governance Descriptors and Financial Descriptors.

5   I/O Data of AI Modules

Table 3 provides the link to the specified AIMs.

Table 3 – I/O Data of CUI-CPP V2.0 AIMs

Acronym Input Output
CUI-CAP Prediction Horizon
Primary Risk Statement
Governance Descriptors
Financial Descriptors		 Organisation Descriptors
Primary Default Descriptors
Primary Discontinuity Descriptors
CUI-FNA Financial Statements  Financial Descriptors
CUI-GVA Governance Statements
Financial Statements		 Governance Descriptors
CUI-PRP Primary Default Descriptors
Secondary Risk Matrix		 Primary Discontinuity Probability
CUI-RMG Secondary Risk Statements Secondary Risk Matrix

6    AIWs and JSON Metadata

Table 4 provides the links to the AIW and AIW specifications and to the JSON Metadata.

Table 4 – AIWs and JSON Metadata

AIW  AIMs Name JSON
CUI-CPP Company Performance Prediction X
CUI-CAP Company Assessment and Prediction X
CUI-FNA Financial Assessment X
CUI-GVA Governance Assessment X
CUI-PRP Prediction Result Perturbation X
CUI-RMG Risk Matrix Generation X

7    Reference Software

As a rule, MPAI provides Reference Software implementing the Technical Specification released with the BSD-3-Clause licence and the following disclaimers:

  1. The purpose of the Reference Software is to demonstrate a working Implementation of an AIW, not to provide a ready-to-use product.
  2. MPAI disclaims the suitability of the Software for any other purposes that those of the MPAI-HMC Standard and does not guarantee that it is secure.
  3. Users shall verify that they have the right to use any third-party software required by the Reference Software Implementation.
  4. Users should note that the Reference Software Implementation may require the acceptance of licences from third-party repositories.

8    Conformance Testing

An implementation of an AI Workflow conforms with MPAI-HMC if it accepts as input and produces as output Data and/or Data Objects (Data and its Qualifier) conforming with those specified or referenced by MPAI-HMC.

The Conformance of an instance of a Data is to be expressed by a sentence like “Data validates against the Data Type Schema”. This means that:

  • Any Data Sub-Type is as indicated in the Qualifier.
  • The Data Format is indicated by the Qualifier.
  • Any File and/or Stream have the Formats indicated by the Qualifier.
  • Any Attribute of the Data is of the type or validates against the Schema specified in the Qualifier.

9    Performance Assessment

Performance is a multidimensional entity because it can have various connotations. Therefore, the Performance Assessment Specification provides methods to measure how well an AIW performs its function, using a metric that depends on the nature of the function, such as:

  1. Quality: the Performance of a Communicating Entities in Context AIW can measure how well the AIW responds to a question.
  2. Bias: Performance of a Communicating Entities in Context AIW can measure the quality of responses in dependence of the type of message received.
  3. Legal compliance: the Performance of an AIW can measure the compliance of the AIW to a regulation, e.g., the European AI Act.
  4. Ethical compliance: the Performance Assessment of an AIW can measure the compliance of an AIW to a target ethical standard.

<- References Go to ToC AI Modules ->