WP3_eXplainable_and_Fair_AI

• Lead Beneficiary: Bern Business School.
• Researchers involved: See link
• Bern Business School (Lead): Adam Kurpisz, Branka Hadji Misheva, Christian Hopp
• University of Naples Federico II: Francesco Palumbo, Alfonso Iodice D'Enza, Maria Iannario, Antonio Pescapè
• Active period: From M4 to M48.
• Activity type: Research.
• Early Stage Researchers involved: 1, 9, 16 & 17.

Objectives

The WP will work towards a unifying framework of explainability for AI models applied to financial use cases. 3.1. To answer the main research questions on solving explainability deployment hurdles for financial applications. 3.2. To demonstrate the proposed framework for audience-dependent explanations, through use cases (SWE, INT, ROY). 3.3. To disseminate the knowledge, validated by an international research centre (FRA, ECB, ARC)

Description

WP 3 is led by BFH and supported by all partners. The work is divided into the following tasks:

• Task 3.1. Technical coordination. Monitoring the related IRPs, store the output generated in a location accessible to the entire network.
• Task 3.2. Support the research training for all assigned ESRs and contribute to advanced training content
• Task 3.3. To provide global and local post hoc explainability techniques that address the explainability needs of different stakeholders.
• Task 3.4. To propose explainability functions, tailored for financial time series, preserving the non-stationary dependence structure.
• Task 3.5. Develop new portfolio optimization models that address challenges of incorporating fairness considerations into investments.
• Task 3.6. Disseminate, communicate and exploit the results (Conferences, OS Day, policy paper, two prototypes, use case, media coverage)

Deliverables

• D.3.1 Documentation of explainable AI methods: Documentation of test setups for applying explainable AI methods (Due in M48)
• D.3.2 Technical report on trustworthy AI methods: Technical report showing the achievements on trustworthy and fair AI models (Due in M48) D.3.3 Summary report on time-series explainability: Summary report on all results and impacts related to explainability for time-series (Due in M24)