WP1 Towards a European financial data space

Objectives

The WP will work towards a European financial data space.

O 1.1. To answer the main research questions on solving data quality and availability hurdles outlined in the IRPs
O 1.2. To demonstrate the novel data quality and augmentation methodologies through industry use cases (SWE, INT, RAI, CAR)
O 1.3. To disseminate the knowledge, validated by an international research centre (FRA, ECB, ARC)

WP 1 is led by BBU and supported by all partners. The work is divided into the following tasks:

Task 1.1. Technical coordination. Monitoring the related IRPs, store the output generated in a location accessible to the entire network.
Task 1.2. Support the research training for all assigned ESRs and contribute to advanced training content.
Task 1.3. Propose novel methodologies for detecting anomalies and dependence structures in high dimensional, high frequency data.
Task 1.4. Develop methods to streamline data collection, resolve data quality issues and structure it to support downstream processes.
Task 1.5. Industry Prototype: Develop solutions that rely on attention networks to incorporate text and temporal dependencies.
Task 1.6. Disseminate, communicate and exploit the results (Conferences, OS Day, policy paper, prototype, use case,).
Task 1.7. Jointly with the other research WPs, ensure that 10 new data-driven models can be built for prototypes for the industry

The WP will work on enabling the use of complex AI models in real-world financial settings.

O 2.1. To answer the main research questions on solving AI deployment hurdles for industry outlined in the IRPs.
O 2.2. To demonstrate the novel dynamic, rating models, automated trading platforms and market environments for RL (CAR, ROY).
O 2.3. To disseminate the knowledge validated by an international research centre (FRA, ECB, ARC)

WP 2 is led by WWU and supported by all partners. The work is divided into the following tasks:

Task 2.1. Technical coordination. Monitoring the related IRPs, store the output generated in a location accessible to the entire network.
Task 2.2. Support the research training for all assigned ESRs and contribute to advanced training content
Task 2.3. Industry Prototype: Propose an accurate, robust, composite, machine learning (ML)-based, dynamic rating model for SMEs.
Task 2.4. Develop a prototype: platforms for trading with improved the explainability of the AI/ML models and ESG/CSR indicators.
Task 2.5. Address the main practical challenges of applying RL in real-world financial settings and building open access use cases.
Task 2.6. Disseminate, communicate and exploit the results (Conferences, OS Day, policy paper, two prototypes, use case, media coverage)