⚙ Implementation

10 sections from the Description of Action (Part B)

3.1. Quality and effectiveness of the work plan, assessment of risks and appropriateness of the effort ........... 29

assigned to work packages ................................................................................................................................. 29

3.1. Quality and effectiveness of the work plan, assessment of risks and appropriateness of the effort

assigned to work packages

3.1.1. Work Packages (WP) List

Table 3.1.a: Work Packages (WP) List

WP Lead Lead Start End Researcher

No. WP Title Benefi Beneficiary Month month Activity Type involvement

ciary Name

WP 1 Towards a European financial data space 2 BBU M4 M48 Research DC 6, 8, 13, 15

WP 2 Artificial intelligence for financial markets 7 WWU M4 M48 Research DC 12, 14

WP 3 Towards explainable and fair AI-generated 14 BFH M4 M48 Research DC 1, 9, 16, 17

decisions

WP 4 Driving digital innovations with 3 ASE M4 M48 Research DC 3, 5, 7

Blockchain applications

WP 5 Sustainability of Digital Finance 4 UNA M4 M48 Research DC 2, 4, 10, 11

WP 6 Doctoral Training 1 UTW M1 M48 Training DC 1 - 17

WP 7 Dissemination, Outreach and Exploitation 6 BFH M1 M48 Dissemination DC 1 - 17

WP 8 Project Management 1 UTW M1 M48 Management DC 1 - 17

WP 9 Ethics Requirements 1 UTW M1 M48 Ethics DC 1 - 17

3.1.2. Recruitment Table per beneficiary

Table 3.1.b: Recruitment Table per Beneficiary

Researcher No. Recruiting Participant P hD awarding entities Planned Start Month Duration (months)

DC 1 UTW University of Twente M9 36

DC 2 UTW University of Twente M9 36

DC 3 UTW University of Twente M9 36

DC 4 UTW University of Twente M9 36

DC 5 WWU WU Vienna M9 36

DC 6 WWU WU Vienna M9 36

DC 7 POZ Poznań University of Economics and Business M9 36

DC 8 ASE Bucharest University of Economic Studies M9 36

DC 9 UNA University of Naples M9 36

DC 10 UNA University of Naples M9 36

DC 11 KUT Kaunas University of Technology M9 36

DC 12 ASE Bucharest University of Economic Studies M9 36

29

Project: 101119635 — DIGITAL — HORIZON-MSCA-DN-2022

DC 13 BBU Babes-Bolyai University M9 36

DC 14 CAR University of Kaiserslautern-Landau M9 36

DC 15 CAR WU Vienna M9 36

DC 16 BFH53, 54 University of Twente M9 36

DC 17 BFH53, 54 University of Twente M9 36

Total 540 + 72

Individual Research Projects, including secondment plan

Table 3.1.c Individual Research Projects

Fellow Host institution PhD enrolment Start date Duration Deliverables

DC 1 UTW UTW Month 9 36 months D 2.1, 2.2

Strengthening European financial service providers through applicable reinforcement learning (WP 3)

Objectives: Reinforcement Learning (RL) has become popular for automating uncertain decision-making in complex environments. Deep

reinforcement learning can make impressive algorithmic decisions in closed environments, but real-world applications in open

environments are harder. This project examines how RL can advance digital finance.

Expected Results: The project will address several RL implementation issues in digital finance. Utility-based RL deliverables will improve

financial decision-making by developing multi-criteria analysis, extreme scenarios, and risk management methods. RL in decision-support

will be optimised for explainability, regulatory compliance, model abstractions, and human judgement. We will also examine technological

challenges like Digital Twin environments, machine learning pipelines, and digital finance ecosystem integration.

Planned secondments: Cardo AI, Altin Kadareja (CEO), M2755, 6 months, applied research on Fintech innovations with Deep learning

ECB, Lukasz Kubicki, M33, 12 months, exposure to globally leading central bank, research training on EU principles, supervision

Fellow Host institution PhD enrolment Start date Duration Deliverables

DC 2 UTW UTW Month 9 36 months D 5.1, 5.2

Modelling green credit scores for a network of retail and business clients (WP 5)

Objectives: Some markets use green credit scores to assess SME credit risk in sustainable and circular economies. Simultaneously, network

customers' default likelihood has been studied. This study develops and deploys green credit score models that account for customers'

networks. We show the impact and give financial institutions methods to improve credit risk assessment and access.

Expected Results: Green credit score models will be developed and implemented. These models inform SMEs about their carbon footprint,

their main risks in a low-carbon economy, and how to mitigate them. SMEs leading on sustainability could gain easier access to capital by

demonstrating positive relationships between creditworthiness and sustainability, creating a fairer credit risk assessment that explicitly

factors in sustainability metrics and encouraging low-carbon measures.

Planned secondments: Swedbank, Prof. Dr. Tadas Gudaitis, M21, 6 months, ESG and credit score modelling

BIS, Rafael Schmidt, M27, 18 months, contribute macro-economic datasets, ongoing projects as well as overall expertise in banking

supervision

Fellow Host institution PhD enrolment Start date Duration Deliverables

DC 3 UTW UTW Month 9 36 months D 4.2 - 4.3

Machine learning in digital finance (WP 4)

Objectives: The project aims to design and enhance the functionality and user interaction of applications that model Early Warning Signals.

It will develop models and frameworks that leverage big data analytics, focusing on refining usability to improve clarity for various

stakeholders. This project also seeks to implement and evaluate explainability methods to determine their impact on the decision-making

processes of internal customers within financial institutions. The goal is to enhance their ability to provide accurate feedback and reporting

and to facilitate implementing necessary corrections.

Expected Results: The project will develop and integrate advanced explainability features into various Early Warning Signal (EWS)

applications, aiming to make analytical results and sentiment assessments more intuitive and actionable for users. Specifically, the project

expects to (i) Enhance user understanding and interaction with big data outputs, promoting broader and more effective use across different

business areas within financial institutions and regulatory bodies. This will involve improvements to make sentiment analysis results more

transparent, enabling supervisors to more effectively assess and verify these insights; (ii) Enables te assessment of the impact of these

enhancements on the decision-making processes of internal stakeholders, with the goal of establishing a feedback loop that encourages

continuous improvement of the platforms.

53 This candidate will be fully financed by the Swiss State Secretariat for Education, Research and Innovation (SERI). The SERI will apply the same rules as the European

Commission, based on the MSCA Work Programme 2021 - 2022, incl. recruiting, mobility and funding rules.

54 The University of Twente will be the formal degree awarding institute for the two DCs from BFH.

55 All months are in absolute terms since start of the project.

30

Project: 101119635 — DIGITAL — HORIZON-MSCA-DN-2022

Planned secondments: ECB, Lukasz Kubicki, M21, 12 months, exposure to globally leading central bank, research training on EU

principles, supervision

Fraunhofer, Prof. Dr. Ralf Korn, M33, 6 months, applied industry-research, contribute to multiple projects on blockchain and decentralized

finance

Swedbank, Prof. Dr. Tadas Gudaitis, M39, 6 months, ESG and credit score modelling

Fellow Host institution PhD enrolment Start date Duration Deliverables

DC 4 UTW UTW Month 9 36 months D 5.1

A recommender system to re-orient investments towards more sustainable technologies and businesses (WP 5)

Objectives: Recommender systems are well-known information filtering systems that suggest items most relevant to a user. To our

knowledge, there are none that suggest investments in sustainable technologies and businesses. This project will develop and deploy a

recommender system to help financial institutions and their clients invest in sustainable technologies.

Expected Results: The project informs user groups about investment sustainability. Sustainability KPI mapping and evaluation are project

deliverables. The recommender system's explainability is crucial. Thus, the recommendations will be tailored to multiple user classes with

appropriate explanations and interpretations. The system recommends sustainable investments, monitors portfolio performance, and

dynamically updates financial and sustainable KPIs.

Planned secondments: BIS, Rafael Schmidt, M21, 18 months, contribute macro-economic datasets, ongoing projects as well as overall

expertise in banking supervision

ARC, Prof. Dr. Ioannis Emiris, M39, 6 months, applied industry-research, work on the technological aspects of recommender systems

Fellow Host institution PhD enrolment Start date Duration Deliverables

DC 5 WWU WWU Month 9 36 months D 4.2 - 4.3

Fraud detection in financial networks (WP 4)

Objectives: Detecting fraud is currently one of the most important topics in Finance. However, it is also one of the most complex, given

that fraudsters typically represent and generate a highly dynamic system, requiring that the boundaries and objectives of any system

designed to detect and reduce fraud be constantly adapted to new extrinsic structures. This enables the definition of not only a static fraud

detection system, but also a dynamic AI learning system, particularly in relation to network analysis.

Expected Results: On a meta-level, a set of Machine Learning and Artificial Intelligence models will be defined to enable a research-based

approach that can be applied directly in financial institutions. The models are defined in such a way that the outcomes of the learning process

within the institutions can be used to define and design new algorithms from a scientific standpoint. The work on network algorithms during

the process of designing Machine Learning environments, will result in the publication of seminal papers.

Planned secondments: RAIFFEISEN, Dr. Stefan Theußl, M27, 18 months, the research exposure in a global business environment will

account for practical considerations when proposing the use of innovative methods for fraud detection

Fellow Host institution PhD enrolment Start date Duration Deliverables

DC 6 WWU WWU Month 9 36 months D 1.1 - 1.3

Collaborative learning across data silos (WP 1)

Objectives: Connecting several dozen different data pipeline components and integrating an excessive number of APIs to leverage siloed

data is a significant barrier to the comprehensive implementation of AI-based systems in finance. Currently, very little research is devoted

to addressing all of the challenges associated with training, testing, and deploying cutting-edge ML and DL methods while leveraging siloed

data. We will concentrate on the data challenges that finance service providers face by proposing solutions to streamline data collection,

resolve data quality issues, and structure data to support downstream processes.

Expected Results: APIs for integrating Machine Learning and Deep Learning algorithms into FinTech processes necessitate careful

abstraction of the specified input and output, which is the responsibility of the researchers to simplify and aggregate the complexity. This

project produced a large number of API definitions that are closely related to research papers in the fields of theory of Artificial Intelligence

and Machine Learning, as well as theory of Finance applications in various sub-fields such as security and compliance. The API

specification itself should not only be integrated into financial institutions' business processes, but should also provide fruitful input for new

research papers that are of interest to readers and users of all involved fields of research.

Planned secondments: Swedbank, Prof. Dr. Tadas Gudaitis, M23, 18 months, research on prototype implementations, applied research

Fraunhofer, Prof. Dr. Ralf Korn, M41, 4 months, applied industry-research, implement various use-cases

Fellow Host institution PhD enrolment Start date Duration Deliverables

DC 7 POZ POZ Month 9 36 months D 4.1

Risk index for cryptos (WP 4)

Objectives: The cryptocurrency market is exceptional: it is volatile, with a constantly shifting market structure. As cryptocurrencies evolve

into a class of investable assets, the need for an index product arises. We investigate the dependencies of tail risk events within

cryptocurrencies, which entails identifying coins with high or low joint tail event risks. Based on this, we intend to develop a risk index for

cryptocurrencies to measure joint tail events, which will be an important tool for communicating risks to the public and regulators.

31

Project: 101119635 — DIGITAL — HORIZON-MSCA-DN-2022

Expected Results: Develop a risk index to understand, measure and forecast upcoming risk flows from all cryptocurrency market

participants and risk drivers. The possibility of pinpointing co-tress components in a dynamic network context makes the tool versatile and

flexible for Digital Finance. The index will provide a thorough understanding of cryptocurrencies, and measure the dependencies and

spillover effects in tail risk events within cryptocurrencies. It helps investors to manage risks and support decision-making.

Planned secondments: Royalton, Dr. Michael Althof, M27, 18 months, research in innovation-driven business, use-case implementation

Fellow Host institution PhD enrolment Start date Duration Deliverables

DC 8 ASE ASE Month 9 36 months D 4.2

Detecting anomalies and dependence structures in high dimensional, high frequency financial data (WP 1)

Objectives: Herding, a well-known financial anomaly, is thought to cause high volatility, volatile prices, and low liquidity (Bikhchandani

and Sharma, 2000). Greed and herd behaviour caused the seventeenth-century tulip mania, the 1995–2000 Internet bubble, and the 2015

Chinese stock market crash. This project studies high-dimensional sentiment networks and herd behaviour on the stock market. To better

fit investor sentiment, the project will calibrate the option pricing model, Stochastic Volatility and Correlated Jump (SVCJ).

Expected Results: The project will detect anomalies like herd behaviour and dependence structures in high-dimensional, high-frequency

financial data. We plan to create a tail event-driven network that graphs or matrices the interconnections of a large panel to understand

sentiment network mechanics. That will inform our herd behaviour detection and option pricing model calibration. 1) Publications in

prestigious journals available via public repositories, 2) Presentations at prestigious conferences, and 3) Knowledge exchange

Planned secondments: DeutscheBank, Roman Timofeev, M27, 6 months, contribute datasets, expertise on applications of AI and anomaly

detection and early warning systems, as well as expertise on predictive analytics, semantic analysis and risk management.

Royalton, Dr. Michael Althof, M33, 12 months, for training in portfolio optimization of ETFs ,

Fellow Host institution PhD enrolment Start date Duration Deliverables

DC 9 UNA UNA Month 9 36 months D 3.1 - 3.2

Audience-dependent explanations (WP 3)

Objectives: To address the issue of explainability in complex models, the literature has proposed an ever-expanding list of post-hoc

explainability methods that can be used to gain some understanding of the inner workings of complex models. However, explaining the

inner workings of algorithms and their interpretation is entirely dependent on the target audience. The existing literature fails to match the

growing number of explainable AI (XAI) methods with the varying explainability requirements of stakeholders. To promote the widespread

adoption of AI-based systems in finance, additional research is required to map the requirements of explainable systems across the various

stakeholders in the finance industry.

Expected Results: Finance decision-makers and AI model builders don't understand XAI's capabilities or ESG's impact on society and

economy. This project promotes dialogue and knowledge transfer between those camps. It facilitates AI, Sustainable Finance, and ESG

Technology innovation and collaboration. The following channels will disseminate expected results: 1) technical reviews, newspapers, and

magazines, 2) public events (workshops for results presentation), and 3) knowledge exchange with stakeholders and project partners.

Planned secondments: Swedbank, Prof. Dr. Tadas Gudaitis, M21, 18 months, policies for asset, sustainable fund management

Fraunhofer, Prof. Dr. Ralf Korn, M39, 6 months, improve know-how transfer by using and implementing advanced financial models

Fellow Host institution PhD enrolment Start date Duration Deliverables

DC 10 UNA UNA Month 9 36 months D 5.2 - 5.3

Experimenting with Green AI to reduce processing time and contributes to creating a low-carbon economy (WP 5)

Objectives: Green AI supports the use of resources more efficiently and conserves them for future generations. Multiple applications have

been presented in different areas, however, there are no studies exploring the impact that the use of green AI concepts can have in the

Financial industry. This research objective focuses on experimenting with green AI concepts in multiple applications in finance, analysing

economical and practical impact of its deployment in industry. It facilitates the exchange of innovative ideas and cooperation opportunities

in the field of Environmental, Social, and Governance (ESG), Sustainable Finance, and ESG Technology.

Expected Results: The project aims at providing reports about pricing and risk management of green financial instruments across all asset

classes, with a focus on new products development, model validation, model risk management, funding and counterparty risk, fair and

prudent valuation, applications. It aims at focusing on financial inclusion and inequality. The WP will also have a strong focus on discussion

and disseminating of the main results with the aim of spreading the culture of green AI and creating a table for the discussion of new

proposals and rules. 1) publications in open access journals, 2) presentations at prestigious conferences and 3) knowledge exchange with

stakeholders and project partners 4) General outreach (Media, Open Science Day).

Planned secondments:Swedbank, Prof. Dr. Tadas Gudaitis, M21, 18 months, policies for asset, sustainable fund management

ARC, Prof. Dr. Ioannis Emiris, M39, 6 months, applied industry-research, using large-scale computing infrastructure to implement the

theory

Fellow Host institution PhD enrolment Start date Duration Deliverables

DC 11 KUT KUT Month 9 36 months D 5.3

Applications of Agent-based Models (ABM) to analyse finance growth in a sustainable manner over a long-term period (WP 5)

32

Project: 101119635 — DIGITAL — HORIZON-MSCA-DN-2022

Objectives: Agent-based systems are computer models that simulate the behaviours and interactions of autonomous agents, either as

individuals or in groups, in order to gain a deeper understanding of how a system behaves and what factors influence its outcomes. In

agentbased modelling, a system is represented as a collection of autonomous decision-making units, or agents (ABM). Each agent evaluates

its own situation and makes decisions according to a set of rules. Agents are capable of a variety of appropriate behaviours for the system

they represent. ABM has been utilised in numerous financial investigations. The literature contains few ABM studies that model economies

and markets while assuming the industry's adoption of sustainable finance.

Expected Results: This study aims to use agent-based models to simulate different market scenarios in which industry agents take

sustainable actions. Long-term financial growth will be analysed, and the findings will aid in the development and modification of industry

policies and strategies. A public repository containing a library of the developed agent-based models is another anticipated outcome. The

WP will place a strong emphasis on disseminating and the anticipated outcomes. Several channels, including peer-reviewed articles in

highimpact journals, research talks at national and international conferences, and use case presentations at industry workshops, will be

utilised to accomplish this objective.

Planned secondments:Royalton, Dr. Michael Althof, M21, 18 months, research on crypto assets for prototype and user acceptance ARC,

Prof. Dr. Ioannis Emiris, M39, 6 months, applied industry-research, using large-scale computing infrastructure to implement the theory

Fellow Host institution PhD enrolment Start date Duration Deliverables

DC 12 ASE ASE Month 9 36 months D 2.3

Developing industry-ready automated trading systems to conduct EcoFin analysis using deep learning algorithms (WP 2)

Objectives: This IRP will focus on addressing the challenges associated with automated trading systems in the direction of industry-ready

platforms, i.e. minimising the risks of mechanical failures, improving the explainability of the underlying AI/ML models used in automated

trading systems to better address performance-related issues, and also addressing ESG/CSR and ethical issues. This area will contribute

significantly to Green Finance, thereby addressing the European Green Deal.

Expected Results: The project's outcomes will provide financial institutions with new automated trading tools. The primary anticipated

outcome of the project is the design of new trading algorithm solutions for mitigating the risks of mechanical failures, enhancing the

explainability of the underlying AI/ML models used in automated trading systems to better address performance-related issues, as well as

ESG/CSR and ethical concerns. The anticipated results will be disseminated through the following channels: 1) Publications in prestigious

journals made widely accessible through public repositories; 2) Presentations at prestigious conferences; and 3) Knowledge exchange with

project partners.

Planned secondments: Royalton, Dr. Michael Althof, M21, 18 months, research on crypto assets for prototype and user acceptance

ARC, Prof. Dr. Ioannis Emiris, M39, 6 months, applied industry-research, use large-scale computing infrastructure for deep-learning

algorithms

Fellow Host institution PhD enrolment Start date Duration Deliverables

DC 13 BBU BBU Month 9 36 months D 1.1, 1.2

Predicting financial trends using text mining and NLP (WP 1)

Objectives: This DC's primary objective is to improve the use of AI-based natural language processing (NLP) solutions in order to predict

credit risk and fiscal fraudulent behaviour based on speech text from audit reports, social media, and other sources. Predicting

noncompliance based on free-text responses from survey respondents' perceptions. Constructing attitudinal indices based on free text and

incorporating them into behavioural models, along with other qualitative or quantitative factors, in order to predict the likelihood of system

fraud or the level of risk associated with accreditation.

Expected Results: Constructing large databases that provide both qualitative and quantitative data for use in the development of AI

algorithms for both public and private entities (prediction of tax fraud) (banks, FinTechs offering credit services, etc.). Using text mining

and NLP, evaluate the viability of various models that could predict the risk of fraudulent behaviour in the financial sector. Utilisation of

these models in both the public sector (public policy formulation) and the private sector (help banks and FinTechs in credit scoring).

Planned secondments: RAIFFEISEN, Dr. Stefan Theußl, M15, 18 months, research exposure in a global business environment, trend

modelling

ECB, Dr. Lukasz Kubicki, M33, 12 months, exposure to globally leading central bank, research training on EU principles, supervision

Fellow Host institution PhD enrolment Start date Duration Deliverables

DC 14 CAR UKL Month 9 36 months D 2.3

Challenges and opportunities for the uptaking of technological development by industry (WP 2)

Objectives: The building blocks of any institutional investor's loan portfolio are cash flows. Using public and proprietary data, the DC will

conduct research and develop a machine learning tool capable of performing grouped time series forecasting on a private debt portfolio

spanning multiple geographies, sectors, and whose features can also be grouped at other levels, such as loan amount and interest rate. In

our innovation-driven industry, we analyse the obstacles and opportunities associated with adopting technological advances.

Expected Results: The project's outcomes will contribute to the expanding body of knowledge concerning the applications of cutting-edge

machine learning and artificial intelligence techniques to traditional financial problems. Specifically, the first phase of the project will

concentrate on missing value imputation for loan payment time series, while the second phase will adopt a more general predictive approach,

that of grouped time series forecasting, possibly incorporating the first step. The anticipated outcome will be three research/conference

papers describing the data analysis, modelling approaches, and experimental results.

33

Project: 101119635 — DIGITAL — HORIZON-MSCA-DN-2022

Planned secondments: Kaiserslautern-Landau, Prof. Dr. Ralf Korn, M33, 12 months, contribution to the theoretical and applied

expertise in machine learning, times-series forecasting and credit portfolio analysis

Fellow Host institution PhD enrolment Start date Duration Deliverables

DC 15 CAR WWU Month 9 36 months D 1.1, 1.3

Deep Generation of Financial Time Series (WP 1)

Objectives: Macroeconomics factors such as central banks’ interest rates, inflation, unemployment rate, house price indices, to name a

few, are of foremost importance in Financial Markets. The aim of this project is to benchmark various methods from classical statistical

learning and modern machine learning, with a special emphasis on data augmentation, convolutional networks with attention

mechanisms, and transformers, in order to predict their point value in the future. As a second step the student will be using the above

predictions to forecast future market scenarios in a what-if fashion.

Expected Results: The project's outcomes will contribute to the expanding body of knowledge concerning the applications of cutting-edge

machine learning and artificial intelligence techniques to traditional financial problems. We will apply recent findings from the ML literature

on time series forecasting in the first step. In the second phase of the project, the DC will be able to conduct research in the field of causal

inference in finance, which also appears to be an extremely promising area of study. The anticipated outcome will be three

research/conference papers describing the data analysis, modelling approaches, and experimental results.

Planned secondments: WWU, Prof. Dr. Kurt Hornik, M27, 14months, theoretical modelling and mathematics for deep learning.

Fraunhofer, Prof. Dr. Ralf Korn, M41, 4 months, applied industry-research, implementing several use-cases,

Fellow Host institution PhD enrolment Start date Duration Deliverables

DC 16 BFH UTW Month 9 36 months D 3.1 - 3.3

Investigating the utility of classical XAI methods in financial time series (WP 3)

Objectives: The introduction of complex ML and DL methods for financial time series forecasts potentially enables higher predictive

accuracy but this comes at the cost of higher complexity and thus lower interpretability. For cross sectional data classical XAI approaches

can lead to valuable insights about the models’ inner workings, but these techniques generally cannot cope well with longitudinal data (time

series) in the presence of dependence structure and non-stationarity. The literature currently does not offer any XAI approach that is

specifically developed for financial time series. Further research is needed on developing explainability methods that can be applied to

complex models like deep learning methods (DL) which preserve and exploit the natural time ordering of the data.

Expected Results: Within this IRP, we will propose a set of novel explainability functions that are specifically tailored for financial time

series. We envision a framework for XAI in finance that addresses the shortcomings of existing methods. Namely, under existing,

perturbation-based XAI methods, if features are correlated, the artificial coalitions created will lie outside of the multivariate joint

distribution of the data. Furthermore, generating artificial data points through random replacement disregards the time sequence hence

producing unrealistic values for the feature of interest. In addition to the novel, finance-tailored methodology for obtaining explanations,

the project will also aim to produce industry-ready deployments of the novel XAI techniques developed.

Planned secondments: ECB, Dr. Lukaz Kubicki, M21, 12 months, exposure to globally leading central bank research, training on

EU principles.

Fraunhofer, Prof. Dr. Ralf Korn, M33, 6 months. Research needs to be validated with industry to achieve the envisioned impact,

BIS, Rafael Schmidt, M39, 6 months, contribute macro-economic datasets, ongoing projects as well as overall expertise in banking

supervision

Fellow Host institution PhD enrolment Start date Duration Deliverables

DC 17 BFH UTW Month 9 36 months D 3.2, 3.3

Fair Algorithmic Design and Portfolio Optimization under Sustainability Concerns (WP 3)

Objectives: The surge in interest in algorithmic fairness and sustainability is present in numerous fields of study, including finance

and portfolio management in particular. This project's objective is to create new portfolio optimization models that address some of

the difficulties associated with incorporating fairness and sustainability into investment management. The objective of the project is

to increase understanding of the source and methods for eliminating algorithmic bias in finance in order to generate sustainable

outcomes. The project will equip financial institutions with new sustainable and equitable algorithmic solutions to increase customer

trust.

Expected Results: The primary anticipated outcome of the project is the development of new algorithmic solutions for multiple areas

of finance, such as sustainable portfolio management. The project will equip financial institutions with new tools to comply with EU

sustainability regulations. The subsequent anticipated outcome is the publication of a library containing all of the designed algorithms

in a public repository. A significant emphasis will be placed on the dissemination of the anticipated results, which will be accomplished

through the following channels: at least one publication in prestigious open-access journals and at least three presentations at

prestigious conferences and open events. The final outcome of the project will be a comprehensive exchange of knowledge with

project partners.

Planned secondments: BIS,Rafael Schmidt, M15, 18 months, contribute macro-economic datasets, ongoing projects as well as

overall expertise in banking supervision

ECB, Dr. Lukazs Kubicki, M33, 12 months, exposure to gloabally leading central bank research, training ion EU principles

34

Project: 101119635 — DIGITAL — HORIZON-MSCA-DN-2022

3.1.3. Network Organization

Management structure. The management structure of DIGITAL consists of eight committees led by different

consortium members. This management structure, observing diversity rules,55 is depicted in Figure 3.1. and elaborated on

below.

Decision-making processes and conflict resolution. Decisions are made by simple majority within each committee.

The Supervisory Board is the ultimate decision-making body and is responsible for resolving conflicts.

Consortium Agreement. Before the start of the project, we will sign a consortium agreement. It will follow the

model consortium agreement from DESCA57. We will specify the relationship among the parties, in particular

concerning the organisation of the work between the parties, the management of the project and the rights and

obligations of the parties concerning inter alia liability, access rights and dispute resolution.

Financial management strategy. The project coordinator is responsible for coordinating the execution of both the

technical and financial aspects of the project. It ensures timely project completion by coordinating the technical work

of the various work packages. It coordinates and monitors the financial administration of the various partners, thereby

ensuring superior project efficacy.

The project coordinator will oversee how the financial resources allocated to each partner are utilised to ensure the

efficiency of the project and the continued production of high-quality deliverables. In this regard, University of

Twente will assign a financial manager to the project, who will collaborate with University of Twente's administrative

offices to ensure financial transparency and compliance. Specifically, the financial manager will consult in advance

with the technical manager to determine whether each partner respects the milestones and deliverables, and if so, in

what proportion, and will allocate the corresponding budget. The budget will be clearly tied to the program's delivery;

in particular, institutional costs for training and management will be allocated proportionally to each partner's and the

project coordinator's contribution to the work packages and doctoral training efforts. In addition, each recipient will

be responsible for establishing their own internal financial infrastructure and all necessary monitoring tools, as well

as other formal financial arrangements, such as expenditure tracking. The network coordinator is responsible for

overall control of the funds and any necessary rerouting of funds. Everyone in the network is additionally also

responsible for auditing their own financial matters.

Four year doctoral programmes. PhD studies at the University of Twente regularly take four years. The Department

High-Tech Business and Entrepreneurship has guaranteed to fully fund the fourth year of the PhD studies for all four

doctoral students. The University of Twente has also agreed to be the formal degree awarding institute for the two

DCs from BFH. In all cases, funding for the fourth year of the PhD studies is in line with the rules of the European

Commission, based on the MSCA Work Programme 2021 - 2022.

Internal communications strategy. DIGITAL will utilise a collaborative online environment that permits daily

discussions on all pertinent topics. In addition, monthly newsletters will be used to facilitate communication between

the various teams and all members of DIGITAL. There will be a specialised intranet website with an accessible

document repository for all members. Face-to-face meetings will happen at least weekly between supervisors and

DCs. In addition to formal meetings, we will hold regular, informal virtual meetings for the entire network.

Executive Board (EB). The Executive Board is composed of all WP leaders, one diversity coordinator and is led by

the project coordinator. Regular quarterly meetings will be strategically scheduled prior to the meetings of the SB to

facilitate the Board's decision-making process. The EU officer will be invited to all meetings, along with all members

from the Supervisory Board. The EB is responsible for the following: 1. Overall management of the training and

research program; 2. Monitoring of IRP progress; 3. Implementation of training activities with associated partners;

3.1.4. Progress monitoring and evaluation of individual research projects

Progress monitoring procedure. Each research partner has extensive experience monitoring and evaluating research

and training projects, having completed more than 50 IRPs successfully over the past few years, as well as running

large national and international research projects. Over the past two years, the coordinator has successfully chaired

the COST network CA19130 with over 240 researchers from 38 European countries. Partners have already agreed to

a unified and standard approach (Progress Monitoring Plan) with a focus on the quality and on-time delivery of

project deliverables and milestones. The Research and Training Committee (RTC), composed of two university

academic supervisors, two industrial partners representatives, and one representative from an associated partner,

oversees each IRP.

Evaluation of IRPs and DCs. IRPs will be evaluated using multiple criteria. Through regular peer-reviews,

presentation of the research to the academic community, and solicitation of feedback from industry partners, we seek

continuous monitoring and evaluations of our work. The Research Committee will conduct formal evaluations prior

to each milestone and deliverable, as well as quarterly. This will be supervised by the board of directors. The progress

and output of DCs will also undergo informal and formal evaluations. The initial Personal Career Development

Plan for each DC will be monitored on a monthly basis and revised every six months. Doctoral candidates and their

supervisors (academic and industrial) will meet once a week to review training, research, and all predetermined

milestones. In addition, all DCs are a part of larger research groups at their home universities where monitoring tools

for PhD projects and research projects, including the participation of institute directors and HR, are already in place.

The training's content, effectiveness, and impact will be evaluated both immediately after each event, via an

evaluation and satisfaction survey to be submitted by the DCs, and more formally every six months by the RTC and

the External Advisory Board (EAB) in accordance with European Commission guidelines.

Work package progress. The research WP leaders are required to report on the status and progress monthly to the

Research Committee and quarterly to the supervisory board.

37

Project: 101119635 — DIGITAL — HORIZON-MSCA-DN-2022

Conflict resolution. In the event of unsatisfactory progress, delays, or discrepancies in the deliverables and

milestones, strict measures will be implemented, ranging from specific recommendations to a comprehensive review

and adjustments, in accordance with the Conflict resolution and risk mitigation plan agreed upon by all project

partners at the outset. The supervisory board will oversee the implementation of the contingency plan.

External Advisory board. Every six months, an external advisory board composed of leading academics and senior

executives will review the progress of DIGITAL, both the training and research aspects, issue recommendations, and

possibly propose corrective measures.

Overall quality assurance. At its quarterly meetings, the supervisory board will evaluate progress based on the

reports of the IRP and WP members and decide on the implementation of all necessary measures. The supervisory

board is the deciding body for necessary measures, and an external opinion from the advisory board will be sought.

3.1.5. Implementation Risks

Continuous monitoring. Each year, during the annual review, all individual DIGITAL projects and training activities

are evaluated against the initial milestones and deliverables. The network coordinator, respective WP leaders, and

supervisors are responsible for the continuous monitoring of the progress of the deliverables and their evaluation,

as well as any additional risks identified during the project's duration. The milestones in Part A serve as formal

decision and review points to identify risks early on and to implement preventive measures. Changes to deliverables,

WPs, or PhD objectives are approved by the Executive Committee, presented to the SB, and proposed to the EU

officer in charge. There are identifiable managerial, scientific, and technical risks (see Part A) despite the solid plan

to monitor progress and ensure quality of both IRPs and doctoral training.

3.1.6. Supervisory board (including gender aspects in the decision making of the board)

Composition. The Supervisory Board (SB) is composed of one representative from each partner, all supervisors, all

WP leaders, and two doctoral candidates who rotate annually. The SB is co-chaired by the project coordinator and

the EU representative. It will elect one representative to serve as the SB's diversity coordinator.

Main activities and responsibilities. The SB will have a kick off meeting at the start of the network activity, with

quarterly consecutive meetings. The SB has the following responsibilities: decide on the strategic directions of the

network; monitor and evaluate the progress of all IRPs, as well as coordinate their technical and financial aspects;

monitor and approve all training, dissemination, and exploitation activities; establish strategic objectives for the

nonacademic sector's contribution to doctoral education; support and encourage the development of sustainable

doctoral programme elements among all partners; examine the improvement of career prospects for DCs and their

skill enhancement; closely monitor the milestones and deliverables for each project; ensure that the IP strategy is

implemented effectively; ensure that aspects of diversity are fully implemented; oversee the implementation of all

scientific procedures; monitor a technically robust deployment of artificial intelligence; implement appropriate risk

mitigation measures, once identified; take corrective action in the event of a breach of scientific integrity.

Gender-conscious decision making. In the composition and decision-making process of the SB, gender parity and

diversity56 considerations will be strictly taken into account. The coordinator for diversity will be asked to comment

on all decisions that are reviewed for gender and diversity-related consequences. Exactly 50% of our work package

leaders are female, as are 40% of the entire network.

3.1.7. Recruitment strategy (including gender aspects in the selection process)

Recruitment and selection process. All beneficiaries have endorsed and will adhere to the Code of Conduct for

the Recruitment of Researchers,57 demonstrating their commitment to act in a responsible and respectable manner

and to provide researchers with fair framework conditions, with the intention of contributing to the advancement of

the European Research area. All local HR departments will provide substantial support to the centralised

recruitment. The positions will be published on DIGITAL websites, at EURAXESS, newsletters, email-lists,

doctoral schools, student organisations, LinkedIn. The network will establish uniform recruitment guidelines at the

outset of the project. All of the candidates' experiences, including variations in the chronological order of their CVs

and mobility experiences, will be considered as selection criteria. The procedure uses initial video screening, followed

by face-to-face interviews by a sector-, gender and discipline-balanced committee.

Employment conditions. All beneficiaries have endorsed the European Charter and Code for researchers, thus

ensuring that researchers can enjoy the same rights and obligations in any European country. All recruiting institutions

56 https://rea.ec.europa.eu/news/tackling-gender-equality-research-and-innovation-2022-03-07_en

57 https://euraxess.ec.europa.eu/jobs/charter/code, https://euraxess.ec.europa.eu/jobs/charter

38

Project: 101119635 — DIGITAL — HORIZON-MSCA-DN-2022

have also agreed to observe the EU Directive on Fixed-Term Work.58 All DCs will receive regular employment

contracts, benefitting from all applicable social security benefits.

Gender-balanced recruitment. The selection committee will be balanced with respect to diversity aspects, taking

into account gender balance, diverse sector, regional and skills composition. Recruitment will in particular target

women-in-science groups, e.g. IEEE Women in Engineering and the European Platform of Women Scientists.59

3.1.8. Environmental aspects in light of the MSCA Green Charter

The MSCA Green Charter,60 which promotes the conduct of research and training activities in a sustainable way, has

been endorsed by each consortium member. This is congruent with the goals of the European Green Deal.61 Each

institution has also endorsed their own Green Charter, in line with official EU policies.