● To develop blended approaches to evaluate innovative financial services and their providers, especially in the FinTech domain, building on Machine Learning methods, focussing on prediction (early warning) of operational fragility, fraudulent and illegal behaviour ranging from appropriation of loaned funds to money laundering activities. ● The development of conceptual and methodological tools for establishing when black-box models are admissible and, to the extent possible, making them more transparent and/or replacing them with interpretable and explainable models. ● To receive input from regulators and practitioners' communities and to validate results with regard to increasing transparency of artificial intelligence applications. ● Pruning and improvement of the vast array of performance attribution models by contributing to the development of methodologies for reducing the false discovery rate in financial research and applied financial investment management. ● Disseminate to the public and share with regulators the results on investment product performance evaluation. ● Creation of the first European platform comparing the out-of-sample performance of banks' investment products, insurance-linked investment products and asset management products available to the general public.

● Create an excellent network of researchers in Europe with lasting collaboration beyond the lifetime of the Action. ● Bringing technological, quantitative and economic researchers together, to tackle future research that can only be done in an interdisciplinary setting, and getting actively involved in the blockchain and FinTech communities across Europe, to constantly monitor developments, get input and disseminate results. ● Bridging the gap between practitioners from the finance industry, academics and regulators by setting up a common knowledge exchange platform. ● Transfer knowledge in terms of expertise, scientific tools and human resources across the different disciplines and between academia and industry. ● Establish an inclusive community of researchers on methodological and technological themes in Machine Learning and Artificial Intelligence, to promote Early Career Investigators and increase their visibility. ● Overcome the siloing of research topics by country and achieve geographical and demographical diversity, with special attention to COST Inclusiveness Target countries. ● Prepare competitive European researchers for a fruitful career in an international environment through intensive use of Short Term Scientific Missions (STSM) and joint educational programs with industrial partners. ● Maximize the job opportunities for PhD students and Early Career Investigators. ● Disseminate the results of the Action's activities to the scientific community, European institutions and to the general public. ● Significantly improve the gender equality in the fields of the Action.

Leader: Objectives: Pruning and improvement of the vast array of performance attribution models by contributing to the development of methodologies for reducing the false discovery rate in financial research and applied financial investment management (long-term scientific impact) Creation of the first European platform comparing the out-of-sample performance of banks' investment products, insurance-linked investment products and asset management products available to the general public (industry impact). Disseminate to the public and share with regulators the results on investment product performance evaluation. Tasks: Identify risk factors for ex-ante performance analysis (back-testing) and ex-post performance evaluation/attribution Create a database with data on the composition, underlying assets and relevant risk factors of investment products Develop and implement methodologies for ex-ante performance analysis (back-testing) and expost performance evaluation/attribution Set up the dialogue with regulators (through conferences, workshops and research collaboration) and citizen science organizations (through a forum and social media, including Linked-in and Twitter) to discuss the research results and gain feedback and further input Disseminate (including to investors) expertise on client-focused investment performance analysis through a dedicated website with resources for both advanced and less advanced users, including a handbook or wiki page describing the approaches for analysing the performance of investment products

Leaders: Objectives: To develop blended approaches to evaluate innovative financial services and their providers, especially in the FinTech domain (primarily but not exclusively ICOs, P2P lending platforms and crowdfunding initiatives), building on machine learning methods for preemptive risk analysis and rating. The focus will be on prediction (early warning) of operational fragility, fraudulent and illegal behaviour ranging from appropriation of loaned funds (including through Ponzi-type schemes) to money-laundering activities. Pursuit of this objective will be assisted by compiling dedicated structured databases to support the large-scale application of the above-mentioned methods. The long-term goal is to improve the quality and transparency of FinTech and of the digital assets space especially in Europe, to facilitate their growth in the interest of European investors and of the European economy more widely. Tasks: Review and extend/develop blended AI-aided models and methods to evaluate and rate innovative financial services and their providers, especially in the FinTech domain Compile appropriate databases to evaluate and implement the above criteria and methods Find solutions to data management and storage needs Interact with stakeholder to raise awareness of the research questions and discuss solutions Create a handbook or wiki page describing approaches to address transparency needs in FinTech by implementing/using insight from the research Monitor and analyse developments in the FinTech domain

Leader: Objectives: The development of conceptual and methodological tools for establishing when black-box models are admissible and, to the extent possible, making them more transparent and/or replacing them with interpretable and explainable models. This will require (i) the classification of algorithms from a range of disciplinary domains (especially ML, Econometrics) according to the predictability of the variables being modelled/forecast, (ii) the identification of methods for mapping results of black-box models to explainable and interpretable ones, at least ex-post, (iii) a better understanding of the conceptual and empirical nexus between identification of causality within models and the interpretability/explainability of the models. To receive input from regulators and practitioners' communities and to validate results with regard to increasing transparency of artificial intelligence applications. Tasks: Review the existing literature on AI (including machine learning) approaches as they are used in the finance industry and identify the most important applications Develop prototypes to demonstrate quantitative methods to improve transparency (including explainability and interpretability) of the "black-box" models or to provide alternatives Interact with stakeholders, in particular regulators, to raise awareness of the research questions and discuss potential solutions Develop a roadmap for including the results in European regulation and policies, in cooperation with regulators Publish policy papers to suggest new regulation Development of a handbook or wiki page describing the prototypes above