Prediction of Cashflow Timing and Patterns in International Bank Accounts
Can Artificial Intelligence help in predicting cash flow timing and patterns in international bank accounts? Our Laboratory has been working on answering this question in cooperation with the European Investment Bank, under the project Prediction of Cashflow Timing and Patterns in International Bank Accounts. The project was funded by the EIB institute as the first STAREBEI (STAges de REcherche BEI-EIB research internships) research grant with a Croatian university. As a part of this collaboration, a workshop on AI was organized for the EIB, as well as a working visit to the EIB offices, where the potential of the developed models was successfully demonstrated. For more details on the project, click here.
Reinforcement Learning Approaches to Optimal Market Making
A new paper authored by the member of the Laboratory has been published in the Mathematics journal:
B. Gašperov, S. Begušić, P. Posedel Šimović, and Z. Kostanjčar, “Reinforcement Learning Approaches to Optimal Market Making,” Mathematics, vol. 9, no. 21, p. 2689, Oct. 2021, doi: 10.3390/math9212689.
The paper brings a discussion of different reinforcement learning approaches to the problem of market making, with an introduction to both topics and a comprehensive literature review. The paper is available in open acces at the link: 10.3390/math9212689.
Special session on Advances in Machine Learning for Finance
The Laboratory for Financial and Risk Analytics is organizing a special session on Advances in Machine Learning for Finance within the International Symposium on Image and Signal Processing and Analysis 2021. The conference is organized under the technical co-sponsorship of the IEEE Signal Processing Society and the European Association for Signal Processing.
The goal of this special session is to bring together researchers from the disciplines of signal processing, machine learning, mathematics, and finance to facilitate diffusion of ideas and foster future research. Topics of interest include, but are not limited to:
Signal processing methods for financial time series,
Machine learning for financial risk modelling,
Deep learning and reinforcement learning for financial data,
Portfolio optimization algorithms and asset allocation,
Fintech innovation and blockchain-based assets.
The conference will take place in Zagreb, Croatia, September 13-15, 2021. See here more information on submission and the full Call for Papers.
Partnership with Know-Center for data-driven business and big data analytics
The Laboratory for Financial and Risk Analytics has committed to support the Know-Center proposal for the COMET (Competence Centers for Excellent Technologies) funding programme, with its scientific focus on data-driven AI. The Know-Center is a leading European research center for data-driven business and artificial intelligence, and LAFRA will join as Consortium Partner within the COMET programme for the funding period 2023-2026.
Products, digital innovations and technologies in insurance - INSURTECH
In cooperation with Croatia osiguranje a postgraduate specialist study programme “Products, digital innovations and technologies in insurance – INSURTECH" has recently been proposed and is being offered at the University of Zagreb, Faculty of Electrical Engineering and Computing. The head of the study programme is prof. Zvonko Kostanjčar, and the members of the Laboratory for Financial and Risk Analytics administer and hold courses within the programme.
The study programme is aimed at improving the understanding and usage of new technologies in insurance, while offering a comprehensive overview on the development of new insurance products. Fore more info, please see the programme website.
New project funded by the EIB: Prediction of Cashflow Timing and Patterns in International Bank Accounts
The European Investment Bank has funded a new project under the STAREBEI program with the Laboratory for Financial and Risk Analytics, under the title Prediction of Cashflow Timing and Patterns in International Bank Accounts.
The goal of this project is to develop a predictive model for cashflow timing and patterns in international bank accounts, based on machine learning approaches which can undertake the complexity and heterogeneity of the data and the underlying mechanisms. The planned project duration is 12 months, and it will include several researchers from the EIB and the Laboratory.