DeepVaR: a framework for portfolio risk assessment leveraging probabilistic deep neural networks.

Determining and minimizing risk exposure pose one of the biggest challenges in the financial industry as an environment with multiple factors that affect (non-)identified risks and the corresponding decisions. Various estimation metrics are utilized towards robust and efficient risk management frameworks, with the most prevalent among them being the Value at Risk (VaR). VaR is a valuable risk-assessment approach, which offers traders, investors, and financial institutions information regarding risk estimations and potential investment insights. VaR has been adopted by the financial industry for decades, but the generated predictions lack efficiency in times of economic turmoil such as the 2008 global financial crisis and the COVID-19 pandemic, which in turn affects the respective decisions. To address this challenge, a variety of well-established variations of VaR models are exploited by the financial community, including data-driven and data analytics models. In this context, this paper introduces a probabilistic deep learning approach, leveraging time-series forecasting techniques with high potential of monitoring the risk of a given portfolio in a quite efficient way. The proposed approach has been evaluated and compared to the most prominent methods of VaR calculation, yielding promising results for VaR 99% for forex-based portfolios. Supplementary Information: The online version contains supplementary material available at 10.1007/s42521-022-00050-0.

Deep learning enhancing banking services: a hybrid transaction classification and cash flow prediction approach.

Small Medium Enterprises (SMEs) are vital to the global economy and all societies. However, they face a complex and challenging environment, as in most sectors they are lagging behind in their digital transformation. Banks, retaining a variety of data of their SME customers to perform their main activities, could offer a solution by leveraging all available data to provide a Business Financial Management (BFM) toolkit to their customers, providing value added services on top of their core business. In this direction, this paper revolves around the development of a smart, highly personalized hybrid transaction categorization model, interconnected with a cash flow prediction model based on Recurrent Neural Networks (RNNs). As the classification of transactions is of great significance, this research is extended towards explainable AI, where LIME and SHAP frameworks are utilized to interpret and illustrate the ML classification results. Our approach shows promising results on a real-world banking use case and acts as the foundation for the development of further BFM banking microservices, such as transaction fraud detection and budget monitoring.