Skip to main content

Training for Big Data in Financial Research and Risk Management

Periodic Reporting for period 2 - BigDataFinance (Training for Big Data in Financial Research and Risk Management)

Reporting period: 2017-10-01 to 2019-09-30

We are witnessing a new industrial revolution driven by digital data, computation, and automation. The resulting datasets are so large and complex that such “Big Data” is becoming difficult to process with the current data management tools and methods. If successfully processed and managed, Big Data has the potential to spur new products, services, and practices as well as new scientific methodologies. One European sector that could greatly benefit from the use of Big Data is Finance. To exploit this potential, banks and other financial institutions must be able to handle and process massive heterogeneous data sets in a fast and robust manner.

BigDataFinance ITN, “Training for Big Data in Financial Research and Risk Management”, has provided doctoral training in sophisticated data-driven risk management and research at the crossroads of Finance and Big Data for 13 Early State Researchers (ESR). The main training objective of BigDataFinance were to meet the increasing commercial demand for well-trained researchers with experience in both Big Data techniques and Finance. The main research object was to develop and implement new quantitative models and econometric methods for empirical financial research and risk management by bridging the gap between research methodologies in Finance and Data Science. To achieve the objectives, the emphasis was put on exploiting big data techniques to manage and use datasets that are too large and complex to process with conventional methods. This program provided new realistic data-driven scientific approaches that will be requisite in finance.
During the second period, the Early Stage Researcher, who were recruited successfully, achieved all the research deliverables according to the research plan. The project has published 14 journal papers, 7 conference papers, and 13 working papers altogether. During this period, the consortium has organized two events: (i) an internal training event on start-ups and proposal writing (Lapland, Finland) and (ii) the final conference on “International Conference on Fintech & Financial Data Science” (Dublin, Ireland) in the collaboration with University College Dublin. The conference released an open call and a special issue “Recent Developments in Financial Data Science and Econometrics” in the European Journal of Finance is associated with the conference. The milestones and deliverables are achieved, except some of the PhD manuscripts will be delayed.
Financial research with Big Data needs multidisciplinary collaboration and new researcher profiles with the right competences to apply both modern data engineering techniques and state-of-the-art econometric methods to the financial domain and to progress towards computational methods with an emphasis on extensive use of real data. Especially financial risk management can no longer rely on pure traditional approaches, which often make unrealistic assumptions for the sake of soluble theoretical models over agreement with empirical data. To address these challenges, BigDataFinance consortium
(i) provides sophisticated methods in data science for financial modelling and risk management and pay special attention to machine learning and knowledge extraction algorithms;
(ii) uses and develops methods and visualisation approaches with complex networks to increase understanding of the phenomena in financial markets arising from large and diverse data sets;
(iii) provides new econometric methods augmented with textual data sources and (ultra-)high-frequency stock market data for advanced risk management;
(iv) develops and publish an open financial sentiment index based on social media data and an open software to model and predict macroeconomic indicators;
(v) implements new Big Data applications with machine learning and knowledge extraction techniques for advanced financial risk and investment management in real business environments.
These objectives stimulate practitioners to exploit data-driven and robust risk management models and abandon less realistic ones for safer operation with financial instruments and better focus on the real properties of financial and economic variables arising from real data. On the academic side, BigDataFinance promotes the use of massive integrated data sources to develop innovative financial models and methods reassessing the unrealistic assumptions so far applied with homogenous data sets. These objectives will be vitally important to the financial sector, solution providers, and researchers.
BigDataFinance Logo