Machine Learning for Financial Data
Financial data analytics are in the focus of interest due to a number of reasons. For example, predictions of vector time series underwent a huge progress due to the deep learning technologies. This is the direction of the stock market. Another direction is to consider the underlying networks. The diverse trees of production lines form such networks; packaging industry depends on miniaturization, the price of steel depends on the price of a number of components, such as oil, iron, chemicals as well as many others. The web of prices and products influences prices in diverse ways and it would be interesting to look at such dependencies. Pattern mining (item sets, association rules, frequent graphs, etc.) or recommendation techniques represent other interesting directions. In turn, financial data analytics have several challenges, such as traditional and deep learning technologies on financial data, data and pattern mining on the web of dependencies, and data visualization for the sake of human-AI interaction and enhanced user experience.
The school will provide an introduction to the benefits and best practices of machine learning and deep learning in the financial sector. Data and pattern mining on the web of special transactions-like data as well as visualization techniques will also be presented.
Students will work on business assignments for innovative use of machine learning in cooperation with companies and start-ups in the Budapest region.
This programme is organised by EIT Digital Summer School and Eötvös Loránd University (ELTE), Hungary.