Deep Finance

Το DeepFinance θέτει ως βασικό στόχο τη δημιουργία μιας ολοκληρωμένης πλατφόρμας σημασιολογικής ανάλυσης και εξαγωγής συναισθήματος από ροές κοινωνικών δικτύων με μεθόδους Βαθιάς Μάθησης (Deep Learning) , αλλά και ολοκληρωμένων εργαλείων διαχείρισης χρηματοοικονομικών χαρτοφυλακίων , οι οποίες είναι σε θέση να συντήξουν πολυτροπική πληροφορία που εξάγεται από ποικίλες (ανομοιόμορφες) πηγές δεδομένων, συμπεριλαμβανομένης και της σημασιολογικής ανάλυσης ροών από κοινωνικά δίκτυα. Έτσι, τίθενται οι εξής στόχοι:

[G1] Develop deep learning tools for automated portfolio management, by SpeedLab (SL), aiming to achieve better performance (according to various financial metrics) compared to the currently used strategies that mainly consist of handcrafted decision rules. Research will focus on developing robust deep learning methods. Furthermore, DeepFinance will research on developing robust agents, using deep learning and deep reinforcement learning methods, aiming to directly maximize the profit, as well as using novel price control strategies, e.g., directly placing limit orders, where the agent decides for the quantity, price and time to place an order at the same time. 

[G2] Develop a platform for semantic analysis of social media streams, e.g., twitter, blogs, etc., by DataScouting (DS), in order to provide semantic and sentiment analysis services for specific stocks, financial indices, etc. It is worth noting that large media companies, e.g., Bloomberg, already provide similar services. The developed platform will integrate state-of-the-art deep learning and natural language processing tools, allowing for semantic and sentiment analysis from heterogeneous data streams. At the same time, the developed platform will allow for further finding cause-effect correlations between various events, providing an additional tool which DS can integrate in its products. 

[G3] Integrate the semantic and sentiment analysis services from DS to the products of SL in order to develop portfolio management products that take into account the information, regarding the market's sentiment, that can be extracted from social media. Develop and integrate multi-modal deep learning and deep reinforcement learning methods for portfolio management that take into account additional heterogeneous information (limit order book, stock/index prices, sentiment, etc.).