Biography

Anna Warno, data scientist, graduated in mathematics, employed at 7bulls. Involved in projects in the field of computer vision, nlp, time series. Actively participates in conferences and research projects, including advanced Horizon 2020 research projects. Published on conferences, including NIPS. Hackathons lover.

Biography

Paweł Skrzypek is a highly experienced architect of ICT systems, with extensive knowledge of machine learning and Big Data solutions. Chief Multi Cloud Architect, working on MELODIC project and other Cloud Computing projects, focusing on multi cloud and serverless approach.

Talk

Complex AI Forecasting Methods for Investments Portfolio Optimization

Presentation of the first complete AI investment platform. It is based on the most innovative AI methods: most advanced neural networks (ResNet/DenseNet, LSTM, GAN autoencoders) and reinforcement learning for risk control and position sizing using the Alpha Zero approach.

It shows how the complex AI system which covers both supervised and reinforcement learning could be successfully used for investment portfolio optimization in real-time. The architecture of the platform and used algorithms will be presented together with the workflow of machine learning. Also, a real demo of the platform will be shown. The M4 conference winning forecasting method will be presented, with the application to financial time series forecasting.

Session Keywords