07.10.2022, 15:02

Seminarium QFRG i DSLab [10.10.2022]

Serdecznie zapraszamy do wzięcia udziału w 22. seminarium organizowanym przez QFRG (Quantitative Finance Research Group) i DSLab (Data Science Lab).

Podczas spotkania dr Paweł Sakowski z Katedry Finansów Ilościowych WNE UW oraz Maciej Wysocki, student Szkoły Doktorskiej Nauk Społecznych Uniwersytetu Warszawskiego przedstawią wyniki badania “Investment Portfolio Optimization Based on Modern Portfolio Theory and Deep Learning Models".

Opis badania:

The study investigates the problem of an appropriate variance-covariance matrix estimation in the Modern Portfolio Theory. A novel approach combining the Markowitz framework with deep learning models was proposed and tested on portfolios of stocks and cryptocurrencies. Long short-term memory neural networks along with probabilistic deep learning models DeepVAR and GPVAR were compared with the classical approaches: frequentist estimator, exponentially weighted moving average, and shrinkage estimators. The LSTM model provided the best results across multiple investment schemes in terms of the information ratio, while the classical estimators in general performed the worst. Although the probabilistic deep learning models produced stable results, these strategies performed worse than the LSTM-based ones.

Spotkanie odbędzie się 10 października 2022 r. o godz. 18:30 za pośrednictwem platformy Google Meet i będzie prowadzone w języku angielskim.

Link do spotkania: meet.google.com/gnr-gfbh-fxc

QFRGiDSLab_2022-10-10_small.png