COST FinAI - Fintech and AI in Finance - WG1 Monthly research seminar

2:00-2:30 pm
A multifactor random field model for the term structure of interest rates

Speaker: Marianna Russo, Postdoc at Norwegian University of Science and Technology (NTNU)

Abstract: In this paper, we aim at representing the term structure of interest rates as a random field starting from the dynamic Nelson-Siegel model specification. We explore volatility clustering patterns and correlation structures in the noise term of a dynamic Nelson-Siegel model through a continuous-in-maturity GARCH with a copula derived in continuous time. In contrast to multifactor models, random field models offer a parsimonious description of the term structure dynamics. This novel approach allows for different intensities of volatility along the maturity dimension of the term structure in the context of a correlated spatio-temporal GARCH random field model.

2:30-3:00 pm
Day-ahead electricity prices prediction applying hybrid models of LSTM-based deep learning methods and feature selection algorithms under consideration of market coupling

Speaker: Wei Li, PhD candidate at Norwegian University of Science and Technology (NTNU)

Abstract: The availability of accurate day-ahead electricity price forecasts is pivotal for electricity market participants. In the context of trade liberalisation and market harmonisation in the European markets, accurate price forecasting becomes even more difficult to obtain. The increasing power market integration has complicated the forecasting process, where electricity forecasting requires considering features from both the local market and ever-growing coupling markets. In this paper, we apply state-of-the-art deep learning models, combined with feature selection algorithms for electricity price prediction under the consideration of market coupling. We propose three hybrid architectures of long-short term memory (LSTM) deep neural networks and compare the prediction performance, in terms of various feature selections. In our empirical study, we construct a broad set of features from the Nord Pool market and its six coupling countries for forecasting the Nord Pool system price. The results show that feature selection is essential to achieving accurate prediction. Superior feature selection algorithms filter meaningful information, eliminate irrelevant information, and further improve the forecasting accuracy of LSTM-based deep neural networks. The proposed models obtain considerably accurate results.