2022/05/14 by German Rodikov, Rodikov, German, Nino Antulov-Fantulin +1
Decision Sciences · Economics, Econometrics and Finance · Engineering · #Complex Systems and Time Series Analysis #Computational Finance (q-fin.CP) #Energy Load and Power Forecasting #FOS: Economics and business #Stock Market Forecasting Methods
paper · pdf · doi:10.48550/arxiv.2205.07022
openalex publication_date 2022/05/14 · openalex created_date 2022/05/22 · openalex updated_date 2026/07/28
Volatility models of price fluctuations are well studied in the econometrics literature, with more than 50 years of theoretical and empirical findings. The recent advancements in neural networks (NN) in the deep learning field have naturally offered novel econometric modeling tools. However, there is still a lack of explainability and stylized knowledge about volatility modeling with neural networks; the use of stylized facts could help improve the performance of the NN for the volatility prediction task. In this paper, we investigate how the knowledge about the "physics" of the volatility process can be used as an inductive bias to design or constrain a cell state of long short-term memory (LSTM) for volatility forecasting. We introduce a new type of σ-LSTM cell with a stochastic processing layer, design its learning mechanism and show good out-of-sample forecasting performance.