|
on Market Microstructure |
| By: | Iuri H. Ferreira; Marcelo C. Medeiros |
| Abstract: | In this paper we examine the relation between market returns and volatility measures through machine learning methods in a high-frequency environment. We implement a minute-by-minute rolling window intraday estimation method using two nonlinear models: Long-Short-Term Memory (LSTM) neural networks and Random Forests (RF). Our estimations show that the CBOE Volatility Index (VIX) is the strongest candidate predictor for intraday market returns in our analysis, specially when implemented through the LSTM model. This model also improves significantly the performance of the lagged market return as predictive variable. Finally, intraday RF estimation outputs indicate that there is no performance improvement with this method, and it may even worsen the results in some cases. |
| Date: | 2021–12 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2112.15108&r= |
| By: | Mei-Ling Cai; Zhang-HangJian Chen; Sai-Ping Li; Xiong Xiong; Wei Zhang; Ming-Yuan Yang; Fei Ren |
| Abstract: | In this paper, we propose a new dynamical model to study the two-stage volatility evolution of stock market index after extreme events, and find that the volatility after extreme events follows a stretched exponential decay in the initial stage and becomes a power law decay at later times by using high frequency minute data. Empirical study of the evolutionary behaviors of volatility after endogenous and exogenous events further demonstrates the descriptive power of our new model. To further explore the underlying mechanisms of volatility evolution, we introduce the sequential arrival of information hypothesis (SAIH) and the mixture of distribution hypothesis (MDH) to test the two-stage assumption, and find that investors transform from the uninformed state to the informed state in the first stage and informed investors subsequently dominate in the second stage. The testing results offer a supporting explanation for the validity of our new model and the fitted values of relevant parameters. |
| Date: | 2022–01 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2201.03213&r= |