Exploring the predictability of range-based volatility estimators using RNNs
This work addresses volatility prediction for financial markets, but it is incremental as it applies existing methods to compare estimators without major breakthroughs.
The paper tackled predicting stock volatility by comparing range-based estimators to the standard close-to-close estimator using LSTM recurrent neural networks, finding that changes in range-based estimators are more predictable, with results averaged across Dow Jones Industrial Average constituents.
We investigate the predictability of several range-based stock volatility estimators, and compare them to the standard close-to-close estimator which is most commonly acknowledged as the volatility. The patterns of volatility changes are analyzed using LSTM recurrent neural networks, which are a state of the art method of sequence learning. We implement the analysis on all current constituents of the Dow Jones Industrial Average index, and report averaged evaluation results. We find that changes in the values of range-based estimators are more predictable than that of the estimator using daily closing values only.