Construction of confidence interval for a univariate stock price signal predicted through Long Short Term Memory Network
This work addresses uncertainty quantification in financial time series forecasting, but it appears incremental as it applies existing bootstrap techniques to LSTM predictions.
The paper tackles the problem of constructing confidence intervals for stock price signals predicted by LSTM models, proposing bootstrap methods for dependent data and providing experimental results on stock price datasets.
In this paper, we show an innovative way to construct bootstrap confidence interval of a signal estimated based on a univariate LSTM model. We take three different types of bootstrap methods for dependent set up. We prescribe some useful suggestions to select the optimal block length while performing the bootstrapping of the sample. We also propose a benchmark to compare the confidence interval measured through different bootstrap strategies. We illustrate the experimental results through some stock price data set.