Construction of confidence interval for a univariate stock price signal predicted through Long Short Term Memory Network

TL;DR

This paper introduces a novel approach to constructing bootstrap confidence intervals for stock price signals predicted by univariate LSTM models, comparing different bootstrap methods and providing practical guidelines.

Contribution

It proposes a new bootstrap-based method for confidence interval construction in LSTM predictions and offers a benchmark for comparing bootstrap strategies.

Findings

Different bootstrap methods vary in interval accuracy

Optimal block length selection improves bootstrap performance

Experimental results demonstrate effectiveness on stock data

Abstract

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.