用于股票价格预测的鲁棒深度学习模型的设计与分析
统计金融
2021-10-12 v1 机器学习
摘要
构建鲁棒且准确的股票价格与股价变动预测模型是一个具有挑战性的研究课题。著名的有效市场假说认为,在有效股票市场中未来股价无法被准确预测,因为假定股价纯随机。然而,研究者提出的众多工作已表明,借助精细的算法、模型架构以及模型中适当变量的选取,可以高精度地预测未来股价。本章提出一组构建于深度学习架构上的预测回归模型,用于对印度国家证券交易所(NSE)中跨行业上市股票的未来价格进行鲁棒而精确的预测。使用 Metastock 工具下载了两年期间(2013–2014)间隔 5 分钟的历史股价。首年记录用于训练模型,其余记录用于测试。文中详细给出了所有模型的设计方法及其性能结果。还基于执行时间与预测精度对模型进行了比较。
引用
@article{arxiv.2106.09664,
title = {Design and Analysis of Robust Deep Learning Models for Stock Price Prediction},
author = {Jaydip Sen and Sidra Mehtab},
journal= {arXiv preprint arXiv:2106.09664},
year = {2021}
}
备注
This is the pre-print of our chapter that has been accepted for publication in the forthcoming book entitled "Machine Learning: Algorithms, Models, and Applications". The book will be published by IntechOpen, London, UK, in an open access in the later part of the year 2021. The chapter is 29 pages long, and it has 20 figures and 21 tables. arXiv admin note: substantial text overlap with arXiv:2103.15096