arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2006.03132q-fin.GNcs.LGstat.ML
收藏

使用深度学习进行盈利预测

Earnings Prediction with Deep Learning

Carl von Ossietzky University of Oldenburg(卡尔·冯·奥西茨基奥尔登堡大学);University of Hamburg(汉堡大学)

Lars Elend, Sebastian A. Tideman, Kerstin Lopatta, Oliver Kramer

摘要:

在金融领域,对公司未来财务业绩的可靠预测对投资者的投资决策至关重要。在本文中,我们将长期短期记忆(LSTM)网络与时间卷积网络(TCN)在预测未来每股收益(EPS)方面进行了比较。实验分析是基于季度财务报告数据和每日股票市场收益率。对于广泛的美国公司样本,我们发现,这两个LSTM优于天真的持久性模型高达30.0%更准确的预测,而TCN实现和30.8%的改善。这两种类型的网络至少与分析师一样准确,并超过分析师12.2%(LSTM)和13.2%(TCN)。

英文摘要:

In the financial sector, a reliable forecast the future financial performance of a company is of great importance for investors' investment decisions. In this paper we compare long-term short-term memory (LSTM) networks to temporal convolution network (TCNs) in the prediction of future earnings per share (EPS). The experimental analysis is based on quarterly financial reporting data and daily stock market returns. For a broad sample of US firms, we find that both LSTMs outperform the naive persistent model with up to 30.0% more accurate predictions, while TCNs achieve and an improvement of 30.8%. Both types of networks are at least as accurate as analysts and exceed them by up to 12.2% (LSTM) and 13.2% (TCN).

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑