Business School, Central South University, Changsha, China.
School of Information Systems, Singapore Management University, Stamford Road, Singapore, Singapore.
PLoS One. 2020 Nov 4;15(11):e0241573. doi: 10.1371/journal.pone.0241573. eCollection 2020.
Construction of a reliable stock portfolio remains an open issue in quantitative investment. Multiple machine learning models have been trained for stock portfolio selection, but their practical applicability remains limited due to the challenges posed by the characteristic of a low signal-to-noise ratio (SNR), the nature of time-series data, and non-independent identical distribution in financial data. Here, we transformed the stock selection task into a matching problem between a group of stocks and a stock selection target. We proposed a novel representation algorithm of stock selection target and a novel deep matching algorithm (TS-Deep-LtM). Then we proposed a deep stock profiling method to extract the optimal feature combination and trained a deep matching model based on TS-Deep-LtM algorithm for stock portfolio selection. Especially, TS-Deep-LtM algorithm was obtained by setting statistical indicators to filter and integrate three deep text matching algorithms. This parallel framework design made it good at capturing signals from time-series data and adapting to non-independent identically distributed data. Finally, we applied the proposed model to stock selection and tested long-only portfolio strategies from 2010 to 2017. We demonstrated that the risk-adjusted returns obtained by our portfolio strategies outperformed those obtained by the CSI300 index and learning-to-rank approaches during the same period.
构建可靠的股票投资组合在定量投资中仍是一个悬而未决的问题。已经有多个机器学习模型被用于股票投资组合选择，但由于低信噪比（SNR）特征、时间序列数据的性质以及金融数据中非独立同分布的挑战，其实际应用仍然有限。在这里，我们将股票选择任务转化为一组股票与股票选择目标之间的匹配问题。我们提出了一种新的股票选择目标表示算法和一种新的深度匹配算法（TS-Deep-LtM）。然后，我们提出了一种深度股票分析方法来提取最佳特征组合，并基于 TS-Deep-LtM 算法训练深度匹配模型进行股票投资组合选择。特别是，TS-Deep-LtM 算法是通过设置统计指标来过滤和整合三种深度文本匹配算法得到的。这种并行框架设计使其善于从时间序列数据中捕捉信号，并适应非独立同分布数据。最后，我们将所提出的模型应用于股票选择，并测试了 2010 年至 2017 年的单一股票投资组合策略。结果表明，在同一时期，我们的投资组合策略获得的风险调整收益优于 CSI300 指数和学习排序方法获得的收益。
