[论文解读] Benchmarking Deep Sequential Models on Volatility Predictions for Financial Time Series

Qiang Zhang, Rui Luo+2 more|arXiv (Cornell University)|Nov 8, 2018

Stock Market Forecasting Methods参考文献 50被引用 5

一句话总结

本论文在为期2,018个交易日的1,314只日频股票系列上，对深度序列模型——特别是空洞卷积和循环网络——进行了金融波动率预测的基准测试。结果表明，空洞神经网络（TCN和DilatedRNN）显著优于传统的GARCH和随机波动率模型，实现了最低的负对数似然（NLL）损失，凸显了其在波动率预测中卓越的灵活性和表达能力。

ABSTRACT

Volatility is a quantity of measurement for the price movements of stocks or options which indicates the uncertainty within financial markets. As an indicator of the level of risk or the degree of variation, volatility is important to analyse the financial market, and it is taken into consideration in various decision-making processes in financial activities. On the other hand, recent advancement in deep learning techniques has shown strong capabilities in modelling sequential data, such as speech and natural language. In this paper, we empirically study the applicability of the latest deep structures with respect to the volatility modelling problem, through which we aim to provide an empirical guidance for the theoretical analysis of the marriage between deep learning techniques and financial applications in the future. We examine both the traditional approaches and the deep sequential models on the task of volatility prediction, including the most recent variants of convolutional and recurrent networks, such as the dilated architecture. Accordingly, experiments with real-world stock price datasets are performed on a set of 1314 daily stock series for 2018 days of transaction. The evaluation and comparison are based on the negative log likelihood (NLL) of real-world stock price time series. The result shows that the dilated neural models, including dilated CNN and Dilated RNN, produce most accurate estimation and prediction, outperforming various widely-used deterministic models in the GARCH family and several recently proposed stochastic models. In addition, the high flexibility and rich expressive power are validated in this study.

研究动机与目标

• 评估现代深度序列模型在金融波动率预测中的性能。
• 比较深度学习架构与GARCH和SV等经典波动率模型在表达能力和灵活性方面的差异。
• 为将深度学习整合到金融时间序列建模中提供实证指导。
• 评估空洞架构在捕捉波动率动态中长程依赖关系方面的有效性。

提出的方法

• 研究采用基准测试框架，基于2,018个交易日内的1,314只日频股票价格序列。
• 深度序列模型包括时间卷积网络（TCN）、空洞RNN（DilatedRNN）、IndRNN、QRNN、SkipRNN、HM-RNN、FS-RNN和RHN，所有模型均基于GRU或LSTM单元构建。
• 空洞卷积和循环层通过使用膨胀因子来扩展感受野，同时保持参数数量不变。
• 模型训练采用ReLU激活函数、Xavier权重初始化、Adam优化算法、Dropout正则化、梯度裁剪以及学习率衰减策略。
• 性能通过在测试集上对1步 ahead 波动率预测的负对数似然（NLL）进行评估。
• 通过五折交叉验证调整超参数，所有模型均使用PyTorch在单张NVIDIA TITAN XP GPU上实现。

实验结果

研究问题

• RQ1 空洞深度学习架构是否能在波动率预测中超越经典的GARCH和随机波动率模型？
• RQ2 不同深度序列模型——尤其是空洞CNN和RNN——在捕捉波动率动态方面的表现如何比较？
• RQ3 卷积结构与循环结构在建模金融时间序列波动率方面各自贡献如何？
• RQ4 空洞架构在多大程度上提升了波动率预测中长程依赖关系的建模能力？

主要发现

• 空洞神经网络，特别是TCN和DilatedRNN，在全部1,314只股票系列中均实现了最低的负对数似然（NLL），表明其具有更高的预测准确性。
• TCN的平均NLL为1.901，显著低于EGARCH的2.003和GARCH的2.084，显示出持续的优越性能。
• TCN优于所有RNN变体，包括DilatedRNN，其平均NLL为1.901，而DilatedRNN为1.903，表明卷积层在波动率建模中更为有效。
• FS-RNN表现最差，平均NLL为2.451，表明其在此任务中适用性有限。
• SkipRNN和QRNN的性能略逊于TCN和DilatedRNN，但依然具有竞争力，其平均NLL分别为1.925和1.908。
• 结果验证了空洞架构在建模金融数据中复杂且时变的波动率模式方面具有高度灵活性和强大的表达能力。