arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.07925cs.LGq-fin.MF
收藏

面向存在分布偏移的金融时序表格数据集的深度增量学习模型

Deep incremental learning models for financial temporal tabular datasets with distribution shifts

Imperial College London(帝国理工学院)

Thomas Wong, Mauricio Barahona

AI总结:

针对金融时序表格数据的分布偏移问题,提出基于决策树的深度增量学习框架,通过XGBoost深度集成实现不同市场环境下的鲁棒预测,且训练硬件要求低、可并行。

摘要:

我们提出了一种适用于金融时序表格数据集回归任务的鲁棒深度增量学习框架,该框架以增量方式调用常用的表格数据与时间序列预测模型构建而成,可适配金融数据集典型的分布偏移特性。该框架采用简单的基础构件(决策树)搭建具备任意所需复杂度的自相似模型,在 regime 切换、肥尾分布、低信噪比等不利场景下仍能保持鲁棒性能。作为详细研究,我们使用在 Numerai 数据集上训练的 XGBoost 模型验证了该方案,结果表明,基于不同模型快照构建的两层 XGBoost 深度集成模型在不同市场 regime 下均能产出高质量预测结果。我们还发现,在小型、标准、大型三种场景下,具有不同提升轮数的 XGBoost 模型性能随模型规模单调提升,并向泛化上界收敛。我们同时评估了模型在不同超参数(如模型复杂度、数据采样设置)变动下的鲁棒性。该模型硬件要求低,无需使用专门的神经网络架构,且每个基模型可独立并行训练。

英文摘要:

We present a robust deep incremental learning framework for regression tasks on financial temporal tabular datasets which is built upon the incremental use of commonly available tabular and time series prediction models to adapt to distributional shifts typical of financial datasets. The framework uses a simple basic building block (decision trees) to build self-similar models of any required complexity to deliver robust performance under adverse situations such as regime changes, fat-tailed distributions, and low signal-to-noise ratios. As a detailed study, we demonstrate our scheme using XGBoost models trained on the Numerai dataset and show that a two layer deep ensemble of XGBoost models over different model snapshots delivers high quality predictions under different market regimes. We also show that the performance of XGBoost models with different number of boosting rounds in three scenarios (small, standard and large) is monotonically increasing with respect to model size and converges towards the generalisation upper bound. We also evaluate the robustness of the model under variability of different hyperparameters, such as model complexity and data sampling settings. Our model has low hardware requirements as no specialised neural architectures are used and each base model can be independently trained in parallel.

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。

↑