[ACM CIKM 2021] Learning to Learn the Future: Modeling Concept Drift in Time Series Prediction

发布者:张琬琪发布时间:2021-08-18浏览次数:690

Authors:

Xiaoyu You, Mi Zhang, Daizong Ding, Fuli Feng, Yuanmin Huang


Publication:

In Proceedings of the 30th ACM International Conference on Information and Knowledge Management (CIKM2021),1-5 November 2021, Australia.


Abstract:

Time series prediction has great practical value in a wide range of real-world scenarios such as stock market and retail. Existing methods typically face model aging issue caused by the concept drift: the model performance degrades along time. Undoubtedly, the model aging issue can cause serious damage in practical usage, e.g. wrong predictions in stock price may cause catastrophic losses in the financial domain. Therefore, it is essential to address the model aging issue so as to promise the predictor's performance in the future. In this paper, we propose a novel solution to address the issue. First, we uncover the theoretical connection between the complex concept drift in time series data and the gradients of deep neural networks. Based on this, we propose a novel framework called \emph{learning to learn the future}. Specifically, we develop a learning method to model the concept drift during the inference stage, which can help the model generalize well in the future. Furthermore, to mitigate the impact of noises and randomness of time series data, we propose to enhance the framework by leveraging similar series in concept drift modeling. To the best of our knowledge, our approach is the first general solution to tackle model aging issue in time series prediction. We conduct extensive experiments on three real-world datasets, which validate the effectiveness of our framework. For instance, it achieves an relative improvement of 33% in stock price prediction over the state-of-the-art methods.