Multi-task Meta Label Correction for Time Series Prediction
This work addresses label quality issues in time series prediction, particularly for financial data, but appears incremental as it builds on existing meta-learning and multi-task frameworks.
The paper tackles the problems of partial feature information and poor label quality in time series classification by developing a multi-task meta-learning label correction method, which is shown to be more effective and accurate than existing techniques on financial datasets like XOM, S&P500, and SZ50.
Time series classification faces two unavoidable problems. One is partial feature information and the other is poor label quality, which may affect model performance. To address the above issues, we create a label correction method to time series data with meta-learning under a multi-task framework. There are three main contributions. First, we train the label correction model with a two-branch neural network in the outer loop. While in the model-agnostic inner loop, we use pre-existing classification models in a multi-task way and jointly update the meta-knowledge so as to help us achieve adaptive labeling on complex time series. Second, we devise new data visualization methods for both image patterns of the historical data and data in the prediction horizon. Finally, we test our method with various financial datasets, including XOM, S\&P500, and SZ50. Results show that our method is more effective and accurate than some existing label correction techniques.