Long-range time series forecasting is usually based on one of two existing forecasting strategies: Direct Forecasting and Iterative Forecasting, where the former provides low bias, high variance forecasts and the later leads to low variance, high bias forecasts. In this paper, we propose a new forecasting strategy called Generative Forecasting (GenF), which generates synthetic data for the next few time steps and then makes long-range forecasts based on generated and observed data. We theoretically prove that GenF is able to better balance the forecasting variance and bias, leading to a much smaller forecasting error. We implement GenF via three components: (i) a novel conditional Wasserstein Generative Adversarial Network (GAN) based generator for synthetic time series data generation, called CWGAN-TS. (ii) a transformer based predictor, which makes long-range predictions using both generated and observed data. (iii) an information theoretic clustering algorithm to improve the training of both the CWGAN-TS and the transformer based predictor. The experimental results on five public datasets demonstrate that GenF significantly outperforms a diverse range of state-of-the-art benchmarks and classical approaches. Specifically, we find a 5% - 11% improvement in predictive performance (mean absolute error) while having a 15% - 50% reduction in parameters compared to the benchmarks. Lastly, we conduct an ablation study to demonstrate the effectiveness of the components comprising GenF.
翻译:长期时间序列预测通常基于两种现有预测战略之一:直接预测和循环预测,前者提供低偏差、高差异预测,而后者则导致低偏差、高偏差预测。在本文件中,我们提出一个新的预测战略,称为“GenF”,为今后几个步骤生成合成数据,然后根据生成和观察到的数据进行远程预测。我们理论上证明,GENF能够更好地平衡预测差异和偏差,从而导致一个更小的预测错误。我们通过三个组成部分执行GENF:(一) 一个新的基于新颖条件的瓦瑟斯坦·吉纳杜萨里网络(GAN)的生成器,用于合成时间序列数据生成,称为CWGAN-TS。 (二) 基于变压器的预测器,利用生成和观察到的数据进行长期预测。(三) 信息理论组合算法,以改进对CWGAN-TS和变压器的训练,从而导致一个更小得多的预测错误。五套公共数据集的实验结果显示,GENF大大超越了以合成时间序列生成数据生成的数据范围,称为CWGANANANAN-一个精确的5级基准,同时对15的精确度的精确度指标进行对比。