It is a challenging problem to predict trends of futures prices with traditional econometric models as one needs to consider not only futures' historical data but also correlations among different futures. Spatial-temporal graph neural networks (STGNNs) have great advantages in dealing with such kind of spatial-temporal data. However, we cannot directly apply STGNNs to high-frequency future data because future investors have to consider both the long-term and short-term characteristics when doing decision-making. To capture both the long-term and short-term features, we exploit more label information by designing four heterogeneous tasks: price regression, price moving average regression, price gap regression (within a short interval), and change-point detection, which involve both long-term and short-term scenes. To make full use of these labels, we train our model in a continual manner. Traditional continual GNNs define the gradient of prices as the parameter important to overcome catastrophic forgetting (CF). Unfortunately, the losses of the four heterogeneous tasks lie in different spaces. Hence it is improper to calculate the parameter importance with their losses. We propose to calculate parameter importance with mutual information between original observations and the extracted features. The empirical results based on 49 commodity futures demonstrate that our model has higher prediction performance on capturing long-term or short-term dynamic change.

翻译：利用传统计量经济学模型预测期货价格趋势是一项具有挑战性的问题，因为不仅需要考虑期货的历史数据，还需考虑不同期货之间的关联性。时空图神经网络（STGNNs）在处理此类时空数据方面具有显著优势。然而，由于期货投资者在决策时需同时考虑长期和短期特征，因此无法直接将STGNNs应用于高频期货数据。为捕捉长期与短期特征，我们通过设计四种异构任务来利用更多标签信息：价格回归、价格移动平均回归、价格缺口回归（短时间间隔内）以及变点检测，这些任务涵盖长期和短期场景。为充分利用这些标签，我们以持续学习方式训练模型。传统连续图神经网络将价格梯度定义为克服灾难性遗忘（CF）的关键参数。然而，这四种异构任务的损失函数位于不同空间，因此用它们的损失计算参数重要性并不恰当。我们提出利用原始观测值与提取特征之间的互信息来计算参数重要性。基于49种商品期货的实证结果表明，我们的模型在捕捉长期或短期动态变化方面具有更高的预测性能。