提出MEANT模型，融合多模态历史信息预测股市走势
MEANT: Multimodal Encoder for Antecedent Information
- 设计多模态编码器，捕捉价格、推文、图像等跨时间信息
- 在超百万条推文的TempStock数据集上提升基准性能15%以上
- 文本信息比视觉信息对预测更关键，适合金融时序建模研究者
股票市场蕴含丰富多模态信息，是开展多模态学习的理想场景。多模态数据在机器学习中日益重要，能有效提升模型性能。但信息不仅跨模态存在，也跨时间分布。如何处理包含多种信息类型的时间序列数据？本文提出（i）MEANT模型——用于捕获前因信息的多模态编码器，以及（ii）新数据集TempStock，包含标普500指数所有公司超过一百万条推文、股价和图形数据。实验表明，MEANT在现有基线基础上性能提升超过15%，消融实验显示文本信息对任务表现的影响远大于视觉信息。
原文摘要 · Abstract (English)
The stock market provides a rich well of information that can be split across modalities, making it an ideal candidate for multimodal evaluation. Multimodal data plays an increasingly important role in the development of machine learning and has shown to positively impact performance. But information can do more than exist across modes -- it can exist across time. How should we attend to temporal data that consists of multiple information types? This work introduces (i) the MEANT model, a Multimodal Encoder for Antecedent information and (ii) a new dataset called TempStock, which consists of price, Tweets, and graphical data with over a million Tweets from all of the companies in the S&P 500 Index. We find that MEANT improves performance on existing baselines by over 15%, and that the textual information affects performance far more than the visual information on our time-dependent task from our ablation study.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。