Financial News in Exchange Rate Prediction: the Relationships between News Platforms, Text Feature Representations, and Supervised Learning Models

Project: National Science and Technology CouncilNational Science and Technology Council Academic Grants

Project Details

Abstract

本研究計畫的結果與發現可以進一步瞭解歷史數據、基本面信息與財經新聞對於匯率趨勢的影響,同時,找出如何搭配不同型態的特徵(文字特徵及情緒特徵)以建構出機器學習技術與深度學習技術之最佳預測模型。因此,在學術上的貢獻為找出現有相關技術之最佳預測模型並可當作未來研究之參考;在實務上的貢獻將可進一步提升AI技術於匯率趨勢預測的實用性。

Project IDs

Project ID:PB11207-2766
External Project ID:NSTC111-2410-H182-015-MY3
StatusFinished
Effective start/end date01/08/2331/07/24

Keywords

  • exchange rate prediction
  • financial news
  • text mining
  • machine learning
  • deep learning

Fingerprint

Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.