• Technical Name
  • 圖機器學習高回報率金融商品推薦技術
  • Operator
  • National Cheng Kung University
  • Booth
  • AIoT&智慧應用 AIoT & Smart Applications
  • Contact
  • 李政德
  • Email
  • reliefli@gmail.com
Technical Description In the context of FinTech, we present Financial Graph Attention Networks (FinGAT) to recommend high-profitable stocks in terms of return ratio using time series of stock pricessector info. Our FinGAT can learn the long-short-term price tendency,model the latent interactionsinfluence between stockssectors without any hand-crafted effort. Experiments conducted on Taiwan Stock, S&P 500,NASDAQ stock markets exhibit remarkable accuracy of FinGAT, comparing to state-of-the-arts (by 11, 14,12 performance improvement). The tech is published in IEEE TKDE 2021.
Scientific Breakthrough Our tech FinGAT is a graph neural network-based high-profitable financial recommender system. FinGAT can learn long-short-term tendency of stock prices,simultaneous capture how stockstheir corresponding sectors are interactedcorrelated with each other without external knowledge on the relationships between listed companies. Experiments conducted on TWSE, S&P500,NASDAQ show that FinGAT outperforms state-of-the-art methods by at least 10. When incorporating human financial knowledge to select candidate stocks, FinGAT can further lead to 0.97 ranking accuracy.
Industrial Applicability FinGAT has been extended to several Taiwan’s financial institutions, including Bank SinoPacE.SUN Bank, to precisely recommend financial items for customers. The main target of FinGAT is financial institutions in Taiwanin the world. We expect to bring three-fold economic impacts: (1) increasing the market value of listed companies, (2) boosting the transaction volumerate of the banking industry, (3) increasing customer profitabilityraise consumer willingness. FinGAT is open-sourced,can be used for e-commerce recommender systems, ad placement,precision marketing.