AI in Finance: Challenges, Techniques, and Opportunities

被引:81
作者
Cao, Longbing [1 ]
机构
[1] Univ Technol Sydney, Sydney, NSW, Australia
基金
澳大利亚研究理事会;
关键词
AI; data science; data analytics; advanced analytics; machine learning; statistics; mathematics; modeling; finance; economics; FinTech; AI in FinTech; AI in finance; smart FinTech; ARTIFICIAL NEURAL-NETWORKS; FOREIGN-EXCHANGE RATES; TIME-SERIES; BEHAVIORAL FINANCE; STOCK-MARKET; DATA SCIENCE; CORPORATE GOVERNANCE; DECISION-SUPPORT; PREDICTION; OPTIMIZATION;
D O I
10.1145/3502289
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
AI in finance refers to the applications of AI techniques in financial businesses. This area has attracted attention for decades, with both classic and modern AI techniques applied to increasingly broader areas of finance, economy, and society. In contrast to reviews on discussing the problems, aspects, and opportunities of finance benefited from specific or some new-generation AI and data science (AIDS) techniques or the progress of applying specific techniques to resolving certain financial problems, this review offers a comprehensive and dense landscape of the overwhelming challenges, techniques, and opportunities of AIDS research in finance over the past decades. The challenges of financial businesses and data are first outlined, followed by a comprehensive categorization and a dense overview of the decades of AIDS research in finance. We then structure and illustrate the data-driven analytics and learning of financial businesses and data. A comparison, criticism, and discussion of classic versus modern AIDS techniques for finance follows. Finally, the open issues and opportunities to address future AIDS-empowered finance and finance-motivated AIDS research are discussed.
引用
收藏
页数:38
相关论文
共 189 条
  • [1] A synchronous deep reinforcement learning model for automated multi-stock trading
    AbdelKawy, Rasha
    Abdelmoez, Walid M.
    Shoukry, Amin
    [J]. PROGRESS IN ARTIFICIAL INTELLIGENCE, 2021, 10 (01) : 83 - 97
  • [2] CREDIT SCORING, STATISTICAL TECHNIQUES AND EVALUATION CRITERIA: A REVIEW OF THE LITERATURE
    Abdou, Hussein A.
    Pointon, John
    [J]. INTELLIGENT SYSTEMS IN ACCOUNTING FINANCE & MANAGEMENT, 2011, 18 (2-3) : 59 - 88
  • [3] Deep Learning for Forecasting Stock Returns in the Cross-Section
    Abe, Masaya
    Nakayama, Hideki
    [J]. ADVANCES IN KNOWLEDGE DISCOVERY AND DATA MINING, PAKDD 2018, PT I, 2018, 10937 : 273 - 284
  • [4] Intelligent forecasting for financial time series subject to structural changes
    Ahn, Jae Joon
    Lee, Suk Jun
    Oh, Kyong Joo
    Kim, Tae Yoon
    [J]. INTELLIGENT DATA ANALYSIS, 2009, 13 (01) : 151 - 163
  • [5] Social media in marketing: A review and analysis of the existing literature
    Alalwan, Ali Abdallah
    Rana, Nripendra P.
    Dwivedi, Yogesh K.
    Algharabat, Raed
    [J]. TELEMATICS AND INFORMATICS, 2017, 34 (07) : 1177 - 1190
  • [6] Albashrawi M., 2016, J Data Sci, V14, P553
  • [7] Improving consistency in hierarchical tactical and operational planning using Robust Optimization
    Alvarez, Pamela P.
    Espinoza, Alejandra
    Maturana, Sergio
    Vera, Jorge
    [J]. COMPUTERS & INDUSTRIAL ENGINEERING, 2020, 139
  • [8] Corporate disclosure via social media: a data science approach
    Amin, Marian H.
    Mohamed, Ehab K. A.
    Elragal, Ahmed
    [J]. ONLINE INFORMATION REVIEW, 2020, 44 (01) : 278 - 298
  • [9] Variable-lag Granger Causality for Time Series Analysis
    Amornbunchornvej, Chainarong
    Zheleva, Elena
    Berger-Wolf, Tanya Y.
    [J]. 2019 IEEE INTERNATIONAL CONFERENCE ON DATA SCIENCE AND ADVANCED ANALYTICS (DSAA 2019), 2019, : 21 - 30
  • [10] [Anonymous], 2000, Data Mining in finance: Advances in Relational and Hybrid Methods