Introduction
FinTech (or Fintech), or financial technology, is at the epicentre of synergizing, innovating and transforming financial services, economy, technology, media, and telecommunication. FinTech nurtures new economic and financial (EcoFin) mechanisms, models, products, services, and opportunities. FinTech also strengthens existing system efficiency, cost-effectiveness, customer experience, risk mitigation, regulation, and security.

AI and data science (AIDS) is the keystone enabler of FinTech and new-generation finance, economics (economy) and society [1-4]. AIDS essentially and comprehensively transforms the way and effect financial businesses operate, transact, interact and collaborate with their consumers, markets, and regulators. AIDS innovates new and intelligent FinTech for more efficient, convenient, personalized, explainable, secure and proactive financial products and services. To achieve these, on one hand, AIDS technologies including knowledge representation, machine learning, pattern recognition, signal processing, data analytics, computer vision, natural language processing, biometrics, and computational intelligence evolve to cultivate FinTech. On the other, FinTech is driving new AIDS research and innovation.

 
Research Topics

The research topics include but are not limited to the following areas:

• Analyzing complex couplings, dependencies, interactions, relations and networking in finance
• Analyzing regional and global financial activities, behaviors, events and their impact and risk
• Analyzing and representation of financial businesses, networks, systems and problems
• Jointly modelling natural, online, social, economic, cultural and political factors in finance
• Analyzing and learning multisource, multimodal and heterogeneous financial events and impact
• Analyzing and modeling high-dimensional, sequential and evolving financial events and impact
• Constructing benchmarkable financial knowledge graph and repositories
• AI for faster, cheaper and smarter design, simulation and evaluation of new financial mechanisms, models, products and services
• Real-time intelligent financial analysis and processing for cloud, online and mobile services
• AI-enabled regtech for digital authentication and identification and intelligent regulation
• AI for active, real-time, tailored and automated regulation of new, digital and mobile financial services
• AI to analyze, predict and intervene new cybersecurity, fraud and risks in banking, insurance and finance
• Cross-market, product, indicator, platform and network modelling, hologram and risk analysis
• Analyzing financial crisis, exception, emergence, uncertainty and ill- to un-structured systemic risk
• Data-driven theories and tools for digital assets and their valuation, risk analysis and management
• New blockchain theories and tools for cryptocurrency, digital asset pricing, trading, mechanism design, smart contract, open banking and investment
• Intelligent innovations in credit loans, SMEs and individual financing, P2P lending, crowdfunding, roboadvising, digital payment, dynamic credit rating, and asset pricing
• Intelligent algorithms, mechanisms, interfaces and systems for digital, mobile, virtual and Internet-based banking, financing, capital markets, regtech, insurtech, and paytech
• AI for assuring trust, privacy, security, compliance, explainability and ethics in FinTech
• Better practice and lessons of AI-enabled FinTech into implementation and productization
• Other important aspects, issues and progress associated with AI in FinTech

The following diagram shows a four-dimensional research landscape of AIDS in Finance [1,2].

Figure 1. A four-dimensional landscape of the synthesis between AIDS and EcoFin toward fostering smart FinTech. Shapes in different colors represent distinct dimensions in the synthetic landscape. Each dimension initiates its interactions and communications with the three other dimensions through its same-colored, directed connectors and channels. Each channel carries business, problem, data (incl. information and knowledge), intelligence, and technology, etc. from one end to another. The four dimensions interact with each other to address specific economic-financial business problems of underlying businesses by particular AIDS techniques on the corresponding data [1,2].

 
Market Compliance, Surveillance, Regulation and Risk Analytics

Market surveillance, compliance and regulation are to maintain and enhance the market integrity by monitoring the market movements as well as detecting and intervening any abnormal behaviors and activities in a market. Data and intelligence-driven risk analytics transform smart market surveillance, regulation and compliance enforcement increasingly widely taken by major stock exchanges, brokerage firms, and regulation bodies. AI and data science play a core role in enabling smart surveillance, regulation and compliance and assuring fair, efficient and transparent trading and investment.

Data and intelligence-driven smart market surveillance, regulation and compliance and risk analytics can be applied to various aspects and by any market participants including investors, regulators and designers, during the whole lifecyle of historical, present and future market operations, and for any forms of manipulations, insider trading, financial reviews, corporate auditing and accounting, etc.

• Real-time surveillance, regulation and compliance analysis and enhancement
• Historical event analysis, linkage analysis, evidence extraction, and scenario replay
• Insider trading characterization, detection and intervention
• Market benchmarking and standarization
• Evaluation and optimization of new market designs, mechanisms, and rules
• Detecting abnormal trading, regulation and listing, evaluation behaviors, disclosures, announcements
• Risk analytics and management of systemic risk, investment risk, operational risk, financial crisis, etc.
• Market replay of exceptional behaviors and scenarios
• Cross-market manipulation, illegal arbitrage, and financial crisis contagion
• Financial event, black swan/grey rhino event and disaster detection, analysis and intervention

Please also refer to the market surveillance website for relevant information, activities, and projects.

 
Trading, Portfolio Management and Algorithmic Trading

Trading can be automatically made by computerized algorithms, called algorithmic trading, and high-frequency trading has become a critical trading method and behavior in more and more markets. AI, machine learning and data science are crucial to identify positive trading signals, design trading strategies, and lodge and execute trading orders to markets with higher winning chances and profitability.

Data-driven smart portfolio investment and algorithmic trading discover positive trading strategies (trading rules) and portfolios for specific market conditions, investment methods and products, and purposes, e.g.:

• market making
• inter-market spreading
• statistical and event arbitrage
• cross-market trading
• pure speculation
• hedging
• pairs trading
• quote stuffing
• spoofing
• transaction cost reduction

 
Activities

• IJCAI2020 Special Track on AI in FinTech
• IEEE Intelligent Systems Special Issue on AI and FinTech
• DSAA’2020 Journal Track on Data Science and AI in FinTech
• ACM Conference on AI in Finance

 
Our Experience and References

We’ve involved in AI in finance and FinTech since 2002. Our interests cover topics and issues including data/evidence-driven market mechanism and movement modeling, market surveillance, portfolio management, algorithmic trading, risk management, cross-market analysis, and financial crisis analysis etc. with a focus on capital markets and their interactions with other markets. Our collaborators include stock exchanges, brokerage firms, and government regulation bodies. We’ve conducted various projects sponsored by the collaborators with some systems and algorithms deployed in the partner’s organizations. Several PhD these have been completed in these areas.

Some of our references related to broad-based AI in finance and FinTech:

• Overview and Review on AI in FinTech/Finance

  • [1] Longbing Cao. AI in Finance: A Review, pp. 1-36, 2020.

  • [2] Longbing Cao, Qiang Yang, Philip S. Yu. Data science and AI in FinTech: An overview, International Journal of Data Science and Analytics, 2021. JDSA, arXiv or SSRN, 1-19, 2021.

  • [3] Longbing Cao. AI in Finance: Challenges, Techniques and Opportunities, at SSRN or arXiv, pp. 1-40, 2021.

  • [4] Longbing Cao. AI in FinTech: A Research Agenda, pp. 1-10, 2020.

  • [5] Longbing Cao; George Yuan; Tim Leung; Wei Zhang. Special Issue on AI and FinTech: The Challenge Ahead, IEEE Intelligent Systems, 35(3): 3-6, 2020.

• (Cross-)Market Surveillance & Crisis/Risk Analytics

  • Wei Cao, Yves Demazeau, Longbing Cao, Weidong Zhu. Financial crisis and global market couplings. DSAA 2015: 1-10. BibTeX

  • Wei Cao, Longbing Cao. Financial Crisis Forecasting via Coupled Market State Analysis, IEEE Intelligent Systems, 30(2): 18-25 (2015). BibTeX

  • Wei Cao, Liang Hu, Longbing Cao. Deep Modeling Complex Couplings within Financial Markets, AAAI2015, 2518-2524. BibTeX

  • Wei Wei, Junfu Yin, Jinyan Li, Longbing Cao. Modeling Asymmetry and Tail Dependence among Multiple Variables by Using Partial Regular Vine. SDM 2014: 776-784. BibTeX

  • Wei Wei, Jinyan Li, Longbing Cao, Xixi Chen. Optimal Allocation of High Dimensional Assets through Canonical Vines, PAKDD 2013, 2013. BibTeX

  • Wei Cao, Longbing Cao, Yin Song. Coupled Market Behavior Based Financial Crisis Detection, IJCNN2013. BibTeX

  • Yin Song, Longbing Cao, et al. Coupled Behavior Analysis for Capturing Coupling Relationships in Group-based Market Manipulation, KDD 2012, 976-984. BibTeX

  • Yin Song and Longbing Cao. Graph-based Coupled Behavior Analysis: A Case Study on Detecting Collaborative Manipulations in Stock Markets, IJCNN 2012, 1-8. BibTeX

  • Longbing Cao, Yuming Ou, Philip S Yu. Coupled Behavior Analysis with Applications, IEEE Trans. on Knowledge and Data Engineering, 24(8): 1378-1392 (2012). BibTeX

  • Longbing Cao, Yuming Ou, Philip S YU, Gang Wei. Detecting Abnormal Coupled Sequences and Sequence Changes in Group-based Manipulative Trading Behaviors, KDD2010, 85-94. BibTeX

  • Yuming Ou, Longbing Cao, Chao Luo and Li Liu. Mining Exceptional Activity Patterns in Microstructure Data, WI2008. BibTeX

  • Yuming Ou, Longbing Cao, Chao Luo and Chengqi Zhang. Domain-Driven Local Exceptional Pattern Mining for Detecting Stock Price Manipulation, PRICAI2008, LNAI 5351, pp. 849-858, 2008. BibTeX

  • Chao Luo, Yanchang Zhao, Longbing Cao, Yuming Ou and Chengqi Zhang. Exception Mining on Multiple Time Series in Stock Market, WI-IAT 08 Workshops, pp. 690-693. BibTeX

  • Chao Luo, Yanchang Zhao, Longbing Cao, Yuming Ou and Li Liu. Outlier Mining on Multiple Time Series Data in Stock Market, PRICAI2008, pp. 1010-1015. BibTeX

  • Yuming Ou, Longbing Cao, Ting Yu, and Chengqi Zhang.Detecting Turning Points of Trading Price and Return Volatility for Market Surveillance Agents, ADMI2007 workshop joint with IAT2007. BibTeX

• (Cross-market) Portfolio Management & Algorithmic Trading

  • Guifeng Wang, Longbing Cao, Hongke Zhao, Qi Liu and Enhong Chen. Coupling Macro-Sector-Micro Financial Indicators for Learning. Stock Representations with Less Uncertainty, AAAI-21

  • Jia Xu, Longbing Cao. Vine Copula-based Asymmetry and Tail Dependence Modeling, PAKDD2018. BibTeX

  • Jia Xu, Wei Wei, Longbing Cao. Copula-Based High Dimensional Cross-Market Dependence Modeling, DSAA2017, 734-743. BibTeX

  • Wei Wei, Junfu Yin, Jinyan Li, Longbing Cao. Modeling Asymmetry and Tail Dependence among Multiple Variables by Using Partial Regular Vine. SDM 2014: 776-784. BibTeX

  • Longbing Cao and Tony He. Developing actionable trading agents, Knowledge and Information Systems: An International Journal, 18(2): 183-198 (2009). BibTeX

  • Wei Wei, Xuhui Fan, Jinyan Li, Longbing Cao. Model the Complex Dependence Structures of Financial Variables by Using Canonical Vine, CIKM 2012. BibTeX

  • Wei Cao, Cheng Wang and Longbing Cao. Trading Strategy Based Portfolio Selection for Actionable Trading Agents, ADMI 2012. BibTeX

  • Li Lin, Longbing Cao. Mining In-Depth Patterns in Stock Market, Int. J. Intelligent System Technologies and Applications, Vol.4, Nos.3/4, pp225-238, 2008. BibTeX

  • Longbing Cao Yuming Ou. Market Microstructure Patterns Powering Trading and Surveillance Agents. Journal of Universal Computer Sciences, 14(14): 2288-2308, 2008. BibTeX

  • Longbing Cao et al. Agent Collaboration for Multiple Trading Strategy Integration. KES-AMS2008, LNCS4953, 361-370. BibTeX

  • Longbing Cao, Chengqi Zhang. F-Trade: An Agent-Mining Symbiont for Financial Services, AAMAS2007. BibTeX

  • Longbing Cao. Multi-strategy integration for actionable trading agents. ADMI2007 workshop joint with IAT2007. BibTeX

  • Longbing Cao, Chao Luo, Chengqi Zhang. Developing actionable trading strategies for trading agents, IAT2007. BibTeX

  • Li Lin, Longbing Cao, Chengqi Zhang. The Visualization of Large Database in Stock Market. The 25th IASTED International Conference on Databases and Applications (DBA 2005), 2005. BibTeX

  • Li Lin, Longbing Cao, Chengqi Zhang. The Fish-eye Visualization of Foreign Currency Exchange Data Streams. The 4th Asia Pacific Symposium on Information Visualisation, Jan. 27-29, 2005 Sydney, Australia, 2005. BibTeX

  • Li Lin, Longbing Cao, Jiaqi Wang, Chengqi Zhang, The Applications of Genetic Algorithms in Stock Market Data Mining Optimisation, Proceedings of Fifth International Conference on Data Mining, Text Mining and their Business Applications, September 15-17, 2004, Malaga, Spain.