Similar articles

Abstract: artificial intelligence (AI) is the core technology of technological revolution and industrial transformation. As one of the new intelligent needs in the AI 2.0 era, financial intelligence has elicited much attention from the academia and industry. In our current dynamic capital market, financial intelligence demonstrates a fast and accurate machine learning capability to handle complex data and has gradually acquired the potential to become a “financial brain.” In this paper, we survey existing studies on financial intelligence. First, we describe the concept of financial intelligence and elaborate on its position in the financial technology field. Second, we introduce the development of financial intelligence and review state-of-the-art techniques in wealth management, risk management, financial security, financial consulting, and blockchain. Finally, we propose a research framework called FinBrain and summarize four open issues, namely, explainable financial agents and causality, perception and prediction under uncertainty, risk-sensitive and robust decision-making, and multi-agent game and mechanism design. We believe that these research directions can lay the foundation for the development of AI 2.0 in the finance field.

金融大脑：当金融遇见AI 2.0

[1]Abdou HA, Tsafack MDD, Ntim CG, et al., 2016. Predicting creditworthiness in retail banking with limited scoring data. Knowl-Based Syst, 103:89-103.

[2]Aleskerov E, Freisleben B, Rao B, 1997. CARDWATCH: a neural network based database mining system for credit card fraud detection. Proc IEEE/IAFE Computational Intelligence for Financial Engineering, p.220-226.

[3]Andreas J, Rohrbach M, Darrell T, et al., 2016. Learning to compose neural networks for question answering. https://arxiv.org/abs/1601.01705

[4]Angelini E, di Tollo G, Roli A, 2008. A neural network approach for credit risk evaluation. Q Rev Econom Finan, 48(4):733-755.

[5]Bahrammirzaee A, 2010. A comparative survey of artificial intelligence applications in finance: artificial neural networks, expert system and hybrid intelligent systems. Neur Comput Appl, 19(8):1165-1195.

[6]Berant J, Chou A, Frostig R, et al., 2013. Semantic parsing on freebase from question-answer pairs. Proc Conf on Empirical Methods in Natural Language Processing, p.1533-1544.

[7]Bolton RJ, Hand DJ, 2001. Unsupervised profiling methods for fraud detection. Proc Credit Scoring and Credit Control VII, p.5-7.

[8]Bordes A, Chopra S, Weston J, 2014. Question answering with subgraph embeddings. https://arxiv.org/abs/1406.3676

[9]Bordes A, Usunier N, Chopra S, et al., 2015. Large-scale simple question answering with memory networks. https://arxiv.org/abs/1506.02075

[10]Buterin V, 2014. A Next Generation Smart Contract & Decentralized Application Platform. Ethereum White Paper.

[11]Chow Y, Tamar A, Mannor S, et al., 2015. Risk-sensitive and robust decision-making: a CVaR optimization approach. https://arxiv.org/abs/1506.02188

[12]Dhingra B, Li LH, Li XJ, et al., 2016. End-to-end reinforcement learning of dialogue agents for information access. https://arxiv.org/abs/1609.00777

[13]Dineshreddy V, Gangadharan GR, 2016. Towards an “Internet of Things” framework for financial services sector. Proc 3^rd Int Conf on Recent Advances in Information Technology, p.177-181.

[14]Ding X, Zhang Y, Liu T, et al., 2015. Deep learning for event-driven stock prediction. Proc 24^th Int Conf on Artificial Intelligence, p.2327-2333.

[15]Dong L, Wei FR, Zhou M, et al., 2015. Question answering over freebase with multi-column convolutional neural networks. Proc 53^rd Annual Meeting of the Association for Computational Linguistics and the 7^th Int Joint Conf on Natural Language Processing, p.260-269.

[16]Etzioni O, 2011. Search needs a shake-up. Nature, 476(7358): 25-26.

[17]Graves A, Wayne G, Reynolds M, et al., 2016. Hybrid computing using a neural network with dynamic external memory. Nature, 538(7626):471-476.

[18]Grover A, Leskovec J, 2016. node2vec: scalable feature learning for networks. Proc 22^nd ACM SIGKDD Int Conf on Knowledge Discovery and Data Mining, p.855-864.

[19]Guo HF, Tang RM, Ye YM, et al., 2017. DeepFM: a factorization-machine based neural network for CTR prediction. https://arxiv.org/abs/1703.04247

[20]Ha VS, Nguyen HN, 2016. Credit scoring with a feature selection approach based deep learning. MATEC Web of Conf, Article 54.

[21]Hamrick JB, Ballard AJ, Pascanu R, et al., 2017. Metacontrol for adaptive imagination-based optimization. https://arxiv.org/abs/1705.02670

[22]Han L, Han LY, Zhao HW, 2013. Orthogonal support vector machine for credit scoring. Eng Appl Artif Intell, 26(2): 848-862.

[23]He X, Liao L, Zhang H, et al., 2017. Neural collaborative filtering. Proc 26^th Int Conf on World Wide Web, p.173-182.

[24]Heaton JB, Polson NG, Witte JH, 2016a. Deep learning in finance. https://arxiv.org/abs/1602.06561

[25]Heaton JB, Polson NG, Witte JH, 2016b. Deep portfolio theory. https://arxiv.org/abs/1605.07230

[26]Hoofnagle CJ, 2014. How the fair credit reporting act regulates big data. Future of Privacy Forum Workshop on Big Data and Privacy: Making Ends Meet.

[27]Jiang ZY, Xu DX, Liang JJ, 2017. A deep reinforcement learning framework for the financial portfolio management problem. https://arxiv.org/abs/1706.10059

[28]Kedia S, Monga EG, 2017. Static signature matching using LDA and artificial neural networks. Int J Adv Res Ideas Innov Technol, 3(3):245-248.

[29]Khandani AE, Kim AJ, Lo AW, 2010. Consumer credit-risk models via machine-learning algorithms. J Bank Finan, 34(11):2767-2787.

[30]Khashman A, 2010. Neural networks for credit risk evaluation: investigation of different neural models and learning schemes. Expert Syst Appl, 37(9):6233-6239.

[31]Kuang ZH, Huang C, Zhang W, 2015. Deeply learned rich coding for cross-dataset facial age estimation. IEEE Int Conf on Computer Vision Workshop, p.338-343.

[32]Kumar PR, Ravi V, 2007. Bankruptcy prediction in banks and firms via statistical and intelligent techniques—a review. Eur J Oper Res, 180(1):1-28.

[33]Li JW, Monroe W, Shi TL, et al., 2017. Adversarial learning for neural dialogue generation. https://arxiv.org/abs/1701.06547

[34]Li XJ, Lipton ZC, Dhingra B, et al., 2016. A user simulator for task-completion dialogues. https://arxiv.org/abs/1612.05688

[35]Li XJ, Chen YN, Li LH, et al., 2017. End-to-end task-completion neural dialogue systems. https://arxiv.org/abs/1703.01008

[36]Micali S, 2016. ALGORAND: the efficient and democratic ledger. https://arxiv.org/abs/1607.01341

[37]Min SH, Lee J, Han I, 2006. Hybrid genetic algorithms and support vector machines for bankruptcy prediction. Expert Syst Appl, 31(3):652-660.

[38]Nakamoto S, 2009. Bitcoin: a Peer-to-Peer Electronic Cash System. Bitcoin White Paper.

[39]Olson DL, Delen D, Meng YY, 2012. Comparative analysis of data mining methods for bankruptcy prediction. Dec Support Syst, 52(2):464-473.

[40]Pan YH, 2016. Heading toward artificial intelligence 2.0. Engineering, 2(4):409-413.

[41]Parkes DC, Wellman MP, 2015. Economic reasoning and artificial intelligence. Science, 349(6245):267-272.

[42]Reed SL, 2014. Bitcoin cooperative proof-of-stake. https://arxiv.org/abs/1405.5741

[43]Ribeiro LFR, Savarese PHP, Figueiredo DR, 2017. struc2vec: learning node representations from structural identity. https://arxiv.org/abs/1704.03165

[44]Rosenfeld M, 2014. Analysis of hashrate-based double spending. https://arxiv.org/abs/1402.2009

[45]Rushin G, Stancil C, Sun MY, et al., 2017. Horse race analysis in credit card fraud—deep learning, logistic regression, and gradient boosted tree. Systems and Information Engineering Design Symp, p.117-121.

[46]Salinas D, Gasthaus J, Flunkert V, 2017. DeepAR: probabilistic forecasting with autoregressive recurrent networks. https://arxiv.org/abs/1704.04110

[47]Shen WW, Wang J, 2016. Portfolio blending via Thompson sampling. Proc 25^th Int Joint Conf on Artificial Intelligence, p.1983-1989.

[48]Shen WW, Wang J, Jiang YG, et al., 2015. Portfolio choices with orthogonal bandit learning. Proc 24^th Int Conf on Artificial Intelligence, p.974-980.

[49]Shum HY, He XD, Li D, 2018. From Eliza to XiaoIce: challenges and opportunities with social chatbots. Front Inform Technol Electron Eng, 19(1):10-26.

[50]Stoica I, Song D, Popa RA, et al., 2017. A Berkeley view of systems challenges for AI. https://arxiv.org/abs/1712.05855

[51]Sun Y, Wang XG, Tang XO, 2014a. Deep learning face representation by joint identification-verification. https://arxiv.org/abs/1406.4773

[52]Sun Y, Wang XG, Tang XO, 2014b. Deep learning face representation from predicting 10,000 classes. IEEE Conf on Computer Vision and Pattern Recognition, p.1891-1898.

[53]Taigman Y, Yang M, Ranzato M, et al., 2014. DeepFace: closing the gap to human-level performance in face verification. IEEE Conf on Computer Vision and Pattern Recognition, p.1701-1708.

[54]Wang F, Zhou JY, Chen D, et al., 2017. Research on mobile commerce payment management based on the face biometric authentication. Int J Mob Commun, 15(3):278-305.

[55]Yeh CC, Lin FY, Hsu CY, 2012. A hybrid KMV model, random forests and rough set theory approach for credit rating. Knowl-Based Syst, 33:166-172.

[56]Yih WT, Chang MW, He XD, et al., 2015. Semantic parsing via staged query graph generation: question answering with knowledge base. Proc 53^rd Meeting of the Association for Computational Linguistics and the 7^th Int Joint Conf on Natural Language Processing, p.1321-1331.

[57]Zhang S, Yao LN, Sun AX, et al., 2017. Deep learning based recommender system: a survey and new perspectives. ACM Comput Surv, 52(1), Article 5.

[58]Zhang YZ, Liu K, He SZ, et al., 2016. Question answering over knowledge base with neural attention combining global knowledge information. https://arxiv.org/abs/1606.00979

[59]Zhao HK, Wu L, Liu Q, et al., 2014. Investment recommendation in P2P lending: a portfolio perspective with risk management. IEEE Int Conf on Data Mining, p.1109-1114.

[60]Zhao HK, Liu Q, Wang GF, et al., 2016. Portfolio selections in P2P lending: a multi-objective perspective. Proc 22^nd ACM SIGKDD Int Conf on Knowledge Discovery and Data Mining, p.2075-2084.

[61]Zhou J, Li XL, Zhao PL, et al., 2017. KunPeng: parameter server based distributed learning systems and its applications in Alibaba and Ant Financial. Proc 23^rd ACM SIGKDD Int Conf on Knowledge Discovery and Data Mining, p.1693-1702.

[62]Zhou H, Chai HF, Qiu ML, 2018. Fraud detection within bankcard enrollment on mobile device based payment using machine learning. Front Inform Technol Electron Eng, 19(12):1537-1545.