Predicting credit card delinquencies: An application of deep neural networks

The objective of this paper is twofold. First, it develops a prediction system to help the credit card issuer model the credit card delinquency risk. Second, it seeks to explore the potential of deep learning (also called a deep neural network), an emerging artificial intelligence technology, in the credit risk domain. With real-life credit card data linked to 711,397 credit card holders from a large bank in Brazil, this study develops a deep neural network to evaluate the risk of credit card delinquency based on the client's personal characteristics and the spending behaviours. Compared with machine-learning algorithms of logistic regression, naive Bayes, traditional artificial neural networks, and decision trees, deep neural networks have a better overall predictive performance with the highest F scores and area under the receiver operating characteristic curve. The successful application of deep learning implies that artificial intelligence has great potential to support and automate credit risk assessment for financial institutions and credit bureaus.     

Shifts in consumer behavior towards organic products: Theory-driven data analytics

Consumer behavior is key in shifts towards organic products. A diversity of factors influences consumer preferences, driving planned, impulsive, and unplanned purchasing decisions. We study choices among organic and conventional wine using an extensive survey among Australian consumers (N = 1003). We integrate five behavioral theories in the survey design, and use supervised and unsupervised machine learning algorithms for analysis. We quantify a gap between intention and behavior, and emphasize the importance of cognitive factors. Findings go beyond correlation to the causation of behavior when combining predictive prowess with explanatory power. Results reveal that affective factors and normative cues may prompt unplanned and spontaneous purchasing behavior, causing consumers to act against their beliefs.     

基于人工神经网络的互联网公司估值方法研究

资本市场认为互联网公司市值的驱动因素应包括盈利因子、运营因子、流量因子和协同因子。将协同效应指标考虑到公司估值体系中,意图构造互联网公司优化估值模型。使用美股上市的互联网企业数据建立了评价指标体系,通过因子分析实现了二级指标降维,通过实证分析确认了四个因子与公司市值的相关关系,最后构建了基于人工神经网络BP算法的互联网公司估值模型,通过预测数据的检验发现模型的准确度较高。随着2018年互联网公司美股上市潮的持续,该模型能有效为资本市场估值提供参考。     

人工智能背景下会计人才教育模式改革研究

在人工智能高速发展的时代,会计人工智能应运而生。会计人工智能以其高效、精确、低成本的特点迅速取代基础会计工作人员的工作。在此背景下,国内会计人才教育该何去何从,文章将从会计教育模式现状入手,结合人工智能对会计的影响,以会计教育侧重点、会计人才的职业道德建设等方面为切入点,探讨会计人才教育模式改革。     

基于BP人工神经网络中国光伏产业贸易摩擦预警研究

建立有效的贸易摩擦预警系统有利于中国新兴产业的健康发展,有利于中国实施制造强国战略。将警兆信号法与人工神经网络相结合,从宏观经济形势、产业供给能力、双边贸易状况、市场需求水平等四个维度切入,构建了中国光伏产品出口贸易摩擦预警系统模型。预警分析表明,模型的预警效果与现实拟合较好,具有可行性。从模型的预警结果来看,2019年~2020年中国输美光伏产品贸易摩擦警情均低于轻警级别,仍面临一定的贸易摩擦风险。     

人工智能技术变革对国际贸易的影响

人工智能技术的快速发展正催生第四次工业革命,可能引发全球价值链深度重构和世界经贸格局重大变革。世界主要经济强国将发展人工智能技术作为争夺新一轮产业竞争优势的重要战略抓手。本文基于全球价值链视角研究人工智能技术变革对国际贸易的影响,我们发现人工智能技术变革可能推动国际贸易规模扩大,提升服务贸易份额,并促进国际贸易交易模式平台化、小宗化,可为中小企业创造更多参与国际贸易的机会。然而,人工智能技术变革也可能通过降低企业劳动力需求从而对我国等发展中国家的出口拉动型增长模式造成严重的潜在威胁。为应对人工智能技术变革,我国应部署并强化对人工智能产业发展的政策支持,加快培育制造业国际竞争新优势,大力推动先进制造业与现代生产性服务业深度融合发展,全面促进"中国制造"攀升全球价值链中高端。     

人工智能在我国公共卫生建设中的应用与思考

新冠疫情的暴发以及长期防治对中国的公共卫生体系造成深远影响，给我国突发公共卫生事件应急与防控机制带来巨大的考验。在疫情防控的过程中，信息化技术为传统医疗机构带来瞩目的帮助与改变，人工智能、大数据、5G高速网络等新兴高科技的蓬勃发展在直接提升医疗水平方面表现出巨大潜力。本文就人工智能在疫情期间的医疗辅助功能展开讨论，并对未来我国公共卫生体系的建设进行了思考。     

Exploring the knowledge spillovers of a technology in an entrepreneurial ecosystem—The case of artificial intelligence in Sydney

New knowledge presents opportunities for commercial value and can hence be a critical asset for entrepreneurial ecosystems (EEs). In particular, general purpose technologies are major drivers of entrepreneurship. Thus, a nuanced understanding on technological knowledge and its spillovers among actors within an EE is warranted. Using knowledge‐spillover‐based strategic entrepreneurship theory, we propose to observe knowledge spillovers through the assessment of the knowledge bases of a technology in an EE. To do so, this article proposes to use three key sources of knowledge: publications reflecting the emerging knowledge base, patents representing the realized knowledge base, and startups showing the experimental knowledge base. This article uses secondary data sources such as Web of Science and applies the method of bibliometrics to illustrate how an assessment is carried out in practice by evaluating the artificial intelligence (AI) knowledge bases in Sydney from 2000 to 2018. The findings are summarized with an illustration of the evolution of the key actors and their activities over time in order to indicate the key strengths and weaknesses in Sydney's AI knowledge among the different bases. Contrary to expectations from the high potential of knowledge spillovers from a general purpose digital technology such as AI, the article shows that apparent knowledge spillovers are yet highly limited in Sydney. Even though Sydney has a strong emerging knowledge base, the realized knowledge base seems weak and the experimental knowledge base is slowly improving. That observation itself verifies the need to take strategic actions to facilitate knowledge spillovers within EEs. After the implications for theory and policy makers are discussed, suggestions for further studies are proposed.     

人工智能技术辅助开发“智铸”系统

采用开源免费的深度学习平台,利用python二次开发了“智铸”系统,包括“识铸”“听铸”“盯铸”三个模块,铸造企业员工可以用手机或电脑自主学习,提升员工从业能力。在设备旁安装“听铸”软硬件一体化设备,可以实现对连续运行设备的在线自动监听侦测。“盯铸”模块实现连续生产铸件的自动检测、铸造缺陷分析与重点安全区域的监控。