Canhoto Ana Isabel
Brunel Business School, Brunel University London, Kingston Lane, Uxbridge, Middlesex UB8 3PH, United Kingdom.
J Bus Res. 2021 Jul;131:441-452. doi: 10.1016/j.jbusres.2020.10.012. Epub 2020 Oct 17.
Financial services organisations facilitate the movement of money worldwide, and keep records of their clients' identity and financial behaviour. As such, they have been enlisted by governments worldwide to assist with the detection and prevention of money laundering, which is a key tool in the fight to reduce crime and create sustainable economic development, corresponding to Goal 16 of the United Nations Sustainable Development Goals. In this paper, we investigate how the technical and contextual affordances of machine learning algorithms may enable these organisations to accomplish that task. We find that, due to the unavailability of high-quality, large training datasets regarding money laundering methods, there is limited scope for using supervised machine learning. Conversely, it is possible to use reinforced machine learning and, to an extent, unsupervised learning, although only to model unusual financial behaviour, not actual money laundering.
金融服务机构促进资金在全球范围内的流动，并记录客户的身份和金融行为。因此，全球各国政府都已招募它们来协助侦查和预防洗钱活动，洗钱是减少犯罪和创造可持续经济发展斗争中的一项关键手段，这与联合国可持续发展目标的目标16相对应。在本文中，我们研究机器学习算法的技术和情境可供性如何使这些机构能够完成该任务。我们发现，由于缺乏关于洗钱方法的高质量、大型训练数据集，使用监督式机器学习的空间有限。相反，可以使用强化机器学习，在一定程度上也可以使用无监督学习，不过只能用于对异常金融行为进行建模，而不是实际的洗钱活动。
