卢旺达移动支付中的洗钱检测：一种机器学习框架
Detecting Money Laundering in Rwandan Mobile Money: A Machine Learning Framework
浏览论文内容
中文总结 AI 辅助
本文针对卢旺达移动支付的极端类别不平衡等约束，开发并评估了符合当地AML/CFT制度的机器学习洗钱检测框架，为非洲移动支付监管机构提供了实用的治理感知监控方案。
中文摘要 AI 辅助
移动支付扩大了撒哈拉以南非洲的金融覆盖范围，但也为洗钱和恐怖主义融资（ML/TF）活动提供了更大的空间，这类活动集中在大量低价值交易的生态系统中。卢旺达就是一个典型例子：该国拥有数百万活跃移动支付用户，MTN和Airtel网络运营的电信钱包，以及金融情报中心（FIC）对交易流进行监督，其规模超出了基于静态规则的监控能力。本文开发并评估了符合卢旺达反洗钱/打击恐怖主义融资（AML/CFT）制度的交易监控框架，该框架需应对三个挑战：（i）极端类别不平衡（患病率约0.1%），（ii）标签稀缺且滞后，（iii）调查人员能力有限。我们使用SAML-D（包含9504852笔交易、17种洗钱类型的合成数据集），构建以账户为中心的行为特征（滚动流速、净流方向、交易对手多样性、突发性），并对监督分类器（逻辑回归、随机森林、LightGBM）、无监督异常检测器（孤立森林、局部异常因子）、密集自动编码器及后期融合元学习器进行基准测试。评估采用实用指标：PR-AUC、校准后约90%准确率下的召回率、前K%的召回率、每万笔交易的警报数。在按时间划分的保留测试期内，LightGBM的PR-AUC为0.0469，在约0.89的准确率下捕获64起洗钱案件，每万笔交易产生0.51个警报；融合堆叠器的PR-AUC达0.0477，准确率约0.91，每万笔交易产生0.46个警报，找回59个真正例。我们将评分区间映射到卢旺达相关分析师工作流程和可疑交易报告（STR/SAR）升级流程，并概述了从合成原型到与卢旺达国家银行和FIC合作进行真实数据验证的分阶段路径。本文的贡献在于实用性：一个符合治理要求的流程和评估协议，针对非洲移动支付监管机构的约束条件进行校准，而非提出新算法。
英文摘要
Mobile money has widened financial access across Sub-Saharan Africa and enlarged the surface for money-laundering and terrorism-financing (ML/TF) activity in ecosystems dominated by high-volume, low-value transactions. Rwanda is a case in point: several million active mobile-money users, telecom-led wallets on the MTN and Airtel networks, and a Financial Intelligence Centre (FIC) supervising transaction streams whose scale exceeds static rule-based monitoring. This paper develops and evaluates a transaction-monitoring framework aligned to the Rwandan AML/CFT regime under (i) extreme class imbalance (~0.1% prevalence), (ii) scarce and delayed labels, and (iii) bounded investigator capacity. Using SAML-D, a synthetic dataset of 9,504,852 transactions with 17 laundering typologies, we engineer account-centric behavioural features (rolling velocity, net-flow directionality, counterparty diversity, burstiness) and benchmark supervised classifiers (Logistic Regression, Random Forest, LightGBM), unsupervised anomaly detectors (Isolation Forest, Local Outlier Factor), a dense autoencoder, and a late-fusion meta-learner. Evaluation is operational: PR-AUC, recall at a calibrated ~90%-precision point, recall at top-K%, and alerts per 10,000. On the chronologically held-out test period, LightGBM attains PR-AUC = 0.0469, capturing 64 laundering cases at precision ~0.89 with 0.51 alerts per 10,000; the fusion stacker reaches PR-AUC = 0.0477 at precision ~0.91 and 0.46 alerts per 10,000, recovering 59 true positives. We map score bands to Rwanda-relevant analyst workflows and STR/SAR escalation, and outline a staged path from synthetic prototyping to real-data validation with the National Bank of Rwanda and FIC. The contribution is operational: a governance-aware pipeline and evaluation protocol calibrated to the constraints of an African mobile-money regulator, not a new algorithm.
发表机构
- African Institute for Mathematical Sciences (AIMS)（非洲数学科学研究所（AIMS））
- AI Research and Innovation Nexus for Africa (AIRINA Labs)（非洲人工智能研究与创新纽带（AIRINA Labs））
- Sefako Makgatho Health Sciences University（塞法科·马加托健康科学大学）
机构由 AI 辅助整理，请以论文原文为准。
