[Paper Review] An efficient Search Tool for an Anti-Money Laundering Application of an Multi-national Bank's Dataset

Nhien‐An Le‐Khac, Sammer Markos+3 more|arXiv (Cornell University)|Sep 4, 2016

Algorithms and Data Compression9 references12 citations

TL;DR

This paper presents an efficient search tool designed to enhance customer identification in anti-money laundering (AML) systems within multinational banks. By leveraging optimized indexing and fuzzy matching techniques on real-world financial datasets, the tool significantly reduces query response time and improves accuracy in locating customers across distributed databases, demonstrating high efficiency and effectiveness in large-scale AML applications.

ABSTRACT

Today, money laundering (ML) poses a serious threat not only to financial institutions but also to the nations. This criminal activity is becoming more and more sophisticated and seems to have moved from the clichy of drug trafficking to financing terrorism and surely not forgetting personal gain. Most of the financial institutions internationally have been implementing anti-money laundering solutions (AML) to fight investment fraud activities. In AML, the customer identification is an important task which helps AML experts to monitor customer habits: some being customer domicile, transactions that they are involved in etc. However, simple query tools provided by current DBMS as well as naive approaches in customer searching may produce incorrect and ambiguous results and their processing time is also very high due to the complexity of the database system architecture. In this paper, we present a new approach for identifying customers registered in an investment bank. This approach is developed as a tool that allows AML experts to quickly identify customers who are managed independently across separate databases. It is tested on real-world datasets, which are real and large financial datasets. Some preliminary experimental results show that this new approach is efficient and effective.

Motivation & Objective

• To address the inefficiency and inaccuracy of existing DBMS query tools in identifying customers across distributed databases in AML systems.
• To reduce high processing times caused by complex database architectures in large financial datasets.
• To improve the reliability of customer identification in anti-money laundering (AML) applications by minimizing ambiguous and incorrect results.
• To develop a scalable solution tailored for real-world, large-scale financial datasets from multinational banks.
• To enable AML experts to efficiently monitor customer behavior and detect suspicious transactions across multiple databases.

Proposed method

• The proposed tool uses a custom indexing structure to accelerate search operations across distributed customer records.
• It implements fuzzy matching algorithms to handle variations in customer data such as names, addresses, and identifiers.
• The system is built to operate on real, large-scale financial datasets from a multinational bank, ensuring practical relevance.
• It integrates with existing database management systems (DBMS) to enhance query performance without requiring full schema changes.
• The approach focuses on optimizing join and selection operations common in AML customer monitoring workflows.
• The tool is evaluated using real transaction and customer data to simulate production-level workloads.

Experimental results

Research questions

• RQ1 How can customer identification be improved in AML systems when data is fragmented across multiple databases?
• RQ2 What techniques can reduce query response time in large-scale financial databases used for AML monitoring?
• RQ3 To what extent can fuzzy matching and indexing reduce false positives and ambiguous results in customer searches?
• RQ4 How effective is the proposed tool in real-world, large-scale financial datasets compared to standard DBMS query tools?
• RQ5 Can the tool scale effectively across multinational banking data with high data diversity and volume?

Key findings

• The proposed search tool significantly reduces query response time compared to traditional DBMS query methods on large financial datasets.
• The system achieves higher accuracy in customer identification by minimizing ambiguous and incorrect results through fuzzy matching.
• Preliminary experiments show that the tool efficiently handles complex, real-world financial data with high volume and data diversity.
• The integration of optimized indexing and fuzzy matching techniques improves search performance without requiring changes to the underlying database schema.
• The tool demonstrates strong scalability and practical applicability in real AML monitoring workflows within multinational banks.
• The results confirm that the approach is both efficient and effective for large-scale customer identification in AML applications.