Towards Artificial Intelligence Enabled Financial Crime Detection

Rouhollahi, Zeinab

doi:10.48550/arxiv.2105.10866

Cited by 3 publications

(3 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A straightforward option is to set scenario-specific constraints to the maximum possible decrease in true-positive alerts or use a concave utility function for the true-positive alerts to smooth the number of alerts across scenarios. Finally, there is consensus among AML experts that the number of false positives in a traditional rule-based system can be considerably decreased by using an appropriate clustering (Symphony AyasdiAI, 2022;Gupta et al, 2021;Protiviti Risk&Business Consulting, 2013;Rouhollahi, 2021). A clustering can be considered as good if the rate of false-positive alerts in the clusters shows large differences.…”

Section: Further Refinementsmentioning

confidence: 99%

Integral representation method based efficient rule optimizing framework for anti-money laundering

Badics

Hajtó

Tornai

et al. 2022

JMLC

View full text Add to dashboard Cite

Purpose This paper aims to introduce a framework for optimizing rule-based anti-money laundering systems with a clear economic interpretation, and the authors introduce the integral representation method. Design/methodology/approach By using a microeconomic model, the authors reformulate the threshold optimization problem as a decision problem to gain insights from economics regarding the main properties of the optimum. The authors used algorithmic considerations to find an efficient implementation by using a kind of weak mode estimate of the distribution and the authors extend this approach to classes of alerts or cases. Findings The method provides a new and efficient alternative for the sampling method or the multidimensional optimization technique described in the literature to decrease the bias emanating from multiple alerts by smoothing the number of alerts across classes in the optimum and decrease the overlapping between scenarios at the case level. Using the method for real bank data, the authors were able to decrease the number of false positives cases by about 18% while retaining almost 98% of the true-positive cases. Research limitations/implications The model assumes that alerts from different scenarios are indifferent to the bank. To include scenario-specific preferences or constraints demands further research. Originality/value The new framework presented in the paper is a flexible extension of the usual above-the-line method, which makes it possible to include bank preferences and use the parallelization capabilities of modern processors.

show abstract

Section: Further Refinementsmentioning

confidence: 99%

Integral representation method based efficient rule optimizing framework for anti-money laundering

Badics

Hajtó

Tornai

et al. 2022

JMLC

View full text Add to dashboard Cite

show abstract

“…So, there are lots of challenges and open questions [53]; For these reasons we were begins to work in this paper. Starting from the base of AI's capacity to classify various crime types and understand them, a truly exhaustive analysis is laid out [54]. AI is enabled by crime codes, descriptions and modus operandi to examine the nuanced morphology of the crimes.…”

Section: Introductionmentioning

confidence: 99%

Using Information Technology for Comprehensive Analysis and Prediction in Forensic Evidence

Mihna,

Habeeb,

Khaleel

et al. 2024

Mesopotamian Journal of CyberSecurity

View full text Add to dashboard Cite

With the escalation of cybercriminal activities, the demand for forensic investigations into these crimeshas grown significantly. However, the concept of systematic pre-preparation for potential forensicexaminations during the software design phase, known as forensic readiness, has only recently gainedattention. Against the backdrop of surging urban crime rates, this study aims to conduct a rigorous andprecise analysis and forecast of crime rates in Los Angeles, employing advanced Artificial Intelligence(AI) technologies. This research amalgamates diverse datasets encompassing crime history, varioussocio-economic indicators, and geographical locations to attain a comprehensive understanding of howcrimes manifest within the city. Leveraging sophisticated AI algorithms, the study focuses on scrutinizingsubtle periodic patterns and uncovering relationships among the collected datasets. Through thiscomprehensive analysis, the research endeavors to pinpoint crime hotspots, detect fluctuations infrequency, and identify underlying causes of criminal activities. Furthermore, the research evaluates theefficacy of the AI model in generating productive insights and providing the most accurate predictionsof future criminal trends. These predictive insights are poised to revolutionize the strategies of lawenforcement agencies, enabling them to adopt proactive and targeted approaches. Emphasizing ethicalconsiderations, this research ensures the continued feasibility of AI use while safeguarding individuals'constitutional rights, including privacy. The anticipated outcomes of this research are anticipated tofurnish actionable intelligence for law enforcement, policymakers, and urban planners, aiding in theidentification of effective crime prevention strategies. By harnessing the potential of AI, this researchcontributes to the promotion of proactive strategies and data-driven models in crime analysis andprediction, offering a promising avenue for enhancing public security in Los Angeles and othermetropolitan areas.

show abstract

“…Several studies regarding AI of financial: AI as an innovative model for predicting risks in financial institutions (Kasztelnik, 2020); AI as a model for identifying distortions in financial applications (Asl et al, 2021); AI as an application for assessing credit risk (Mhlanga, 2021); application of AI to predict financial market trading (Cohen, 2022) and stock prices (Shahpazov et al, 2014); the role of AI in human resource management and development (Tiwari et al, 2022); AI system to predict financial risk in the banking sector (Lomakin et al, 2022); and the role of AI in detecting financial crimes (Rouhollahi, 2021).…”

Section: Introductionmentioning

confidence: 99%

Artificial Intelligence (AI) of Financial in the VUCA Era: A Systematic Mapping Study

Iryani

Yulianto

2023

CNAHPC

View full text Add to dashboard Cite

The purpose of the study was to systematically map Artificial Intelligence (AI) in the financial sector in the VUCA era. The research design employed a quantitative approach with a descriptive method. The study utilized a systematic literature review with bibliometric analysis techniques. Researchers collected the data from the Google Scholar database, technique analysis using VOSviewer, and descriptive statistics as data analysis techniques. The results indicated the following: (RQ1) 539 articles met the criteria for research; (RQ2) Springer was the publisher with the highest number of AI in Financial articles (58 articles); (RQ3) Karina Kasztelnik authored the most papers on AI in financial (3 documents); (RQ4) an article written by David Mhlanga titled "Industry 4.0 in Finance: The Impact of Artificial Intelligence (AI) on Digital Financial Inclusion" had the most citations (145 citations); and (RQ5) the systematic mapping results identified 8 clusters as research gaps, suggesting potential themes for future studies related to AI in the financial domain. The findings indicate a research gap and highlight the potential for further research on AI in the financial sector in the VUCA era. The role of AI in the financial industry in the VUCA era was to enhance efficiency, speed, accuracy, and security. AI can assist in addressing rapidly emerging complex challenges, providing competitive advantages for FinTech companies to navigate dynamic changes and uncertain business environments.

show abstract

Towards Artificial Intelligence Enabled Financial Crime Detection

Cited by 3 publications

References 61 publications

Integral representation method based efficient rule optimizing framework for anti-money laundering

Integral representation method based efficient rule optimizing framework for anti-money laundering

Using Information Technology for Comprehensive Analysis and Prediction in Forensic Evidence

Artificial Intelligence (AI) of Financial in the VUCA Era: A Systematic Mapping Study

Contact Info

Product

Resources

About