Skip to main content

Towards Effective Local Financial Cybercrime Detection using Machine Learning

Marouane Dirchaoui ; Abdallah Abarda (2024) — 2024 Mediterranean Smart Cities Conference (MSCC)

Citation activity

Total citations · Google Scholar
Unavailable
Average per calendar year
Citation count unavailable

Counts reflect Google Scholar’s coverage and do not measure research quality. Source, calculation and limitations

View Original Source (opens in a new tab)

DOI: 10.1109/mscc62288.2024.10696987 (opens in a new tab)

Country:   Morocco
Tags:   Dataset Access, Dating App Fraud Detection, Fake Profiles, Financial Cybercrime, Machine Learning, Model Generalizability, Morocco, Romance Scams
What do these research terms mean?
Preprint
A manuscript shared before formal peer review and publication. Check whether a later published version is available.
Dataset
A collection of data or examples for others to inspect or reuse. It can appear in Library search and topic mapping, but RSRC does not use dataset records as evidence in Research Insights.
Dissertation or thesis
Research submitted for an academic degree. This describes its format, not its reliability.
Journal article
An article published in a journal. This label alone does not establish peer review, study quality, or how well the findings apply elsewhere.
Qualitative research
Examines experiences, meanings, or processes, often through interviews or observations. It can explain how something happens without estimating how common it is.
Quantitative research
Uses numerical measurements to describe patterns or test relationships. A relationship between two measurements does not by itself show that one causes the other.
Systematic review
Uses a planned, documented method to find and assess research addressing a question. Its conclusions still depend on the included studies and what the search covered.
Meta-analysis
Statistically combines results from multiple studies. Combining studies does not remove weaknesses in their design or make unlike populations interchangeable.
Not classified
This record has no recognized label in this filter. It does not mean the publication used no method, or that no research exists.

Definitions draw on DataCite resource types; Cochrane review methods; NLM: association and causation. RSRC’s dataset and classification rules are explained in our methodology.

Citation tools
Download RIS Download BibTeX 


              
              

            

          

        


      

      

    

        
Transparency

        
Evidence and review status

        
This page contains AI-generated content. No human content review or subject-matter-expert review is recorded.

    


    

                    

                
Source basis

                

                    Downloaded PDF
                

            

                    

                
Source updates

                

                    No notice found at last check
                

            

                    

                
AI-generated page content

                

                    Yes
                

            

                    

                
Automated checks

                

                    Passed
                

            

                    

                
Administrative approval

                

                    Yes
                

            

                    

                
Human content review

                

                    Not recorded
                

            

                    

                
Subject-matter-expert review

                

                    Not recorded
                

            

            


    

        
            How this was prepared
        
        

                            

                    
Source basis

                    

                    
RSRC downloaded and privately stored a copy of the paper for internal analysis. The PDF is not offered to viewers from this page.


                                            
    
                                                            
  • 
                                    PDF added to RSRC:
                                    
                                
    • 
                                                    

                    
                                        

                

                            

                    
Source updates

                    

                    
No incoming update notice was found in the dated Crossref response. Coverage is incomplete, particularly for corrections and expressions of concern; this is not a guarantee that the source is valid or unchanged.


                                            
    
                                                            
  • 
                                    Last source-status attempt:
                                    
                                
    • 
                                                    

                    
                                        

                

                            

                    
AI-generated page content

                    

                    
AI-generated research notes displayed on this page: Synopsis, Identified gaps, Methods, Limitations, Future work. The paper itself is not described as AI-generated.


                                            
    
                                                            
  • 
                                    Document analysis recorded:
                                    
                                
    • 
                                                            
  • 
                                    Synopsis generation recorded:
                                    
                                
    • 
                                                            
  • 
                                    Page record updated:
                                    
                                
    • 
                                                    

                    
                                        

                

                            

                    
Automated checks

                    

                    
The current, source-bound synopsis passed the recorded versioned publication checks.


                                            
    
                                                            
  • 
                                    Checks completed:
                                    
                                
    • 
                                                    

                    
                                            

                            
                                View passed checks (3)
                            
                            
    
                                                                    
  • Length, completeness, repetition, refusal, boilerplate, and active-markup screening
    • 
                                                                    
  • Numerical claims checked against the available source text
    • 
                                                                    
  • English-source lexical grounding check
    • 
                                                            

                        

                                        

                

                            

                    
Administrative approval

                    

                    
An authenticated administrator approved the bibliographic record for public Library display. This is not a review of every research claim.


                                            
    
                                                            
  • 
                                    Approved for public display:
                                    
                                
    • 
                                                    

                    
                                        

                

                            

                    
Human content review

                    

                    
No human review is recorded for the AI-generated content displayed on this page.


                    
                                        

                

                            

                    
Subject-matter-expert review

                    

                    
RSRC has not recorded review of this content by a subject-matter or methods expert.


                    
                                        

                

                    

    


    

        Review-state definitions

        Found a possible error?
        Request a correction.
    



    



              

        
                  

            
Synopsis

            
This 2024 study by Dirchaoui and Abarda, presented at the Mediterranean Smart Cities Conference (MSCC), surveys how researchers have used machine learning to detect five financial cybercrimes at the local level: social engineering, romance fraud, pump-and-dump schemes, fake reviews, and money laundering. The authors frame the work as a comparative analysis intended to help researchers prioritize efforts based on the prevalence of each fraud type in different regions and the resources available. They position the local complexity of financial cybercrime as an open problem and emphasize data access and labeling as central challenges. The paper reviews a range of prior studies that apply machine learning to each crime type, discussing data sources, labeling practices, funding, and reported performance. It highlights how data collection often hinges on access to self-generated datasets, publicly available corpora, or compromised data from platforms, and notes issues such as imbalanced datasets and the need to demonstrate robustness across platforms and time. Several studies are described as using deep learning, ensemble, or unsupervised approaches, with varying degrees of transparency about methodologies and data sharing. The authors also summarize what factors researchers identify as relevant to performance, including data type, dataset size, labeling procedures, and whether data are publicly available. In conclusion, the authors acknowledge that although advances in ML offer promise, many studies do not report false-positive rates with enough detail, and generalizability to other locales or platforms remains uncertain. They call for more accessible datasets, transparent reporting, and attention to local context to improve practical detection of financial cybercrimes. These cautions frame a path toward more locally informed ML defenses.

          

        
                  

            
Identified Gaps

            
Accessible, representative datasets are lacking because financial-cybercrime data often contain sensitive personal or organizational information. Labeling is difficult for crimes requiring confirmation from multiple actors. Small datasets and limited confirmed fraud instances undermine generalizability, while novel fraud patterns and cross-platform variation can reduce model performance. Many reviewed studies also omit false-positive and false-negative reporting, limiting assessment of real-world deployment suitability.

          

        
                  

            
Methods

            
The paper comparatively reviews machine-learning studies addressing social engineering, romance fraud, pump-and-dump schemes, fake reviews, and money laundering. It tabulates each study's crime type, data collection, dataset size, labeling, imbalance, data availability, funding, results, and best model. The discussion synthesizes barriers involving data access, labeling, funding, generalizability, and false-positive and false-negative performance.

          

        
                  

            
Limitations

            
The comparison covers only five financial-cybercrime types and does not include all forms of financial cybercrime. Its conclusions are based on selected prior studies rather than a newly collected local dataset or direct evaluation of models. The paper also notes that small datasets, limited confirmed instances, and platform-specific training data can constrain the generalizability and deployment relevance of the reviewed models.

          

        
                  

            
Future Work

            
Broaden the comparison to include a more comprehensive range of financial cybercrimes, with the aim of providing deeper insights for locally effective detection efforts.

          

              

    
    

        
Related Research Insights

        

            See how this publication connects to RSRC's living evidence syntheses through current citations and research-topic mapping.