Real-Time Fraud Detection: How Stream Computing Can Help the Retail Banking Industry

Topics: Bank, Retail banking, Fraud Pages: 176 (56858 words) Published: March 26, 2013
Para os meus pais, porque "o valor das coisas não está no tempo que elas duram, mas na intensidade com que acontecem. Por isso existem momentos inesquecíveis, coisas inexplicáveis e pessoas incomparáveis" como vocês! Obrigado por tudo, Filipe

The Retail Banking Industry has been severely affected by fraud over the past few years. Indeed, despite all the research and systems available, fraudsters have been able to outsmart and deceive the banks and their customers. With this in mind, we intend to introduce a novel and multi-purpose technology known as Stream Computing, as the basis for a Fraud Detection solution. Indeed, we believe that this architecture will stimulate research, and more importantly organizations, to invest in Analytics and Statistical Fraud-Scoring to be used in conjunction with the already in-place preventive techniques. Therefore, in this research we explore different strategies to build a Streambased Fraud Detection solution, using advanced Data Mining Algorithms and Statistical Analysis, and show how they lead to increased accuracy in the detection of fraud by at least 78% in our reference dataset. We also discuss how a combination of these strategies can be embedded in a Stream-based application to detect fraud in real-time. From this perspective, our experiments lead to an average processing time of 111,702ms per transaction, while strategies to further improve the performance are discussed. Keywords: Fraud Detection, Stream Computing, Real-Time Analysis, Fraud, Data Mining, Retail Banking Industry, Data Preprocessing, Data Classification, Behavior-based Models, Supervised Analysis, Semi-supervised Analysis

Privatbankerna har drabbats hårt av bedrägerier de senaste åren. Bedragare har lyckats kringgå forskning och tillgängliga system och lura bankerna och deras kunder. Därför vill vi införa en ny, polyvalent strömmande datorteknik (Stream Computing) för att upptäcka bedrägerier. Vi tror att denna struktur kommer att stimulera forskningen, och framför allt få organisationerna att investera i analytisk och statistisk bedrägerispårning som kan användas tillsammans med befintlig förebyggande teknik. Vi undersöker i vår forskning olika strategier för att skapa en strömmande lösning som utnyttjar avancerade algoritmer för datautvinning och statistisk analys för att upptäcka bedrägerier, och visar att dessa ökar träffsäkerheten för att upptäcka bedrägerier med minst 78% i vår referensbas. Vi diskuterar även hur en kombination av dessa strategier kan bäddas in i en strömmande applikation för att upptäcka bedrägerier i realtid. Våra försök ger en genomsnittlig bearbetningstid på 111,702ms per transaktion, samtidigt som olika strategier för att fortsätta förbättra resultaten diskuteras.

"Silent gratitude isn’t much use to anyone" Gladys Bronwyn Stern When I wrote the first words in this report I think I had no idea what a Master Thesis is about! I can’t blame myself though since I never wrote one before, but if you ask me now to describe this experience I would say that it’s like a road trip: you set yourself a destination, you have a loyal crew that is always there for you, a roadmap, supporters on the side and then the journey begins. Within the latter, you face setbacks with the help of others, you share knowledge, you meet new people and most importantly you get to know them... This journey would not have been possible without the support, camaraderie and guidance of many friends, colleagues and my family. For all these reasons, I couldn’t let the journey end without expressing my gratitude to each and everyone of them. First and foremost, I would like to express my sincere gratitude to my supervisor, Philippe Spaas, who made it possible for me to work in this project under his supervision and in collaboration with IBM. It was a privilege to work alongside with him and a unique learning opportunity for me! I am indebted for his precious guidance and for...

Bibliography: [99] Richard Collard. “Preventing fraud in credit and debit card transactions: Look beyond packaged solutions for a holistic approach”. IBM Software WebSphere, Thought Leadership White Paper (June, 2011).
Continue Reading

Please join StudyMode to read the full document

You May Also Find These Documents Helpful

  • Fraud Detection and Electronic Banking Essay
  • Essay about Forces of Retail Banking Industry
  • Fraud Detection in Banking Essay
  • Fraud Detection in Banking Transactions Essay
  • Real time edge detection Essay
  • Retail Banking Essay
  • Global Retail Industry IT Spending Market Essay
  • How Cloud Computing Can Help Airlines N Essay

Become a StudyMode Member

Sign Up - It's Free