001484678 000__ 05455cam\\2200541\a\4500
001484678 001__ 1484678
001484678 003__ OCoLC
001484678 005__ 20240117003333.0
001484678 006__ m\\\\\o\\d\\\\\\\\
001484678 007__ cr\un\nnnunnun
001484678 008__ 231213s2023\\\\si\\\\\\ob\\\\000\0\eng\d
001484678 019__ $$a1412621275
001484678 020__ $$a9789819952571$$q(electronic bk.)
001484678 020__ $$a9819952573$$q(electronic bk.)
001484678 020__ $$z9819952565
001484678 020__ $$z9789819952564
001484678 0247_ $$a10.1007/978-981-99-5257-1$$2doi
001484678 035__ $$aSP(OCoLC)1413377736
001484678 040__ $$aYDX$$beng$$cYDX$$dGW5XE$$dEBLCP$$dOCLCO
001484678 049__ $$aISEA
001484678 050_4 $$aHG176.7
001484678 08204 $$a658.15$$223/eng/20231219
001484678 1001_ $$aWang, Cheng.
001484678 24510 $$aAnti-fraud engineering for digital finance :$$bbehavioral modeling paradigm /$$cCheng Wang.
001484678 260__ $$aSingapore :$$bSpringer,$$c2023.
001484678 300__ $$a1 online resource
001484678 504__ $$aIncludes bibliographical references.
001484678 5050_ $$aIntro -- Contents -- 1 Overview of Digital Finance Anti-fraud -- 1.1 Situation of Anti-fraud Engineering -- 1.2 Challenge of Anti-fraud Engineering -- 1.3 Strategies of Anti-fraud Engineering -- 1.4 Typical Application in Financial Scenarios -- 1.5 Outline of This Book -- References -- 2 Vertical Association Modeling: Latent Interaction Modeling -- 2.1 Introduction to Vertical Association Modeling in Online Services -- 2.2 Related Work -- 2.2.1 Composite Behavioral Modeling -- 2.2.2 Customized Data Enhancement -- 2.3 Fine-Grained Co-occurrences for Behavior-Based Fraud Detection
001484678 5058_ $$a2.3.1 Fraud Detection System Based in Online Payment Services -- 2.3.2 Experimental Evaluation -- 2.4 Conclusion -- 2.4.1 Behavior Enhancement -- 2.4.2 Future Work -- References -- 3 Horizontal Association Modeling: Deep Relation Modeling -- 3.1 Introduction to Horizontal Association Modeling in Online Services -- 3.1.1 Behavior Prediction -- 3.1.2 Behavior Sequence Analysis -- 3.2 Related Work -- 3.2.1 Fraud Prediction by Account Risk Evaluation -- 3.2.2 Fraud Detection by Optimizing Window-Based Features -- 3.3 Historical Transaction Sequence for High-Risk Behavior Alert
001484678 5058_ $$a3.3.1 Fraud Prediction System Based on Behavior Prediction -- 3.3.2 Experimental Evaluation -- 3.3.3 Enhanced Anti-fraud Scheme -- 3.4 Learning Automatic Windows for Sequence-Form Fraud Pattern -- 3.4.1 Fraud Detection System based on Behavior Sequence Analysis -- 3.4.2 Experimental Evaluation -- 3.5 Conclusion -- 3.5.1 Behavior Prediction -- 3.5.2 Behavior Analysis -- 3.5.3 Future Work -- References -- 4 Explicable Integration Techniques: Relative Temporal Position Taxonomy -- 4.1 Concepts and Challenges -- 4.2 Main Technical Means of Anti-fraud Integration System
001484678 5058_ $$a4.2.1 Anti-fraud Function Divisions -- 4.2.2 Module Integration Schemes -- 4.2.3 Explanation Methods -- 4.3 System Integration Architecture -- 4.3.1 Anti-fraud Function Modules -- 4.3.2 Center Control Module -- 4.3.3 Communication Architecture -- 4.4 Performance Analysis -- 4.4.1 Experimental Set-Up -- 4.4.2 Implementation -- 4.4.3 Evaluation of System Performance -- 4.4.4 Exemplification of CAeSaR's Advantages -- 4.5 Discussion -- 4.5.1 Faithful Explanation -- 4.5.2 Online Learning -- 4.6 Conclusion -- References -- 5 Multidimensional Behavior Fusion: Joint Probabilistic Generative Modeling
001484678 5058_ $$a5.1 Online Identity Theft Detection Based on Multidimensional Behavioral Records -- 5.2 Overview of the Solution -- 5.3 Identity Theft Detection Solutions in Online Social Networks -- 5.3.1 Composite Behavioral Model -- 5.3.2 Identity Theft Detection Scheme -- 5.4 Evaluation and Analysis -- 5.4.1 Datasets -- 5.4.2 Experiment Settings -- 5.4.3 Performance Comparison -- 5.5 Literature Review -- 5.6 Conclusion -- References -- 6 Knowledge Oriented Strategies: Dedicated Rule Engine -- 6.1 Online Anti-fraud Strategy Based on Semi-supervised Learning -- 6.2 Development and Present State
001484678 506__ $$aAccess limited to authorized users.
001484678 520__ $$aThis book offers an introduction to the topic of anti-fraud in digital finance based on the behavioral modeling paradigm. It deals with the insufficiency and low-quality of behavior data and presents a unified perspective to combine technology, scenarios, and data for better anti-fraud performance. The goal of this book is to provide a non-intrusive second security line, rather than replaced with existing solutions, for anti-fraud in digital finance. By studying common weaknesses in typical fields, it can support the behavioral modeling paradigm across a wide array of applications. It covers the latest theoretical and experimental progress and offers important information that is just as relevant for researchers as for professionals.
001484678 588__ $$aOnline resource; title from PDF title page (SpringerLink, viewed December 19, 2023).
001484678 650_6 $$aIngénierie financière.
001484678 650_0 $$aFinancial engineering.$$0(DLC)sh 91003887
001484678 650_0 $$aFraud$$xPrevention.$$0(DLC)sh2003006752
001484678 655_0 $$aElectronic books.
001484678 77608 $$iPrint version: $$z9819952565$$z9789819952564$$w(OCoLC)1391916712
001484678 852__ $$bebk
001484678 85640 $$3Springer Nature$$uhttps://univsouthin.idm.oclc.org/login?url=https://link.springer.com/10.1007/978-981-99-5257-1$$zOnline Access$$91397441.1
001484678 909CO $$ooai:library.usi.edu:1484678$$pGLOBAL_SET
001484678 980__ $$aBIB
001484678 980__ $$aEBOOK
001484678 982__ $$aEbook
001484678 983__ $$aOnline
001484678 994__ $$a92$$bISE