Modeling the Field Value Variations and Field Interactions Simultaneously for Fraud Detection
نویسندگان
چکیده
With the explosive growth of e-payment industry, online transaction fraud has become one biggest challenges for business. The historical behavior information users provides rich digging into users' risk. While considerable efforts have been made in this direction, a long-standing challenge is how to effectively exploit user's behavioral and provide explainable prediction results. In fact, value variations same field from different events interactions fields within event proven be strong indicators fraudulent behaviors. paper, we propose Dual Importance-aware Factorization Machines (DIFM), which exploits inter- intra-event among users’ sequence dual perspectives, i.e., simultaneously detection. proposed model deployed Alipay's risk management system, real-time detection service e-commerce platforms. Experimental results on industrial data under various scenarios platform clearly demonstrate that our achieves significant improvements compared with state-of-the-art baseline models. Moreover, \model~could also give an insight explanation perspectives.
منابع مشابه
the relationship between field-related cognitive styles and global reading comprehension of hypertext
this study investigates the relationship between field-related cognitive styles and global reading comprehension of hypertext. technically, field dependency is prevailing dominance of field on perception of parts, while global comprehension is skim-like reading to grasp the general content. in this research project, 60 senior and junior students of arak university majoring in english literature...
15 صفحه اولsimulation and experimental studies for prediction mineral scale formation in oil field during mixing of injection and formation water
abstract: mineral scaling in oil and gas production equipment is one of the most important problem that occurs while water injection and it has been recognized to be a major operational problem. the incompatibility between injected and formation waters may result in inorganic scale precipitation in the equipment and reservoir and then reduction of oil production rate and water injection rate. ...
Edge detection in gravity field of the Gheshm sedimentary basin
Edge detection and edge enhancement techniques play an essential role in interpreting potential field data. This paper describes the application of various edge detection techniques to gravity data in order to delineate the edges of subsurface structures. The edge detection methods comprise analytic signal, total horizontal derivative (THDR), theta angle, tilt angle, hyperbolic of tilt angle (H...
متن کاملDesign and fabrication of a high-Q near-field probe for subsurface crack detection
Non-destructive detection and evaluation of invisible cracks in metal structures is an important matter in several critical environments including ground transportation, air transportation and power plants. In this paper, a high-Q near-field Microwave probe is designed and fabricated using defected ground structures for surface and subsurface crack detection in metal structures. For this purpos...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Proceedings of the ... AAAI Conference on Artificial Intelligence
سال: 2021
ISSN: ['2159-5399', '2374-3468']
DOI: https://doi.org/10.1609/aaai.v35i17.17755