Identifying E-Commerce Fraud Through User Behavior Data: Observations and InsightsIdentifying E-Commerce Fraud Through User Behavior Data: Observations and InsightsZ. Zhang et al.

被引:0
|
作者
Ziyi Zhang [1 ]
Hang Yin [2 ]
Susie Xi Rao [2 ]
Xiao Yan [3 ]
Zhurong Wang [4 ]
Weiming Liang [2 ]
Yang Zhao [2 ]
Yinan Shan [2 ]
Ruixuan Zhang [2 ]
Yuhao Lin [1 ]
Jiawei Jiang [1 ]
机构
[1] Wuhan University,School of Computer Science
[2] eBay,Department of Computer Science
[3] ETH Zurich,undefined
[4] Centre for Perceptual and Interactive Intelligence (CPII),undefined
关键词
Fraud detection; User behavior; Mouse trajectory;
D O I
10.1007/s41019-024-00275-6
中图分类号
学科分类号
摘要
Traditional fraud detection approaches often use linking entities, such as device, email, and address, to identify fraudulent transactions and users. However, as fraud methods continue to evolve and escalate, the fraudsters can fabricate the involved entities and thus hide their real intent. To make fraud detection more robust, we incorporate user behaviors in the pipeline and consider biometric characteristics that are difficult to forge. In this work, we conduct a detailed study of how user behavior data can help identify and prevent fraudulent activity in e-commerce. We present Multi-Modal Behavioral Transformer (MMBT), where we combine both inner-page behavioral data, such as mouse trajectory, and inter-page behavioral data, such as page view sequences. We propose to construct mouse trajectory data as an image, treat each mouse position as a pixel in the image, convert the image into small patches, and hence transform the mouse trajectory into patch index sequences. Our experimental results on real-word data show that MMBT significantly outperforms baselines — the precision@recall = 0.1 increases by up to 7%. In addition, we have built an online pipeline to operationalize our model. In production, the 99th percentile latency is maintained below 500 milliseconds, allowing the platform to initiate rapid response measures and prevent potential losses.
引用
收藏
页码:24 / 39
页数:15
相关论文
共 50 条
  • [31] E-COMMERCE DATA MINING ANALYSIS BASED ON USER PREFERENCES AND ASSICIATION RULES
    Fan, Zhiying
    SCALABLE COMPUTING-PRACTICE AND EXPERIENCE, 2024, 25 (03): : 1765 - 1772
  • [32] E-COMMERCE DATA MINING ANALYSIS BASED ON USER PREFERENCES AND ASSICIATION RULES
    Fan Z.
    Scalable Computing, 2024, 25 (03): : 1765 - 1772
  • [33] Discovering User's Interest at E-Commerce Site Using Clickstream Data
    Chen, Lu
    Su, Qiang
    2013 10TH INTERNATIONAL CONFERENCE ON SERVICE SYSTEMS AND SERVICE MANAGEMENT (ICSSSM), 2013, : 124 - 129
  • [34] Quantitative Detection of Financial Fraud Based on Deep Learning with Combination of E-Commerce Big Data
    Liu, Jian
    Gu, Xin
    Shang, Chao
    COMPLEXITY, 2020, 2020
  • [35] Beyond Hadoop for e-commerce Big Data Analysis through Amazon
    Verma, Ankush
    Sethi, Nidhi
    Jain, Neelesh
    2018 INTERNATIONAL CONFERENCE ON ADVANCED COMPUTATION AND TELECOMMUNICATION (ICACAT), 2018,
  • [36] E-commerce Flow Management in Fulfillment Centers Through Data Visualization
    Tarigonda, Amith
    Hymes, Bruce
    Nikonovich-Kahn, Alexei
    HCI IN BUSINESS, GOVERNMENT, AND ORGANIZATIONS, 2018, 10923 : 767 - 778
  • [37] Google Discover data-driven study of user activity on e-commerce platforms
    Strzelecki, Artur
    Rizun, Mariia
    ASLIB JOURNAL OF INFORMATION MANAGEMENT, 2025,
  • [38] Latent Dirichlet allocation for linking user-generated content and e-commerce data
    Zoghbi, Susana
    Vulic, Ivan
    Moens, Marie-Francine
    INFORMATION SCIENCES, 2016, 367 : 573 - 599
  • [39] RETRACTED: Big Data Analytics in E-Commerce User Interest Patterns (Retracted Article)
    Amarnadh, V
    Akhila, M.
    INTERNATIONAL CONFERENCE ON COMPUTER VISION AND MACHINE LEARNING, 2019, 1228
  • [40] ESTABLISHING CUSTOMER BEHAVIOR THROUGH E-COMMERCE WEBSITES IN NEWLY EMERGING MARKET
    Thi Huong Giang Vo
    Cho, James
    Khoa Huan Le
    Duy Binh Luong
    MARKETING AND MANAGEMENT OF INNOVATIONS, 2022, (04): : 85 - 93