Article
Computer Science, Artificial Intelligence
Jing Long, Fei Fang, Cuiting Luo, Yehua Wei, Tien-Hsiung Weng
Summary: Online transaction fraud is increasing due to mobile payment convenience. Researchers have applied graph neural network to fraud detection. Existing methods do not fully consider the imbalances in the heterogeneous graph, which directly affects the model performance. This work proposes a hybrid graph neural network model that addresses the imbalance issues in online fraud detection.
CONNECTION SCIENCE
(2023)
Article
Green & Sustainable Science & Technology
Junghee Kim, Haemin Jung, Wooju Kim
Summary: This paper proposes a personalized alarm model to detect fraud in online banking transactions by analyzing sequence patterns in each user's normal transaction log. The model divides user logs into transactions, extracts sequence patterns, and uses them to determine if a new transaction is fraudulent.
Review
Computer Science, Information Systems
Khaled Gubran Al-Hashedi, Pritheega Magalingam
Summary: This study provides a comprehensive review of financial fraud detection research over the past decade, revealing that most data mining techniques are extensively implemented in the areas of bank and insurance fraud. Support Vector Machine is identified as the most widely used financial fraud detection technique, with countries like China and India being significantly impacted by financial fraud.
COMPUTER SCIENCE REVIEW
(2021)
Review
Computer Science, Information Systems
Songkai Tang, Luhua Jin, Fan Cheng
Summary: In online product review systems, fake reviews posted by fraudulent users mislead consumers and bring losses to enterprises. Traditional fraud detection algorithms are insufficient for the rich user interactions and graph-structured data. Therefore, a new model named FAHGT is proposed to address camouflage and inconsistency problems in a unified manner, showing remarkable performance gain compared to several baselines on different datasets.
Review
Biochemical Research Methods
Yuguo Zha, Kang Ning
Summary: This article introduces the ontology-aware neural network (ONN) as a new framework for microbiome data mining, emphasizing its advantages in mining efficiency and accuracy, and highlighting its characteristic of knowledge discovery.
BRIEFINGS IN BIOINFORMATICS
(2022)
Article
Computer Science, Artificial Intelligence
Mario Luca Bernardi, Marta Cimitile, Fabrizio Maria Maggi
Summary: This study uses a multi-perspective declarative language to model the behavior of malware and trusted applications, and identifies malware applications and evaluates their membership to malware families through system call traces. The empirical study shows that the approach performs well in identifying infected applications and evaluating their family membership, and exhibits high performance and robustness against code transformations and evasion techniques.
Article
Business, Finance
Yu-Tian Lei, Chao-Qun Ma, Yi-Shuai Ren, Xun-Qi Chen, Seema Narayan, Anh Ngoc Quang Huynh
Summary: This paper proposes a distributed neural network model for detecting credit card fraud by federating credit card transaction data among different financial institutions and introducing a model optimization algorithm to achieve convergence. The results demonstrate that the distributed model can avoid privacy leakage and data handling costs, accelerate model convergence through simultaneous computation, and outperform centralized models in credit card fraud detection.
FINANCE RESEARCH LETTERS
(2023)
Article
Computer Science, Artificial Intelligence
Gabriel Mariano de Castro Silva, Jaime Simao Sichman
Summary: Anomaly-based impersonation detection involves constructing typical profiles and comparing them with new data to identify possible fraud. This study explores the feasibility of using spatiotemporal mobility profiles and group patterns for fraud detection in Physical Access Control Systems.
APPLIED SOFT COMPUTING
(2022)
Article
Computer Science, Artificial Intelligence
Javad Forough, Saeedeh Momtazi
Summary: The rapid development of e-commerce technologies in recent years has provided more choices for people, but also increased the risk of fraud. This paper proposes an ensemble model based on deep learning and artificial neural networks to detect fraudulent actions, showing its advantage in real-time performance.
APPLIED SOFT COMPUTING
(2021)
Article
Engineering, Civil
Fumin Zhu, Chen Zhang, Zunxin Zheng, Sattam Al Otaibi
Summary: Online advertising delivers marketing messages to promotional consumers using Internet techniques, but advertisers face risks of malicious clicks and privacy issues. To counter the problem of fraud clicks, this study introduces a tensor-based mechanism to predict fraud clicks, showing better accuracy and prediction-recall rate compared to state-of-art machine learning algorithms.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Computer Science, Hardware & Architecture
Fanzhen Liu, Zhao Li, Baokun Wang, Jia Wu, Jian Yang, Jiaming Huang, Yiqing Zhang, Weiqiang Wang, Shan Xue, Surya Nepal, Quan Z. Sheng
Summary: In this study, the eRiskCom platform is designed to detect risky communities in e-commerce, containing identified fraudsters and closely related users. The platform utilizes a connected graph, graph partition, and pruning to identify risky communities, and experimental results confirm its effectiveness and deployability for real-world applications.
Article
Computer Science, Cybernetics
Hu Teng, Cheng Wang, Qing Yang, Xue Chen, Rui Li
Summary: The emergence of online trading greatly facilitates people's life, but it also brings hidden dangers, such as online fraudulent trading. In order to solve this issue, researchers have proposed many different detection models. However, in actual business scenarios, fraudulent transactions usually only account for a small portion of normal transactions, resulting in extremely imbalanced data. Besides, the concealment of fraud is reflected in that the fraudsters are imitating the normal transactions of users, posing a huge challenge for fraudulent transaction detection modeling. Inspired by generative adversarial networks (GANs), a GAN-based framework called BalanceGAN is proposed to detect online banking fraud on extremely imbalanced data. A fraud detection model is first pretrained using the data generated by the generator and then the model is fine-tuned using transfer learning on real-world datasets to address data imbalances. Compared with the conventional methods for solving imbalanced data, BalanceGAN can avoid overfitting of the model relatively, and experiments on two real datasets show that BalanceGAN has more than 10% performance improvement in precision and recall.
IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS
(2023)
Article
Computer Science, Information Systems
Rui Song, Fausto Giunchiglia, Qiang Shen, Nan Li, Hao Xu
Summary: With the rapid development of online social media, abusive language detection (ALD) has become a hot topic in the field of affective computing. However, most existing methods for ALD in social networks fail to consider the interactive relationships among user posts. This paper proposes a pipeline approach that takes into account both the context of a post and the characteristics of the interaction network, and experimentally demonstrates its effectiveness.
INFORMATION PROCESSING & MANAGEMENT
(2022)
Article
Computer Science, Information Systems
Yadong Zhu, Xiliang Wang, Qing Li, Tianjun Yao, Shangsong Liang
Summary: Mobile advertising is a fast-growing industry, but fraud has become a problem. We propose BotSpot++ to improve fraud detection by addressing issues such as device neighbor sparsity, weak interactive information, and noisy labels. Experimental results show that BotSpot++ outperforms other methods, and online experiments demonstrate its effectiveness.
ACM TRANSACTIONS ON INFORMATION SYSTEMS
(2022)
Article
Business
Tobias Knutha, Dennis C. Ahrholdtb
Summary: This study focuses on the identification of consumer fraud risk indicators and combinations in online shopping transaction data, using data mining techniques. By analyzing data from one of the world's largest online retailers, several patterns of fraud that improve the separation between fraudulent and legitimate transactions are identified. The results can guide the choice of variables and design of fraud prevention actions and systems in future practical and theoretical work.
INTERNATIONAL JOURNAL OF ELECTRONIC COMMERCE
(2022)
Article
Computer Science, Information Systems
Jinjin Guo, Longbing Cao, Zhiguo Gong
Summary: This work introduces a dynamic topic modeling method based on multi-topic-thread evolution, successfully disentangling the multi-couplings between evolving topics through data augmentation techniques, improving the effectiveness and efficiency of inference technique.
ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA
(2022)
Article
Computer Science, Artificial Intelligence
Chengzhang Zhu, Longbing Cao, Jianping Yin
Summary: This paper introduces a shallow but powerful unsupervised learning method called UNTIE for representing coupled categorical data. It reveals heterogeneous distributions between couplings and achieves significant performance improvement on multiple categorical datasets.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2022)
Article
Multidisciplinary Sciences
Longbing Cao, Chengzhang Zhu
Summary: Automated next-best action recommendation for each customer in a sequential, dynamic and interactive context is widely needed in decision-making. However, existing modeling theories and tools cannot quantify such complex decision-making on a personal level. This study proposes a data-driven approach using a reinforced coupled recurrent neural network to learn personalized next-best actions, demonstrating the potential of personalized deep learning and automated dynamic intervention for personalized decision-making in complex systems.
Article
Biology
Qinfen Wang, Geng Chen, Xuting Jin, Siyuan Ren, Gang Wang, Longbing Cao, Yong Xia
Summary: Mortality prediction is crucial in evaluating illness severity and improving patient prognosis. Existing methods for analyzing multivariate time series (MTSs) suffer from sparse and incomplete data. We propose a BiT-MAC network that captures both intra-time series coupling and inter-time series coupling to estimate missing values and improve MTS-based prediction. Extensive experiments on clinical datasets demonstrate the superiority of BiT-MAC and the interpretability of its features.
COMPUTERS IN BIOLOGY AND MEDICINE
(2023)
Article
Computer Science, Artificial Intelligence
Ping Qiu, Yongshun Gong, Yuhai Zhao, Longbing Cao, Chengqi Zhang, Xiangjun Dong
Summary: This article explores an efficient method for mining negative sequential patterns (NSPs) using temporal point processes (TPPs) to model frequently occurring and nonoccurring events and behaviors. By loosening constraints, a new definition of negative containment is provided, and an efficient method for calculating the supports of negative sequences is proposed. Finally, a novel and efficient algorithm is presented to identify valuable NSPs.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Editorial Material
Computer Science, Artificial Intelligence
Longbing Cao
Summary: The uncertain world faces increasing emergencies, crises and disasters, including COVID-19 pandemic, hurricane Ian, global financial inflation and recession, misinformation disaster, and cyberattacks. AI for smart disaster resilience transforms traditional reactive and scripted disaster management into proactive and intelligent resilience in the face of diverse ECDs. This article provides a systematic overview of various ECDs, conventional ECD management, ECD data complexities, and the research landscape of AISDR. Translational disaster AI is crucial in enabling smart disaster resilience.
INTERNATIONAL JOURNAL OF DATA SCIENCE AND ANALYTICS
(2023)
Article
Computer Science, Artificial Intelligence
Longbing Cao
Summary: After years of development, a new generation of AI and data science has emerged, based on the integration of science, technology, and engineering. This new generation embraces Trans-AI/DS thinking, which combines AI and data science to promote transformative, transdisciplinary, and translational approaches. These paradigm shifts encourage innovative thinking beyond traditional AI and data-driven methods, and focus on the complexities of human intelligence, nature, society, and their creations.
INTERNATIONAL JOURNAL OF DATA SCIENCE AND ANALYTICS
(2023)
Article
Computer Science, Artificial Intelligence
Longbing Cao
Summary: After 70 years of AI and 50 years of DS, AI/DS have entered a new age, where they are built upon the integration of science, technology, and engineering. This integration has resulted in Trans-AI/DS, which promote transformative, transdisciplinary, and translational thinking, methodologies, and practices in AI/DS.
INTERNATIONAL JOURNAL OF DATA SCIENCE AND ANALYTICS
(2023)
Article
Computer Science, Artificial Intelligence
Shoujin Wang, Yan Wang, Liang Hu, Xiuzhen Zhang, Qi Zhang, Quan Z. Sheng, Mehmet A. Orgun, Longbing Cao, Defu Lian
Summary: Users' purchase behaviors are complex and dynamic, driven by personal demands evolving over time. Predicting the next basket involves tracking demand changes and satisfying the current demand. The EvoDESA model predicts the next basket by learning demand dynamics and effectively packing item combinations to best satisfy the user, showing considerable superiority over existing approaches.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2023)
Article
Computer Science, Artificial Intelligence
Jia Xu, Longbing Cao
Summary: This paper proposes a method that combines deep variational sequential learning with copula-based statistical dependence modeling to address the challenging problem of modeling high-dimensional, long-range dependencies between nonnormal multivariates. The method can characterize both the temporal dependence degrees and structures between the hidden variables representing the nonnormal multivariates, and it outperforms benchmarks in terms of both technical significance and portfolio forecasting performance.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Zhilin Zhao, Longbing Cao, Kun-Yu Lin
Summary: In deep neural learning, training a discriminator on in-distribution samples may lead to misclassification of out-of-distribution samples, which poses a significant challenge for robust and safe deep learning. To address this issue, we propose a general approach called Fine-tuning Discriminators by Implicit Generators (FIG) that enhances the discriminatory power of standard discriminators in distinguishing in-distribution and out-of-distribution samples. FIG leverages information theory to infer an energy-based implicit generator from a discriminator and uses a Langevin dynamic sampler to draw specific out-of-distribution samples. Experimental results demonstrate that FIG achieves state-of-the-art out-of-distribution detection performance.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Zhilin Zhao, Longbing Cao, Kun-Yu Lin
Summary: Deep neural networks for image classification only learn to map in-distribution inputs to their corresponding ground-truth labels in training without differentiating out-of-distribution samples from in-distribution ones. To address this issue, we draw out-of-distribution samples from the vicinity distribution of training in-distribution samples for learning to reject the prediction on out-of-distribution inputs. Experiments show that the proposed method significantly outperforms existing methods in improving the capacity for discriminating between in-and out-of-distribution samples.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Zhilin Zhao, Longbing Cao, Chang-Dong Wang
Summary: The integrity of training data is uncertain, especially for non-IID datasets. Experts may misclassify samples, leading to unreliable labels. This study proposes a gray learning (GL) method that leverages both ground-truth and complementary labels to improve the robustness of neural networks.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Theory & Methods
Longbing Cao
Summary: This article provides an overview of the application of artificial intelligence techniques in the finance industry. It offers a comprehensive and dense landscape of the challenges, techniques, and opportunities of AIDS research in finance over the past decades. The article outlines the challenges of financial businesses and data, categorizes the decades of AIDS research in finance, illustrates the data-driven analytics and learning in financial businesses, compares classic and modern AIDS techniques, and discusses future opportunities for AIDS-empowered finance and finance-motivated AIDS research.
ACM COMPUTING SURVEYS
(2023)
Proceedings Paper
Computer Science, Information Systems
Md Fahim Arefin, Chowdhury Farhan Ahmed, Redwan Ahmed Rizvee, Carson K. Leung, Longbing Cao
Summary: In this paper, a novel measure of similarity is proposed to evaluate contextual similarity between items without using any additional metadata. An optimal algorithm and a heuristic algorithm are proposed to calculate this measure. The experimental results confirm the effectiveness and versatility of this measure in data of varying nature.
PROCEEDINGS OF THE 2022 16TH INTERNATIONAL CONFERENCE ON UBIQUITOUS INFORMATION MANAGEMENT AND COMMUNICATION (IMCOM 2022)
(2022)