Deep Representation Learning With Full Center Loss for Credit Card Fraud Detection

Li, Zhenchuan; Liu, Guanjun; Jiang, Changjun

doi:10.1109/tcss.2020.2970805

Cited by 91 publications

(40 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most prominent and effective classification techniques for text data are Random Forests (RF) [23], [24], Support Vector Machines (SVM) and Multinomial Nave Bayes (MNB). Random Forest has also used in for different fraud detections [25] through textual data. Therefore, this research involves the testing of all these well-known classifiers to choose the best one for the classification of human loss related news corpus.…”

Section: Methodology a News Classificationmentioning

confidence: 99%

Semi-Automatic Classification and Duplicate Detection From Human Loss News Corpus

et al. 2020

View full text Add to dashboard Cite

Automatic news repository collection systems involve a news crawler that extracts news from different news portals, subsequently, these news need to be processed to figure out the category of a news article e.g. sports, politics, showbiz etc. In this process there are two main challenges first one is to place a news article under the right category of news, while the second one is to detect a duplicate news, i.e. when the news are being extracted from multiple sources, it is highly probable to get the same news from many different portals, resulting into duplicate news; failing to which may result into inconsistent statistics obtained after pre-processing the news text. This problem becomes more pertinent when we deal with human loss news involving crime, accident etc. related news articles. As the system may count the same news many times resulting into misleading statistics. In order to address these problems, this research presents the following contributions. Firstly, a news corpus comprising of human loss news of different categories has been developed by gathering data from different sources of well-known and authentic news websites. The corpus also includes a number of duplicate news. Secondly, a comparison of different classification approaches has been conducted to empirically find out the best suitable text classifier for the categorization of different sub-categories of human loss news. Lastly, methods have been proposed and compared to detect duplicate news from the corpus by involving different pre-processing techniques and widely used similarity measures, cosine similarity, and Jaccard's coefficient. The results show that conventional text classifiers are still relevant and perform well in text classification tasks as MNB has given 89.5% accurate results. While, Jaccard coefficient exhibits much better results than Cosine similarity for duplicate news detection with different pre-processing variations with an average accuracy of 83.16%.

show abstract

Section: Methodology a News Classificationmentioning

confidence: 99%

Semi-Automatic Classification and Duplicate Detection From Human Loss News Corpus

et al. 2020

View full text Add to dashboard Cite

show abstract

“…However, more advanced AI techniques have recently appeared: expert systems to detect fraud in the form of rules [19], pattern recognition to approximate classes or patterns of suspicious behavior [20], ML to automatically detect risky features [21], neural networks that can learn suspicious patterns from data [22], optimization of weighted extreme learning machines for imbalanced classification in credit card fraud detection [23], transaction fraud detection based on total order relation and behavior diversity [24], online fault detection models and strategies based on clouds [25], and deep representation learning with full center loss for credit card fraud detection [26].…”

Section: ML For Risky Websites Detectionmentioning

confidence: 99%

Knowledge-Based Approach to Detect Potentially Risky Websites

et al. 2021

View full text Add to dashboard Cite

Nowadays, fraudulent and malicious websites are emerging as a harmful and very common problem on the Internet. It causes huge money losses and irreparable damage for both companies and particulars. To face this situation, governments have approved multiple law projects. This way, the legality on the Internet is being enforced and sanctions to those offenders who develop illegal or malicious activities are being imposed. However, governments still need a way to simplify the classification of websites into risky or non-risky, since most of this work is manual. This paper presents the DOmains Classifier based on RIsky Websites (DOCRIW ) framework to detect domains that contain possible fraud or malicious content. It is based on two main components. The first component is a previously built knowledge base containing information from risky websites. The second one complements the system with a binary classifier able to label a website (as risky or not) considering just its domain. The system makes use of web information sources and includes host-based variables. It also applies similarity measures, supervised learning algorithms and optimization methods to enhance its performance. The presented work is experimental, rendering promising outcomes.INDEX TERMS Risky website detection, malware alerts, knowledge-based systems, similarity metrics, combination of information.

show abstract

“…Deep learning due to its power to form the high quality of the user/item representation has been applied in the research of the recommender system widely. CNN has been widely used for feature representation and has achieved good results [18]- [20]. DeepCoNN [18] constructs the user and item representation by two parallel CNN structure, which consumes the review text.…”

Section: Related Work a Deep Learning Recommender Systemmentioning

confidence: 99%

RACRec: Review Aware Cross-Domain Recommendation for Fully-Cold-Start User

et al. 2020

View full text Add to dashboard Cite

Traditional recommendation algorithms such as matrix factorization, collaborative filtering perform poorly when lack of interactive information of user and product, known as the user cold-start problem, which may cut down the revenue of E-Commerce platform. Moreover, it is more challenging to generate recommendation lists for users who have no information at all because there is no preference information about them that could be leveraged, which is the user fully-cold-start problem. In this paper, a review aware cross-domain recommendation algorithm, called RACRec, is proposed to address the fullycold-start problem in the field of product recommendation. Firstly, reviews are dynamically selected by using the adjacency matrix. Secondly, domain-specific preference vectors and domain-shared preference vectors of the cold start user are extracted by a migration model. On the other hand, the product feature vector in the target domain, which is generated from review texts by encoder and decoder, is combined with preference vectors of the cold-start user to make the rating prediction. Experiments on the Amazon datasets reveal that RACRec outperforms the state-of-the-art recommendation algorithms.

show abstract

Deep Representation Learning With Full Center Loss for Credit Card Fraud Detection

Cited by 91 publications

References 32 publications

Semi-Automatic Classification and Duplicate Detection From Human Loss News Corpus

Semi-Automatic Classification and Duplicate Detection From Human Loss News Corpus

Knowledge-Based Approach to Detect Potentially Risky Websites

RACRec: Review Aware Cross-Domain Recommendation for Fully-Cold-Start User

Contact Info

Product

Resources

About