A Novel Methodology for HYIP Operators’ Bitcoin Addresses Identification

Toyoda, Kentaroh; Mathiopoulos, P. Takis; Ohtsuki, Tomoaki

doi:10.1109/access.2019.2921087

Cited by 63 publications

(45 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…5). This confirms that the RF classifier, already known to be effective both on biomedical data [59] as well as in different application fields [60]- [62], can be successfully applied also in presence of imbalanced class distributions [57], [63]. On the other hand, there is no selection method that clearly outperforms the others.…”

Section: Discussionsupporting

confidence: 61%

Learning From High-Dimensional Biomedical Datasets: The Issue of Class Imbalance

Pes

2020

IEEE Access

View full text Add to dashboard Cite

As witnessed by a vast corpus of literature, dimensionality reduction is a fundamental step for biomedical data analysis. Indeed, in this domain, there is often the need for coping with a huge number of data attributes (or features). By removing irrelevant or redundant attributes, feature selection techniques can significantly reduce the complexity of the original problem, with important benefits in terms of domain understanding and knowledge discovery. When learning from biomedical data, however, the dimensionality issue is often addressed without a joint consideration of other critical aspects that may compromise the performance of the induced models. The adverse implications of an imbalanced class distribution, for example, are often neglected in this domain. The aim of this work is to investigate the effectiveness of hybrid learning strategies that incorporate both methods for dimensionality reduction as well as methods for alleviating the issue of class imbalance. Specifically, we combine different feature selection techniques, both univariate and multivariate, with sampling-based class balancing methods and cost-sensitive classification. The performance of the resulting learning schemes is experimentally evaluated on six highdimensional genomic benchmarks, using different classification algorithms, with interesting insight about the best strategies to use based on the characteristics of the data at hand.

show abstract

Section: Discussionsupporting

confidence: 61%

Learning From High-Dimensional Biomedical Datasets: The Issue of Class Imbalance

Pes

2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…For Ponzi-schemes detection in Ethereum, Jung et al [53] used J48 (decision tree algorithm), random forest and stochastic gradient descent (SGD) for classification. HYIP classification has been addressed in [54] using a dataset with a total of 2,134 HYIP addresses. Toyoda et al [54] used random forest (RF), gradient boosting implementation (XGBoost), ANN, SVM and k-NN for binary classification of HYIP and non-HYIP addresses.…”

Section: Fraud Detectionmentioning

confidence: 99%

“…HYIP classification has been addressed in [54] using a dataset with a total of 2,134 HYIP addresses. Toyoda et al [54] used random forest (RF), gradient boosting implementation (XGBoost), ANN, SVM and k-NN for binary classification of HYIP and non-HYIP addresses. Random forest achieved the best results based on 7 features characterizing the transactions.…”

Section: Fraud Detectionmentioning

confidence: 99%

“…Even studies that used the Chainalysis dataset still face the problem of dealing with the high class-imbalance problem. Except for [50], which combined semi-supervised and supervised techniques, other efforts [51]- [54] solely relied on supervised techniques. The high costs of manual labeling as done in [52] and the small size of the labeled datasets for fraudulent addresses suggest we need to explore using semi-supervised learning techniques for fraud detection in a way similar to [55].…”

Section: Fraud Detectionmentioning

confidence: 99%

“…Price prediction [11], [13], [15], [18], [20], [21], [24]- [26] [12], [16], [17], [19], [22], [23], [28] Volatility prediction [38], [39] [35]- [37], [40] Automated trading [9], [42], [44]- [46], [48], [49] [23] Fraud detection [50]- [52], [54] [53] Mining [68], [71] [69], [70] Security [72], [76], [77], [82] [70], [81] Anonymity and privacy [54], [60]- [63], [65]- [67] None…”

Section: Challengementioning

confidence: 99%

See 2 more Smart Citations

Cryptocurrencies and Artificial Intelligence: Challenges and Opportunities

et al. 2020

View full text Add to dashboard Cite

Decentralized cryptocurrencies have gained a lot of attention over the last decade. Bitcoin was introduced as the first cryptocurrency to allow direct online payments without relying on centralized financial entities. The use of Bitcoin has vastly grown as a financial asset rather than just a tool for online payments. A lot of cryptocurrencies have been created since 2011 with Bitcoin dominating the cryptocurrencies' market. With plenty of cryptocurrencies being used as financial assets and with millions of trades being executed through different exchange services, cryptocurrencies are susceptible to trading problems and challenges similar to those traditionally encountered in the financial domain. Price and trend prediction, volatility prediction, portfolio construction and fraud detection are some examples related to trading. In addition, there are other challenges that are specific to the domain of cryptocurrencies such as mining, cybersecurity, anonymity and privacy. In this paper, we survey the application of artificial intelligence techniques to address these challenges for cryptocurrencies with their vast amount of daily transactions, trades and news that are beyond human capabilities to analyze and learn from. This paper discusses the recent research work done in this emerging area and compares them in terms of used techniques and datasets. It also highlights possible research gaps and some potential areas for improvement.

show abstract

Securing logistics system and supply chain using Blockchain

Kumar

Abhishek

Ghalib

et al. 2020

Appl Stoch Models Bus & Ind

View full text Add to dashboard Cite

Past international trade practices have been associated with opaque information flows that have hindered traceability and created hurdles in hassle‐free trade. Blockchain and allied technologies have been investigated as a panacea for the problems faced by supply chain and logistics industry. Network analysis also uncovered twenty types of legal and antisocial entities operating on bitcoin and provided a path for uncovering these antisocial entities. However, earlier works of literature have focused on limited aspects of a typical supply chain such as monitoring assets, securing traceability, data integrity negligence, and data access. To overcome such drawbacks, this article proposes permissioned Blockchain with relevant processes and functions to obtain a holistic framework for securing the supply chain and logistic operations. The efficacy of the proposed framework was demonstrated in the case study. Comparative study was performed with the existing frameworks where the proposed framework was found to be better at four counts compared on the basis of data integrity in supply chain, decentralized decision making and traceability. It was found that critical loopholes in a current supply chain can be overcome using the proposed framework.

show abstract

A Novel Methodology for HYIP Operators’ Bitcoin Addresses Identification

Cited by 63 publications

References 18 publications

Learning From High-Dimensional Biomedical Datasets: The Issue of Class Imbalance

Learning From High-Dimensional Biomedical Datasets: The Issue of Class Imbalance

Cryptocurrencies and Artificial Intelligence: Challenges and Opportunities

Securing logistics system and supply chain using Blockchain

Contact Info

Product

Resources

About