Topological Data Analysis for Portfolio Management of Cryptocurrencies

Rivera-Castro, Rodrigo; Pilyugina, Polina; Burnaev, Evgeny

doi:10.1109/icdmw.2019.00044

Cited by 7 publications

(4 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Time series clustering is also discussed in the literature with applications to spatial data [32] and finance [33]. The authors in [34,35] applied TDA to portfolio management for cryptocurrencies. However, they used only basic features and studied a limited area of the cryptocurrency market, which is less competitive than a general stock market.…”

Section: Related Workmentioning

confidence: 99%

Portfolio selection via topological data analysis

Sokerin,

Kuznetsov,

Makhneva

et al. 2024

Sixteenth International Conference on Machine Vision (ICMV 2023)

View full text Add to dashboard Cite

Portfolio management is an essential part of investment decision-making. However, traditional methods often fail to deliver reasonable performance. This problem stems from the inability of these methods to account for the unique characteristics of multivariate time series data from stock markets. We present a two-stage method for constructing an investment portfolio of common stocks. The method involves the generation of time series representations followed by their subsequent clustering. Our approach utilizes features based on Topological Data Analysis (TDA) for the generation of representations, allowing us to elucidate the topological structure within the data. Experimental results show that our proposed system outperforms other methods. This superior performance is consistent over different time frames, suggesting the viability of TDA as a powerful tool for portfolio selection.

show abstract

Section: Related Workmentioning

confidence: 99%

Portfolio selection via topological data analysis

Sokerin,

Kuznetsov,

Makhneva

et al. 2024

Sixteenth International Conference on Machine Vision (ICMV 2023)

View full text Add to dashboard Cite

show abstract

“…On this research I will analyze several transactions gathered from the Bitcoin Blockchain to determine whether it is possible to easily categorize each transaction as being from a specific ransomware family or not pertaining to any of them at all. Relevant research has been conducted on this field in [7], [8] and [9].…”

Section: Introductionmentioning

confidence: 99%

Bitcoin Blockchain Clustering Analysis for Ransomware Detection

Lima¹

2021

Preprint

View full text Add to dashboard Cite

Bitcoin is the most popular digital currency. It is not controlled by any sort of central bank or government institution and is the preferred payment method requested by cyber criminals through ransomware. This type of malware encrypts a victim’s files and forces them to pay a ransom in order to regain access. In this short paper, Bitcoin transaction data of tenyears is analyzed by generating a K-Means clustering model, using it to predict each sample’s cluster, and then creating a confusion matrix and evaluating the results (Rand Score).

show abstract

“…Similarly, TDA can extract seasonality and periodicity, [14], [5]. Authors have found success with TDA for a wide array of applications ranging from marketing data, [18], to cryptocurrencies, [17]. This highlights one of its benefits.…”

Section: Introductionmentioning

confidence: 99%

TOTOPO: Classifying univariate and multivariate time series with Topological Data Analysis

Pilyugina¹,

Rivera-Castro²,

Burnaev³

2020

Preprint

Self Cite

View full text Add to dashboard Cite

This work is devoted to a comprehensive analysis of topological data analysis for time series classification. Previous works have significant shortcomings, such as lack of large-scale benchmarking or missing state-of-the-art methods. In this work, we propose TOTOPO for extracting topological descriptors from different types of persistence diagrams. The results suggest that TOTOPO significantly outperforms existing baselines in terms of accuracy. TOTOPO is also competitive with the state-of-the-art, being the best on 20% of univariate and 40% of multivariate time series datasets. This work validates the hypothesis that TDA-based approaches are robust to small perturbations in data and are useful for cases where periodicity and shape help discriminate between classes.

show abstract

Topological Data Analysis for Portfolio Management of Cryptocurrencies

Cited by 7 publications

References 16 publications

Portfolio selection via topological data analysis

Portfolio selection via topological data analysis

Bitcoin Blockchain Clustering Analysis for Ransomware Detection

TOTOPO: Classifying univariate and multivariate time series with Topological Data Analysis

Contact Info

Product

Resources

About