Summary of Bitcoin Research with a Transaction Graph Dataset, by Hugo Schnoering and Michalis Vazirgiannis
Bitcoin Research with a Transaction Graph Dataset
by Hugo Schnoering, Michalis Vazirgiannis
First submitted to arxiv on: 15 Nov 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: General Finance (q-fin.GN)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary A novel dataset and set of tasks are introduced in this paper, focusing on large-scale transactions graph for Bitcoin users over a 13-year period. The dataset consists of 252 million nodes and 785 million edges, with each node and edge timestamped. Two labeled sets are provided: one based on entity type (33,000 nodes) and another labeling nearly 100,000 Bitcoin addresses with an entity name and type. This comprehensive dataset aims to facilitate advanced research in the domain, overcoming existing limitations. Various graph neural network models are trained to predict node labels, establishing a baseline for future research. Additionally, several use cases demonstrate the dataset’s applicability beyond Bitcoin analysis. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper creates a massive database of Bitcoin transactions that can be used by researchers to explore and analyze the digital economy. The data set includes information about 252 million transactions over 13 years, which is a lot! It also has labels for certain things like what kind of entity (like a person or business) is making a transaction. This will help scientists understand how Bitcoin works and make predictions about future transactions. The researchers also test some special computer models on the data to see how well they can predict what kind of transaction is happening. Finally, all the data and code are shared so that others can repeat their results. |
Keywords
» Artificial intelligence » Graph neural network
