A Blockchain Transaction Graph based Machine Learning Method for Bitcoin Price Prediction

• URL: http://arxiv.org/abs/2008.09667v1
• Date: Fri, 21 Aug 2020 20:08:17 GMT
• Title: A Blockchain Transaction Graph based Machine Learning Method for Bitcoin Price Prediction
• Authors: Xiao Li and Weili Wu
• Abstract summary: Existing bitcoin prediction works mostly on trivial feature engineering. We propose k-order transaction graph to reveal patterns under different scope. A novel prediction method is proposed to accept the features and make price prediction, which can take advantage from particular patterns from different history period.
• Score: 8.575998118995216
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Bitcoin, as one of the most popular cryptocurrency, is recently attracting much attention of investors. Bitcoin price prediction task is consequently a rising academic topic for providing valuable insights and suggestions. Existing bitcoin prediction works mostly base on trivial feature engineering, that manually designs features or factors from multiple areas, including Bticoin Blockchain information, finance and social media sentiments. The feature engineering not only requires much human effort, but the effectiveness of the intuitively designed features can not be guaranteed. In this paper, we aim to mining the abundant patterns encoded in bitcoin transactions, and propose k-order transaction graph to reveal patterns under different scope. We propose the transaction graph based feature to automatically encode the patterns. A novel prediction method is proposed to accept the features and make price prediction, which can take advantage from particular patterns from different history period. The results of comparison experiments demonstrate that the proposed method outperforms the most recent state-of-art methods.

Related papers

• BlockFound: Customized blockchain foundation model for anomaly detection [47.04595143348698]
  BlockFound is a customized foundation model for anomaly blockchain transaction detection. We introduce a series of customized designs to model the unique data structure of blockchain transactions. BlockFound is the only method that successfully detects anomalous transactions on Solana with high accuracy.
  arXiv  Detail & Related papers  (2024-10-05T05:11:34Z)
• IT Strategic alignment in the decentralized finance (DeFi): CBDC and digital currencies [49.1574468325115]
  Decentralized finance (DeFi) is a disruptive-based financial infrastructure. This paper seeks to answer two main questions 1) What are the common IT elements in the DeFi? And 2) How the elements to the IT strategic alignment in DeFi?
  arXiv  Detail & Related papers  (2024-05-17T10:19:20Z)
• Blockchain Metrics and Indicators in Cryptocurrency Trading [0.22940141855172028]
  The objective of this paper is the construction of new indicators that can be useful to operate in the cryptocurrency market. These indicators are based on public data obtained from the blockchain network, specifically from the nodes that make up Bitcoin mining.
  arXiv  Detail & Related papers  (2024-02-11T12:34:58Z)
• Interplay between Cryptocurrency Transactions and Online Financial Forums [41.94295877935867]
  This study focuses on the study of the interplay between these cryptocurrency forums and fluctuations in cryptocurrency values. It shows that the activity of Bitcointalk forum keeps a direct relationship with the trend in the values of BTC. The experiment highlights that forum data can explain specific events in the financial field.
  arXiv  Detail & Related papers  (2023-11-27T16:25:28Z)
• A Data-driven Deep Learning Approach for Bitcoin Price Forecasting [10.120972108960425]
  We propose a shallow Bidirectional-LSTM (Bi-LSTM) model to forecast bitcoin closing prices in a daily time frame. We compare the performance with that of other forecasting methods, and show that with the help of the proposed feature engineering method, a shallow deep neural network outperforms other popular price forecasting models.
  arXiv  Detail & Related papers  (2023-10-27T10:35:47Z)
• Predicting Digital Asset Prices using Natural Language Processing: a survey [2.806897141084325]
  The rise of Machine Learning, and Natural Language Processing, in particular, has shed light monitoring and predicting the price behaviors of cryptocurrencies. This paper aims to review and analyze the recent efforts in applying Machine Learning and Natural Language Processing methods to predict the prices and analyze the behaviors of digital assets such as Bitcoin.
  arXiv  Detail & Related papers  (2022-11-28T17:37:06Z)
• Graph Regularized Nonnegative Latent Factor Analysis Model for Temporal Link Prediction in Cryptocurrency Transaction Networks [1.6801544027052142]
  Link prediction learning structure of network is helpful to understand the mechanism of network. We propose a single latent factor-dependent, non-negative, multiplicative and graph regularized-incorporated update (SLF-NMGRU) algorithm. Experiments on a real cryptocurrency transaction network show that the proposed method improves both the accuracy and the computational efficiency.
  arXiv  Detail & Related papers  (2022-08-03T08:58:59Z)
• Pattern Analysis of Money Flow in the Bitcoin Blockchain [1.14219428942199]
  We propose a method based on taint analysis to extract taint flows. We apply graph embedding methods to characterize taint flows. Our work proves that tracing the money flows can be a promising approach to classifying source actors.
  arXiv  Detail & Related papers  (2022-07-15T07:15:16Z)
• Sequence-Based Target Coin Prediction for Cryptocurrency Pump-and-Dump [39.06710188537909]
  This paper focuses on predicting the pump probability of all coins listed in the target exchange before a scheduled pump time. We conduct a comprehensive study of the latest 709 P&D events organized in Telegram from Jan. 2019 to Jan. 2022. We develop a novel sequence-based neural network, dubbed SNN, which encodes a channel's P&D event history into a sequence representation.
  arXiv  Detail & Related papers  (2022-04-21T16:34:53Z)
• BABD: A Bitcoin Address Behavior Dataset for Address Behavior Pattern Analysis [36.42552617883664]
  We build a dataset comprising Bitcoin transactions between 12 July 2019 and 26 May 2021. This dataset contains 13 types of Bitcoin addresses, 5 categories of indicators with 148 features, and 544,462 labeled data. We use our proposed dataset on common machine learning models, namely: k-nearest neighbors algorithm, decision tree, random forest, multilayer perceptron, and XGBoost.
  arXiv  Detail & Related papers  (2022-04-10T06:46:51Z)
• Smart Contract Vulnerability Detection: From Pure Neural Network to Interpretable Graph Feature and Expert Pattern Fusion [48.744359070088166]
  Conventional smart contract vulnerability detection methods heavily rely on fixed expert rules. Recent deep learning approaches alleviate this issue but fail to encode useful expert knowledge. We develop automatic tools to extract expert patterns from the source code. We then cast the code into a semantic graph to extract deep graph features.
  arXiv  Detail & Related papers  (2021-06-17T07:12:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.