앙상블 머신러닝 기법과 블록체인 정보를 활용한 이더리움 엉클 블록 예측 분석 = Predictive Analysis of Ethereum Uncle Block using Ensemble Machine Learning Technique and Blockchain Information

다국어 초록 (Multilingual Abstract)

The advantages of Blockchain present the necessity of Blockchain in various fields. However, there are several disadvantages to Blockchain. Among them, the uncle block problem is one of the problems that can greatly hinder the value and utilization of Blockchain. Although the value of Blockchain may be degraded by the uncle block problem, previous studies did not pay much attention to research on uncle block. Therefore, the purpose of this study attempts to predict the occurrence of uncle block in order to predict and prepare for the uncle block problem of Blockchain. This study verifies the validity of introducing new attributes and ensemble analysis techniques for accurate prediction of uncle block occurrence. As a research method, voting, bagging, and stacking ensemble analysis techniques were employed for Ethereum's uncle block where the uncle block problem actually occurs. We used Blockchain information of Ethereum and Bitcoin as analysis data. As a result of the study, we found that the best prediction result was presented when voting and stacking ensemble techniques were applied using only Ethereum Blockchain information. The result of this study contributes to more accurately predict the occurrence of uncle block and prepare for the uncle block problem of Blockchain.

국문 초록 (Abstract)

블록체인의 장점들은 다양한 분야에서 블록체인의 필요성을 제시한다. 하지만 블록체인에는 몇 가지 단점들이 존재한다. 그 중 엉클블록 문제는 블록체인의 가치와 활용을 크게 저해할 수 있는 문제 중 하나다. 엉클블록 문제로 인해 블록체인의 가치가 저하 될 수 있음에도 불구하고 이전의 연구들은 엉클블록에 대한 연구에 크게 주목하지 않았다. 따라서 본 연구의 목적은 블록체인의 엉클 블록 문제를 예측하고 대비할 수 있도록 엉클블록의 발생을 예측 하고자 한다. 본 연구는 엉클 블록 발생의 정확한 예측을 위해서 새로운 변수와 앙상블 분석 기법 도입의 타당성을 검증한다. 연구 방법으로 엉클블록 문제가 실제로 발생하는 이더리움의 엉클블록을 대상으로 보팅, 배깅, 스태킹 앙상블 분석 기법을 활용하였다. 분석 데이터로는 이더리움과 비트코인 블록체인 정보를 활용하였다. 연구 결과, 이더리움 블록체인 정보만을 활용하여 보팅, 스태킹 앙상블 기법을 적용할 경우 가장 높은 예측 결과가 나타난다는 사실을 발견하였다. 본 연구의 결과는 엉클블록의 발생을 보다 정확하게 예측하여 블록체인의 엉클블록 문제에 대비할 수 있도록 기여한다.

참고문헌 (Reference)

• 1 김시욱, "블록체인 기반 금융 플랫폼의 성별 수용의도 결정요인에 관한 탐색 연구" 한국디지털정책학회 18 (18): 139-147, 2020
• 2 김한민, "머신러닝 기법을 활용한 블록체인의 엉클블록 분석 연구" 한국경영정보학회 22 (22): 1-16, 2020
• 3 이호현, "기계학습 응용 및 학습 알고리즘 성능 개선방안 사례연구" 한국디지털정책학회 14 (14): 245-258, 2016
• 4 김용훈, "개인정보보호를 위한 스마트컨트랙트 연구" 한국디지털정책학회 17 (17): 215-220, 2019
• 5 K. An, "Voting-averaged combination method for regressor ensemble" Springer 540-546, 2010
• 6 N. F. F. Da Silva, "Tweet sentiment analysis with classifier ensembles" 66 : 170-179, 2014
• 7 M. Saad, "Toward characterizing blockchain-based cryptocurrencies for highly accurate predictions" 14 (14): 321-332, 2019
• 8 C. Cortes, "Support-vector networks" 20 (20): 273-297, 1995
• 9 F. Divina, "Stacking ensemble learning for short-term electricity consumption forecasting" 11 (11): 949-, 2018
• 10 G. Wang, "Sentiment classification : The contribution of ensemble learning" 57 : 77-93, 2014
• 11 P. Wang., "Pricing currency options with support vector regression and stochastic volatility model with jumps" 38 (38): 1-7, 2011
• 12 D. C. Mallqui, "Predicting the direction, maximum, minimum and closing prices of daily Bitcoin exchange rate using machine learning techniques" 75 : 596-606, 2019
• 13 Y. B. Kim, "Predicting fluctuations in cryptocurrency transactions based on user comments and replies" 11 (11): e0161197-, 2016
• 14 H. M. Kim, "Predicting Ethereum Prices using Machine Learning and Block Chain Information" 1-5, 2019
• 15 L. Rokach., "Pattern classification using ensemble methods" World Scientific 2010
• 16 A. M. Antonopoulos, "Mastering Ethereum: Building Smart Contracts and Dapps" O'Reilly Media 2018
• 17 A. M. Antonopoulos., "Mastering Bitcoin : Unlocking Digital Cryptocurrencies" O'Reilly Media Inc 2014
• 18 K. P. Murphy., "Machine learning : a probabilistic perspective" MIT press 2012
• 19 X. Hu, "Landslide Susceptibility Mapping Using the Stacking Ensemble Machine Learning Method in Lushui, Southwest China" 10 (10): 4016-, 2020
• 20 A. O. Kwok, "Is blockchain technology a watershed for tourism development?" 22 (22): 2447-2452, 2019
• 21 H. Si, "IoT information sharing security mechanism based on blockchain technology" 101 : 1028-1040, 2019
• 22 X. Yue, "Healthcare data gateways : found healthcare intelligence on blockchain with novel privacy risk control" 40 (40): 218-, 2016
• 23 W. Foxley, "Ethereum Classic’s Terrible, Horrible, No Good, Very Bad Week" Coindesk
• 24 J. Abraham, "Cryptocurrency price prediction using tweet volumes and sentiment analysis" 1 (1): 1-, 2018
• 25 A. S. Assiri, "Breast Tumor Classification Using an Ensemble Machine Learning Method" 6 (6): 39-, 2020
• 26 T. T. Kuo, "Blockchain distributed ledger technologies for biomedical and health care applications" 24 (24): 1211-1220, 2017
• 27 L. Kristoufek., "BitCoin meets Google Trends and Wikipedia : Quantifying the relationship between phenomena of the Internet era" 3 (3): 1-7, 2013
• 28 H. Jang, "An empirical study on modeling and prediction of bitcoin prices with bayesian neural networks based on blockchain information" 6 : 5427-5437, 2017
• 29 Y. Liu, "An Evaluation of Uncle Block Mechanism Effect on Ethereum Selfish and Stubborn Mining Combined With an Eclipse Attack" 8 : 17489-17499, 2020
• 30 C. Bai, "A supply chain transparency and sustainability technology appraisal model for blockchain technology" 58 (58): 2142-2162, 2020
• 31 M. M. Islam, "A new algorithm to design compact two-hidden-layer artificial neural networks" 14 (14): 1265-1278, 2001