Prediction of ROI Achievements and Potential Maximum Profit on Spot Bitcoin Rupiah Trading Using K-means Clustering and Patterned Dataset Model

Rizky Parlika - Diponegoro University, Semarang, Indonesia
R. Rizal Isnanto - Diponegoro University, Semarang, Indonesia
Basuki Rahmat - University of Pembangunan Nasional Veteran Jawa Timur, Surabaya, Indonesia


Citation Format:



DOI: http://dx.doi.org/10.62527/joiv.8.3-2.3120

Abstract


Since Satoshi Nakamoto first proposed the idea of bitcoin in 2009, the cryptocurrency and prediction methods for it have grown and changed exceptionally quickly. The Patterned Dataset Model was a valuable tool in earlier studies to explain how changes in the price of Bitcoin affect the movements of other cryptocurrencies in a digital trading market. Three different kinds of datasets are generated by this model: patterned datasets under full conditions, patterned datasets under dropping prices (Crash), and patterned datasets under rising prices (Moon). The K-means approach was then used to cluster these three datasets. Specifically, each dataset was split into two clusters, and the clustering score was determined by utilizing eight unique clustering metrics. Consequently, the best clustering score was found in the patterned dataset in the crash situation. Additionally, from 2022 to 2024, the raw data from this crash-condition-patterned dataset is used to determine the possibility of reaching maximum profit and return on investment (ROI) daily and monthly. According to the calculation results, the range computed over the course of a whole month (30 to 31 days) is significantly larger than the daily range (24 hours multiplied by one month), which represents the most significant profit and ROI attained before the emergence of the first diamond crash level. This research also covers the application of a deep learning model to forecast patterned datasets for crash scenarios that may occur many days in advance. The ConvLSTM2D Model performs better in predicting pattern dataset values for the subsequent crash scenario, according to the hyperparameter comparison between the Gated Recurrent Unit (GRU) Model and the 2D Convolutional Long Short-Term Memory Model.

Keywords


Patterned datasets; Bitcoin; Altcoin; cryptocurrency, k-means cluster, diamond crash, return of investment

Full Text:

PDF

References


R. Parlika, Mustafid, and B. Rahmat, “Detect Areas of Upward and Downward Fluctuations in Bitcoin Prices Using Patterned Datasets,” in 2023 IEEE 9th Information Technology International Seminar (ITIS), 2023, pp. 1–6. doi: 10.1109/ITIS59651.2023.10420129.

D. O. Oyewola, E. G. Dada, and J. N. Ndunagu, “A novel hybrid walk-forward ensemble optimization for time series cryptocurrency prediction,” Heliyon, vol. 8, no. 11, p. e11862, 2022, doi:10.1016/j.heliyon.2022.e11862.

S. Nakamoto, “Bitcoin: A Peer-to-Peer Electronic Cash System,” p. 9, [Online]. Available: https://bitcoin.org/bitcoin.pdf

B. Yang, Y. Sun, and S. Wang, “A novel two-stage approach for cryptocurrency analysis,” Int. Rev. Financ. Anal., vol. 72, no. October 2019, p. 101567, 2020, doi: 10.1016/j.irfa.2020.101567.

K. Dunbar and J. Owusu-amoako, “Journal of Behavioral and Experimental Finance Predictability of crypto returns : The impact of trading behavior ✩,” J. Behav. Exp. Financ., vol. 39, p. 100812, 2023, doi: 10.1016/j.jbef.2023.100812.

Z. Wen, E. Bouri, Y. Xu, and Y. Zhao, “Intraday return predictability in the cryptocurrency markets: Momentum, reversal, or both,” North Am. J. Econ. Financ., vol. 62, no. June, p. 101733, 2022, doi:10.1016/j.najef.2022.101733.

A. Brauneis, R. Mestel, R. Riordan, and E. Theissen, “Bitcoin unchained: Determinants of cryptocurrency exchange liquidity,” J. Empir. Financ., vol. 69, no. August, pp. 106–122, 2022, doi:10.1016/j.jempfin.2022.08.004.

R. Parlika, Mustafid, and B. Rahmat, “Use of Patterned Datasets (Minimum and Maximum) to predict Bitcoin and Ethereum price movements,” Technium: Romanian Journal of Applied Sciences and Technology, vol. 16, pp. 137–142, Oct. 2023, doi: 10.47577/technium.v16i.9972.

R. Parlika, Mustafid, and B. Rahmat, “Minimum, Maximum, and Average Implementation of Patterned Datasets in Mapping Cryptocurrency Fluctuation Patterns,” Int. J. Informatics Vis., vol. 8, no. 1, pp. 378–386, 2024, doi: 10.62527/joiv.8.1.1543.

M. Ozdamar, A. Sensoy, and L. Akdeniz, “Retail vs institutional investor attention in the cryptocurrency market,” J. Int. Financ. Mark. Institutions Money, vol. 81, no. February, p. 101674, 2022, doi:10.1016/j.intfin.2022.101674.

C. Cai, W. Li, H. Han, and M. Liu, “Risk scenario-based value estimation of Bitcoin,” Procedia Comput. Sci., vol. 199, pp. 1198–1204, 2021, doi: 10.1016/j.procs.2022.01.152.

R. Chowdhury, M. A. Rahman, M. S. Rahman, and M. R. C. Mahdy, “An approach to predict and forecast the price of constituents and index of cryptocurrency using machine learning,” Phys. A Stat. Mech. its Appl., vol. 551, p. 124569, 2020, doi:10.1016/j.physa.2020.124569.

M. M. Patel, S. Tanwar, R. Gupta, and N. Kumar, “A Deep Learning-based Cryptocurrency Price Prediction Scheme for Financial Institutions,” J. Inf. Secur. Appl., vol. 55, no. May, p. 102583, 2020, doi: 10.1016/j.jisa.2020.102583.

L. Morissette and S. Chartier, “The k-means clustering technique: General considerations and implementation in Mathematica,” Tutor. Quant. Methods Psychol., vol. 9, no. 1, pp. 15–24, 2013, doi:10.20982/tqmp.09.1.p015.

I. Nasirtafreshi, “Forecasting cryptocurrency prices using Recurrent Neural Network and Long Short-term Memory,” Data Knowl. Eng., vol. 139, no. March, p. 102009, 2022, doi:10.1016/j.datak.2022.102009.

A. A. Ewees, M. A. Elaziz, Z. Alameer, H. Ye, and Z. Jianhua, “Improving multilayer perceptron neural network using chaotic grasshopper optimization algorithm to forecast iron ore price volatility,” Resour. Policy, vol. 65, no. November 2019, p. 101555, 2020, doi: 10.1016/j.resourpol.2019.101555.

R. Parlika, Mustafid, and B. Rahmat, “The next cryptocurrency price movement prediction application uses patterned datasets,” AIP Conf. Proc., vol. 3116, no. 1, p. 30003, May 2024, doi: 10.1063/5.0210203.

R. Parlika and P. W. Atmaja, “Rizubot Version 1.0 algorithm: How to read the price movements of Crypto Currency Using the API to find a good purchase price,” vol. 1, no. Icst, pp. 1045–1049, 2018, doi:10.2991/icst-18.2018.211.

R. Parlika and A. Pratama, “Use of the Web API as a basis for obtaining the latest data on bitcoin prices at 30 exchange places,” IOP Conf. Ser. Mater. Sci. Eng., vol. 1125, no. 1, p. 12035, 2021, doi:10.1088/1757-899X/1125/1/012035.

R. Parlika, Mustafid, and B. Rahmat, “Detect Areas of Upward and Downward Fluctuations in Bitcoin Prices Using Patterned Datasets,” 2023 IEEE 9th Information Technology International Seminar (ITIS), pp. 1–6, Oct. 2023, doi: 10.1109/itis59651.2023.10420129.

N. X. Vinh, “Information Theoretic Measures for Clusterings Comparison : Variants , Properties , Normalization and Correction for Chance,” vol. 11, pp. 2837–2854, 2010.

A. Rosenberg and J. Hirschberg, “V-Measure : A conditional entropy-based external cluster evaluation measure,” no. June, pp. 410–420, 2007.

C. Yeh and M. Yang, “Evaluation measures for cluster ensembles based on a fuzzy generalized Rand index,” Appl. Soft Comput. J., vol. 57, pp. 225–234, 2017, doi: 10.1016/j.asoc.2017.03.030.

D. Chicco and G. Jurman, “A statistical comparison between Matthews correlation coefficient ( MCC ), prevalence threshold , and Fowlkes – Mallows index,” J. Biomed. Inform., vol. 144, no. June, p. 104426, 2023, doi: 10.1016/j.jbi.2023.104426.

E. Koo and G. Kim, “Centralized decomposition approach in LSTM for Bitcoin price prediction,” Expert Syst. Appl., vol. 237, no. PA, p. 121401, 2024, doi: 10.1016/j.eswa.2023.121401.

P. J. R and V. S. Das, “Cryptocurrency Price Prediction Using Long-Short Term Memory Model,” Int. J. Res. Sci. Innov. |, vol. V, no. Vii, pp. 70–72, 2018, [Online]. Available: www.rsisinternational.org

I. E. Livieris, N. Kiriakidou, S. Stavroyiannis, and P. Pintelas, “An Advanced CNN-LSTM Model for Cryptocurrency Forecasting,” 2021. doi: 10.3390/electronics10030287.

C. Wang, D. Shen, and Y. Li, “Aggregate Investor Attention and Bitcoin Return: The Long Short-term Memory Networks Perspective,” Financ. Res. Lett., vol. 49, no. May, p. 103143, 2022, doi:10.1016/j.frl.2022.103143.

S. H. Othman, R. Z. Radzi, D. Stiawan, and T. Sutikno, “Hybrid gated recurrent unit bidirectional-long short-term memory model to improve cryptocurrency prediction accuracy,” vol. 12, no. 1, pp. 251–261, 2023, doi: 10.11591/ijai.v12.i1.pp251-261.

M. J. Hamayel, “A Novel Cryptocurrency Price Prediction Model Using GRU , LSTM and bi-LSTM Machine Learning Algorithms,” pp. 477–496, 2021.

Y. Yue, X. Li, D. Zhang, and S. Wang, “How cryptocurrency affects economy? A network analysis using bibliometric methods,” Int. Rev. Financ. Anal., vol. 77, no. 71988101, p. 101869, 2021, doi: 10.1016/j.irfa.2021.101869.

D. F. Gerritsen, R. A. C. Lugtigheid, and T. Walther, “Can Bitcoin Investors Profit from Predictions by Crypto Experts?,” Financ. Res. Lett., vol. 46, May 2022, doi: 10.1016/j.frl.2021.102266.

Y. Wang, C. Wang, A. Sensoy, S. Yao, and F. Cheng, “Can investors’ informed trading predict cryptocurrency returns? Evidence from machine learning,” Res. Int. Bus. Financ., vol. 62, no. August 2021, p. 101683, 2022, doi: 10.1016/j.ribaf.2022.101683.

J. Bowden and R. Gemayel, “Sentiment and trading decisions in an ambiguous environment: A study on cryptocurrency traders,” J. Int. Financ. Mark. Institutions Money, vol. 80, no. January, p. 101622, 2022, doi: 10.1016/j.intfin.2022.101622.

S. W. Akingbade, M. Gidea, M. Manzi, and V. Nateghi, “Communications in Nonlinear Science and Numerical Simulation Why topological data analysis detects financial bubbles ?,” Commun. Nonlinear Sci. Numer. Simul., vol. 128, no. October 2023, p. 107665, 2024, doi: 10.1016/j.cnsns.2023.107665.

Z. Zhang and R. Zhao, “International Review of Financial Analysis Good volatility , bad volatility , and the cross section of cryptocurrency,” Int. Rev. Financ. Anal., vol. 89, no. June, p. 102712, 2023, doi: 10.1016/j.irfa.2023.102712.

H. Chaudhari and M. Crane, “Cross-correlation dynamics and community structures of cryptocurrencies,” J. Comput. Sci., vol. 44, p. 101130, 2020, doi: 10.1016/j.jocs.2020.101130.

R. Parlika and P. W. Atmaja, “Realtime monitoring of Bitcoin prices on several Cryptocurrency markets using Web API, Telegram Bot, MySQL Database, and PHP-Cronjob,” Proceeding - 6th Inf. Technol. Int. Semin. ITIS 2020, pp. 253–257, 2020, doi:10.1109/ITIS50118.2020.9321109.

R. Gemayel and A. Preda, “International Review of Financial Analysis Performance and learning in an ambiguous environment : A study of cryptocurrency traders ✩,” Int. Rev. Financ. Anal., vol. 77, no. July, p. 101847, 2021, doi: 10.1016/j.irfa.2021.101847.

R. Parlika, “Crypto-Patterned-Dataset https://bit.ly/dsi5.” [Online]. Available: https://github.com/pddsi5/Crypto-Patterned-Dataset/blob/main/README.md