Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Jurnal Ilmiah Manajemen Kesatuan
Amrullah Amrullah
Universitas Muhammadiyah Sumatera Utara, Indonesia
Economics, Econometrics & Finance Social Sciences

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Comparing Linear Regression and Trend Moment with MAPE Optimization for Bitcoin Price Forecasting Accuracy Baihaqi Ammy; Amrullah Amrullah; M. Firza Alpi
Jurnal Ilmiah Manajemen Kesatuan Vol. 13 No. 6 (2025): JIMKES Edisi November 2025
Publisher : LPPM Institut Bisnis dan Informatika Kesatuan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37641/jimkes.v13i6.3968

Abstract

The cryptocurrency market, particularly Bitcoin, exhibits extreme volatility, necessitating robust forecasting tools for informed trading decisions. This study aimed to evaluate the performance of linear regression and trend moment models in predicting Bitcoin prices using daily data from 2022 to 2024. Historical closing prices were collected from reliable cryptocurrency exchanges, cleaned to ensure consistency, and augmented with relative strength index and moving average convergence divergence indicators to enhance predictive accuracy. The models were trained on 2022–2023 data and tested on 2024 data, with forecasting accuracy measured using the Mean Absolute Percentage Error metric. The findings revealed that linear regression achieved a lower error rate of 36.44% compared to Trend Moment’s 39.21%, demonstrating superior performance in stable and trending market conditions. Both models struggled with volatile price swings, though linear regression proved more adaptable when incorporating technical indicators. These results suggest that linear regression offers a practical, computationally efficient solution for short-term Bitcoin price forecasting, particularly for retail traders. Future research could explore hybrid models or additional predictors to improve accuracy in volatile markets, contributing to accessible forecasting tools for the cryptocurrency domain.
Co-Authors Baihaqi Ammy M. Firza Alpi