Fatih, Muhamad Ardi Al
Unknown Affiliation

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

Found 1 Documents
Search

Comparison of Airdrop Coin Prices in Cryptocurrency Using LSTM: A Case Study of Grass, Not Pixel, and Dogs Coins Fatih, Muhamad Ardi Al; Paradise, Paradise; Nugroho, Nicolaus Euclides Wahyu
MALCOM: Indonesian Journal of Machine Learning and Computer Science Vol. 6 No. 3 (2026): MALCOM July 2026
Publisher : Institut Riset dan Publikasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57152/malcom.v6i3.2748

Abstract

The distribution of airdrops across the cryptocurrency ecosystem often leads to extreme price volatility, complicating data-driven strategic decision-making for investors. This study aims to implement a Long Short-Term Memory (LSTM) architecture to predict airdrop coin prices and integrate the results into an interactive dashboard-based Decision Support System (DSS). The research methodology employs a Recursive Multi-step Forecasting strategy to model nonlinear time-series data across three case studies: GRASS, NOT PIXEL, and DOGS, covering the period from August 2024 to March 2026. Data were obtained via the CoinGecko API v3 and evaluated using MSE, MAE, RMSE, and MAPE metrics. The experimental results demonstrate that the LSTM model achieved high accuracy with MAPE values of 10.75% for GRASS, 6.29% for NOT PIXEL, and 6.73% for DOGS, with NOT PIXEL recording the best overall performance. The primary contribution of this research is the transformation of numerical projections into automated decision signals (Strong Buy, Hold, Caution, and Strong Sell) integrated into the DSS. In conclusion, this system serves as an effective tool for mitigating investment risk, providing strategic guidance to airdrop cryptocurrency users amid dynamic market fluctuations.