Answers are grounded in this paper and cite their sources.
This analysis compares deep learning models, highlighting their effectiveness in predicting coin failures, suggesting significant implications for investors.
In recent years, the rapid rise in the popularity of cryptocurrencies has drawn increasing attention from investors, entrepreneurs, and the public. However, this rapid growth comes with risk: Many coins fail early and become what are known as ``dead coins", defined by a lack of recorded activity for more than a year. A substantial number of cryptocurrencies fail to reach the one-year mark, leading to significant financial losses for investors. This study compares deep neural network architectures Long Short-Term Memory (LSTM), Bidirectional LSTM (BiLSTM), and Gated Recurrent Unit (GRU) to estimate the likelihood of a coin's failure within 10 days. Among the three models, LSTM exhibited the most fluctuating and comparatively lower performance. Using the previous 180 days of data as input, GRU achieved the highest point accuracy of 0.7134, whereas BiLSTM exhibited the best performance when evaluated across input sequence lengths varying from 10 to 180 days, reaching an average accuracy of 0.676. These findings show how recurrent architectures can be used to anticipate short-term failures in cryptocurrency markets.
No takes yet. Share an insight, caveat, or question.
Konuk et al. (2025) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: