Zhang Xiangyue, Kang Yuyun, Li Chao, Wang Wenjing, Wang Keqing
School of Information Science and Engineering, Linyi University, Linyi, Shandong, China.
School of Logistics, Linyi University, Linyi, Shandong, China.
PLoS One. 2025 May 2;20(5):e0319008. doi: 10.1371/journal.pone.0319008. eCollection 2025.
Cryptocurrency is a new type of asset that has emerged with the advancement of financial technology, creating significant opportunities for research. bitcoin is the most valuable cryptocurrency and holds significant research value. However, due to the significant fluctuations in bitcoin's value in recent years, predicting its value and ensuring the reliability of these predictions, which have become crucial, have gained increasing importance. A method that combines Long Short-term Memory (LSTM) with conformal prediction is proposed in this paper. Initially, the high-dimensional features in the dataset are divided using the Spearman correlation coefficient method, and features below 0.75 and above 0.95 are excluded. Subsequently, an LSTM model is built, and data are fed into it and the data is used to train the model to generate predictions. Finally, the predicted values generated by the LSTM are fed into the conformal prediction model, and confidence intervals for these values are generated to verify their reliability. In the conformal prediction model, the quantile loss of the loss function is defined, and an Average Coverage Interval (ACI) predictor is designed to improve the accuracy of the results. The experiments are conducted using data from CoinGecko, which is a publicly available data. The results show that the LSTM-conformal prediction (LSTM-CP) combination improves reliability.
加密货币是随着金融技术发展而出现的一种新型资产，为研究创造了重要机遇。比特币是最具价值的加密货币，具有重大研究价值。然而，由于近年来比特币价值波动巨大，预测其价值并确保这些预测的可靠性变得至关重要，且愈发重要。本文提出了一种将长短期记忆（LSTM）与共形预测相结合的方法。首先，使用斯皮尔曼相关系数法对数据集中的高维特征进行划分，排除相关性低于0.75和高于0.95的特征。随后，构建LSTM模型，将数据输入该模型并用于训练模型以生成预测。最后，将LSTM生成的预测值输入共形预测模型，生成这些值的置信区间以验证其可靠性。在共形预测模型中，定义了损失函数的分位数损失，并设计了平均覆盖区间（ACI）预测器以提高结果的准确性。实验使用来自CoinGecko的公开可用数据进行。结果表明，LSTM-共形预测（LSTM-CP）组合提高了可靠性。
