学习使用订单流图像表示预测短期波动率
Learning to Predict Short-Term Volatility with Order Flow Image Representation
AI总结：
本文提出将订单流数据转换为图像并映射至颜色通道，结合3层CNN、ResNet-18和ConvMixer等模型预测比特币短期波动率，实验表明CNN结合聚合特征表现最佳，RMSPE达0.85+/-1.1。
摘要：
引言：本文解决了使用订单流信息预测比特币价格短期已实现波动率的挑战性问题。价格固有的随机性和反持久性给准确预测带来了困难。方法：为此，我们提出了一种将固定时间间隔内的订单流数据（快照）转换为图像的方法。订单流包括交易规模、交易方向和限价订单簿，并被映射到图像的颜色通道中。这些图像随后被用于训练一个简单的3层卷积神经网络（CNN）以及更先进的ResNet-18和ConvMixer，并额外补充人工设计的特征。这些模型与经典的GARCH、在原始数据上训练的多层感知机以及一种将当前波动率作为预测值的朴素猜测方法进行了对比评估。结果：实验使用2021年1月的价格数据进行，并通过均方根百分比误差（RMSPE）评估模型性能。结果表明，我们以订单流表示结合CNN作为预测模型取得了最佳性能，对于包含聚合特征的模型，RMSPE为0.85+/-1.1，对于无特征补充的模型为1.0+/-1.4。带有特征补充的ConvMixer紧随其后。相比之下，朴素猜测方法的RMSPE为1.4+/-3.0。
英文摘要：
Introduction: The paper addresses the challenging problem of predicting the short-term realized volatility of the Bitcoin price using order flow information. The inherent stochastic nature and anti-persistence of price pose difficulties in accurate prediction. Methods: To address this, we propose a method that transforms order flow data over a fixed time interval (snapshots) into images. The order flow includes trade sizes, trade directions, and limit order book, and is mapped into image colour channels. These images are then used to train both a simple 3-layer Convolutional Neural Network (CNN) and more advanced ResNet-18 and ConvMixer, with additionally supplementing them with hand-crafted features. The models are evaluated against classical GARCH, Multilayer Perceptron trained on raw data, and a naive guess method that considers current volatility as a prediction. Results: The experiments are conducted using price data from January 2021 and evaluate model performance in terms of root mean square error (RMSPE). The results show that our order flow representation with a CNN as a predictive model achieves the best performance, with an RMSPE of 0.85+/-1.1 for the model with aggregated features and 1.0+/-1.4 for the model without feature supplementation. ConvMixer with feature supplementation follows closely. In comparison, the RMSPE for the naive guess method was 1.4+/-3.0.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
