Return trajectory and the forecastability of bitcoin returns
本文利用拓扑数据分析球映射器，发现比特币回报符号的可预测性依赖于历史回报轨迹，并展示了将历史轨迹映射作为预测模型能提高方向预测准确性。
Abstract This paper tests the extent to which the ability to correctly predict subsequent bitcoin (BTC) return signs is dependent upon historic BTC return trajectories. Using topological data analysis ball mapper (TDABM), we demonstrate that the performance of random forest and logit regression models varies according to return trajectory. A novel use of TDABM as a forecast model shows that mapping historic return trajectories can also produce more accurate directional return forecasts. Our approach highlights how the predictability of BTC price change direction is dependent on return trajectories. Visualizing historic return trajectories when forming and evaluating return forecasts is imperative.