[论文解读] Forecasting Economics and Financial Time Series: ARIMA vs. LSTM

Sima Siami‐Namini, Akbar Siami Namin|arXiv (Cornell University)|Mar 16, 2018

Stock Market Forecasting Methods参考文献 22被引用 59

一句话总结

这篇论文比较 ARIMA 与 LSTM 在经济与金融时间序列预测中的表现，结果显示 LSTM 在预测精度方面显著优于 ARIMA，平均误差降低约 84–87%。同时报告训练轮次对性能没有一致影响。

ABSTRACT

Forecasting time series data is an important subject in economics, business, and finance. Traditionally, there are several techniques to effectively forecast the next lag of time series data such as univariate Autoregressive (AR), univariate Moving Average (MA), Simple Exponential Smoothing (SES), and more notably Autoregressive Integrated Moving Average (ARIMA) with its many variations. In particular, ARIMA model has demonstrated its outperformance in precision and accuracy of predicting the next lags of time series. With the recent advancement in computational power of computers and more importantly developing more advanced machine learning algorithms and approaches such as deep learning, new algorithms are developed to forecast time series data. The research question investigated in this article is that whether and how the newly developed deep learning-based algorithms for forecasting time series data, such as "Long Short-Term Memory (LSTM)", are superior to the traditional algorithms. The empirical studies conducted and reported in this article show that deep learning-based algorithms such as LSTM outperform traditional-based algorithms such as ARIMA model. More specifically, the average reduction in error rates obtained by LSTM is between 84 - 87 percent when compared to ARIMA indicating the superiority of LSTM to ARIMA. Furthermore, it was noticed that the number of training times, known as "epoch" in deep learning, has no effect on the performance of the trained forecast model and it exhibits a truly random behavior.

研究动机与目标

• 评估传统时间序列模型（ARIMA）与深度学习方法（LSTM）在经济与金融数据上的相对预测精度。
• 量化使用 LSTM 相对于 ARIMA 的平均预测误差改进。
• 探究训练动态（epochs）对时间序列预测中 LSTM 模型性能的影响。

提出的方法

• 对经济/金融时间序列进行 ARIMA 与 LSTM 预测的回顾与经验比较。
• 使用标准预测误差指标量化性能差异。
• 分析训练轮次对 LSTM 性能的影响（发现 epoch 数量表现出随机行为/无显著影响）。

实验结果

研究问题

• RQ1 LSTM 模型是否在预测经济与金融时间序列方面优于 ARIMA？
• RQ2 使用 LSTM 相比 ARIMA 的误差降低幅度有多大？
• RQ3 在该领域中，训练轮次如何影响 LSTM 的预测性能？

主要发现

• LSTM 在预测经济与金融时间序列方面优于 ARIMA。
• 使用 LSTM 时误差率的平均降低被报告为 84–87% 相对于 ARIMA。
• 训练轮次的数量对 LSTM 性能没有一致性影响（随机行为）。