Skip to main content
QUICK REVIEW

[论文解读] Predicting Stock Market Time-Series Data using CNN-LSTM Neural Network Model

A Aadhitya, R. Rajapriya|arXiv (Cornell University)|May 21, 2023
Stock Market Forecasting Methods被引用 11
一句话总结

本论文提出一种 CNN-LSTM 神经网络来预测股票市场时间序列数据,使用 1-D 股票特征转化为张量以供 CNN 使用,并在多个数据集上进行评估,考虑实时数据部署。

ABSTRACT

Stock market is often important as it represents the ownership claims on businesses. Without sufficient stocks, a company cannot perform well in finance. Predicting a stock market performance of a company is nearly hard because every time the prices of a company stock keeps changing and not constant. So, its complex to determine the stock data. But if the previous performance of a company in stock market is known, then we can track the data and provide predictions to stockholders in order to wisely take decisions on handling the stocks to a company. To handle this, many machine learning models have been invented but they didn't succeed due to many reasons like absence of advanced libraries, inaccuracy of model when made to train with real time data and much more. So, to track the patterns and the features of data, a CNN-LSTM Neural Network can be made. Recently, CNN is now used in Natural Language Processing (NLP) based applications, so by identifying the features from stock data and converting them into tensors, we can obtain the features and then send it to LSTM neural network to find the patterns and thereby predicting the stock market for given period of time. The accuracy of the CNN-LSTM NN model is found to be high even when allowed to train on real-time stock market data. This paper describes about the features of the custom CNN-LSTM model, experiments we made with the model (like training with stock market datasets, performance comparison with other models) and the end product we obtained at final stage.

研究动机与目标

  • 激励并设计一个 CNN-LSTM 方法来预测股票市场时间序列数据。
  • 探索将 1-D 股票数据转换为适合 CNN 的张量的预处理策略。
  • 在不同数据集和实时数据源上评估模型性能。
  • 将 CNN-LSTM 与其他模型进行比较并讨论部署注意事项。

提出的方法

  • 构建一个自定义的 CNN-LSTM 架构,包含 3 个 CNN 层(64,128,64),核大小为 3,随后是 2 个 Bi-LSTM 层,每层 100 个单元。
  • 使用 100 行滑动窗口和特征均值编码,将 1-D 股票数据(强调 Close 列)转换为 [100,1] 张量。
  • 使用均方误差损失进行训练,采用 Adam 优化器,并用 MSE、MAE 与 R2 指标进行评估。
  • 对 Alpha Vantage TIME_SERIES_DAILY 全模式和 Kaggle 数据集进行预处理,处理 NULL 值,并进行 TimeDistributed CNN 的缩放/重塑。
  • 将模型保存为 HDF5,并提供本地和 Kubernetes 环境的 Docker 与 Helm 部署。

实验结果

研究问题

  • RQ1与其他模型相比,CNN-LSTM 架构在捕捉股票时间序列数据中的特征和时间模式方面的表现如何?
  • RQ2哪些预处理策略(张量构建和滑动窗口)能提升 1-D 股票数据上 CNN 的有效性?
  • RQ3模型在不同股票市场(NYSE、NASDAQ、NIFTY)和实时数据源上的表现如何?
  • RQ4用于现实世界使用的 CNN-LSTM 股票预测器的实际部署考虑因素(Docker/Kubernetes)有哪些?

主要发现

  • 在各数据集上 MSE 分数约为 0.001–0.035,MAE 约 0.075,R2 在某些测试中约为 0.935。
  • Table II 报告 MSE 0.035, MAE 0.075, Variance 0.935370, R2 0.9353, Max Error 0.174930 针对测试设置。
  • Table III 显示数据集特定的 MSE 分数(例如 NIFTY 0.001, NASDAQ 0.1565, IBM 0.0027, RELIANCE 0.0145)。
  • Table IV 将 CNN-LSTM 与自定义模型进行比较,CNN-LSTM MSE 0.035 vs LSTM 0.045 与 XGBoost 0.047。
  • Table V 将 CNN-LSTM 与其他模型进行比较,MSE 0.035(均值)对比不同基线(如 LBL-LSTM 0.017 训练/0.026 测试,LSTM 去中心化 0.0003)。
  • 论文展示了通过 Docker 镜像和 Helm 图表进行部署,支持 Kubernetes 部署和基于 CI 的镜像发布。

更好的研究,从现在开始

从阅读论文到最终审阅,大幅缩短您的研究时间。

无需绑定信用卡

本解读由 AI 生成,并经人工编辑审核。