An analysis of deep neural networks for predicting trends in time series data

  title={An analysis of deep neural networks for predicting trends in time series data},
  author={Kouame Hermann Kouassi and D. Moodley},
  • Kouame Hermann Kouassi, D. Moodley
  • Published 2020
  • Computer Science, Mathematics
  • ArXiv
  • Recently, a hybrid Deep Neural Network (DNN) algorithm, TreNet was proposed for predicting trends in time series data. While TreNet was shown to have superior performance for trend prediction to other DNN and traditional ML approaches, the validation method used did not take into account the sequential nature of time series data sets and did not deal with model update. In this research we replicated the TreNet experiments on the same data sets using a walk-forward validation method and tested… CONTINUE READING
    1 Citations
    Automatic deep learning for trend prediction in time series data
    • PDF


    Hybrid Neural Networks for Learning the Trend in Time Series
    • 57
    • Highly Influential
    • PDF
    On the use of cross-validation for time series predictor evaluation
    • 279
    Stock Market Trend Prediction Using High-Order Information of Time Series
    • 21
    • PDF
    Robust Online Time Series Prediction with Recurrent Neural Networks
    • 71
    • PDF
    Real-time crash risk prediction on arterials based on LSTM-CNN.
    • 28
    Improving Multi-Step Prediction of Learned Time Series Models
    • 115
    • PDF
    Stock market's price movement prediction with LSTM neural networks
    • 183
    Forecasting Wavelet Transformed Time Series with Attentive Neural Networks
    • 17
    Prediction of Index Trend based on LSTM Model for Extracting Image Similarity Feature
    • 4
    Reinforced Two-Step-Ahead Weight Adjustment Technique for Online Training of Recurrent Neural Networks
    • 51