• Corpus ID: 235727483

MegazordNet: combining statistical and machine learning standpoints for time series forecasting

  title={MegazordNet: combining statistical and machine learning standpoints for time series forecasting},
  author={Angelo Garangau Menezes and Saulo Martiello Mastelini},
Forecasting financial time series is considered to be a difficult task due to the chaotic feature of the series. Statistical approaches have shown solid results in some specific problems such as predicting market direction and singleprice of stocks; however, with the recent advances in deep learning and big data techniques, new promising options have arises to tackle financial time series forecasting. Moreover, recent literature has shown that employing a combination of statistics and machine… 

Figures and Tables from this paper

Noise reduction for LSTM using Wavelet Transform and Singular Spectrum Analysis

The LSTM variant of RNN had the ability to learn the long-term dependencies that RNN cells had difficulty learning, and have become the default method for time-series analysis using deep networks as they have good predictive ability across a multitude of use cases.



Conditional Time Series Forecasting with Convolutional Neural Networks

This paper compares the performance of the WaveNet model to a state-of-the-art fully convolutional network (FCN), and an autoregressive model popular in econometrics and shows that the model is much better able to learn important dependencies in between financial time series resulting in a more robust and accurate forecast.

A novel time series forecasting model with deep learning

Stock Market Trend Prediction Using High-Order Information of Time Series

A new method to simplify noisy-filled financial temporal series via sequence reconstruction by leveraging motifs (frequent patterns), and then utilize a convolutional neural network to capture spatial structure of time series is introduced.

A deep learning framework for financial time series using stacked autoencoders and long-short term memory

A novel deep learning framework where wavelet transforms, stacked autoencoders and long-short term memory are combined for stock price forecasting and shows that the proposed model outperforms other similar models in both predictive accuracy and profitability performance.

Stock market's price movement prediction with LSTM neural networks

This article studies the usage of LSTM networks on that scenario, to predict future trends of stock prices based on the price history, alongside with technical analysis indicators, and the results are promising.

Hybrid Neural Networks for Learning the Trend in Time Series

TreNet is proposed, a novel end-toend hybrid neural network to learn local and global contextual features for predicting the trend of time series, and demonstrates its effectiveness by outperforming CNN, L STM, the cascade of CNN and LSTM, Hidden Markov Model based method and various kernel based baselines on real datasets.

Deep Learning for Time-Series Analysis

A review of the main Deep Learning techniques is presented, and some applications on Time-Series analysis are summaried, making it clear that Deep Learning has a lot to contribute to the field.

Statistical and Machine Learning forecasting methods: Concerns and ways forward

It is found that the post-sample accuracy of popular ML methods are dominated across both accuracy measures used and for all forecasting horizons examined, and that their computational requirements are considerably greater than those of statistical methods.