Autoregressive and neural network models: A comparative study with linearly lagged series
Institute of Electrical and Electronics Engineers Inc.
Time series analysis such as stock price forecasting is an important part of financial research. In this regard, autoregressive (AR) and neural network (NN) models offer contrasting approaches to time series modeling. Although AR models remain widely used, NN models and their variant long short-term memory (LSTM) networks have grown in popularity. In this paper, we compare the performance of AR, NN, and LSTM models in forecasting linearly lagged time series. To test the models we carry out extensive numerical experiments based on simulated data. The results of the experiments reveal that despite the inherent advantage of AR models in modeling linearly lagged data, NN models perform just as well, if not better, than AR models. Furthermore, the NN models outperform LSTMs on the same data. We find that a simple multi-layer perceptron can achieve highly accurate out of sample forecasts. The study shows that NN models perform well even in the case of linearly lagged time series. © 2021 IEEE.
This conference paper is not available at CUD collection. The version of scholarly record of this conference paper is published in2021 International Conference on Innovation and Intelligence for Informatics, Computing, and Technologies, 3ICT 2021 (2021), available online at: https://doi.org/10.1109/3ICT53449.2021.9581812
AR, ARIMA, forecast, LSTM, neural network, time series
Kamalov, F., Gurrib, I., & Thabtah, F. (2021). Autoregressive and neural network models: A comparative study with linearly lagged series. Paper presented at the 2021 International Conference on Innovation and Intelligence for Informatics, Computing, and Technologies, 3ICT 2021, 175-180. https://doi.org/10.1109/3ICT53449.2021.9581812