Time Series Analysis- A Comparative Analysis Between ANN and RNN
Rafi, Taki Hasan; Rinky, Rehnuma Karim
Time series analysis is a significant undertaking in time series data mining and has pulled in extraordinary interests and huge endeavours during the most recent decades. However, data handling is a prior task in time series data. The main objective of time series analysis is to get intuition of the data. In recent years, AI models come with some enormous results in time series analysis. The motivation of this study is to determine a suitable artificial intelligence-based model for time-series related analysis. In this comparative analysis, authors utilize a publically accessible dataset to conduct the research. Author utilizes Long Short Term Memory (LSTM) model along with Feed Forward Neural Network (FNN), Time lagged Neural Network (TLNN) and Seasonal Artificial Neural Network (SANN) to compare the performance. However, some extensively used performance matrices such as Mean Squared Error (MSE), Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE) utilizes the evaluate all the models.
Time Series; Long short term memory; Recurrent neural network; Artificial neural network.