Performance of Deep Learning models with transfer learning for multiple-step-ahead forecasts in monthly time series

03/18/2022
by   Martín Solís, et al.
0

Deep Learning and transfer learning models are being used to generate time series forecasts; however, there is scarce evidence about their performance prediction that it is more evident for monthly time series. The purpose of this paper is to compare Deep Learning models with transfer learning and without transfer learning and other traditional methods used for monthly forecasts to answer three questions about the suitability of Deep Learning and Transfer Learning to generate predictions of time series. Time series of M4 and M3 competitions were used for the experiments. The results suggest that deep learning models based on TCN, LSTM, and CNN with transfer learning tend to surpass the performance prediction of other traditional methods. On the other hand, TCN and LSTM, trained directly on the target time series, got similar or better performance than traditional methods for some forecast horizons.

READ FULL TEXT
research
03/26/2021

Multi-source Transfer Learning with Ensemble for Financial Time Series Forecasting

Although transfer learning is proven to be effective in computer vision ...
research
01/25/2023

Recursive deep learning framework for forecasting the decadal world economic outlook

Gross domestic product (GDP) is the most widely used indicator in macroe...
research
04/07/2022

Forecasting new diseases in low-data settings using transfer learning

Recent infectious disease outbreaks, such as the COVID-19 pandemic and t...
research
01/31/2022

Deep Learning Macroeconomics

Limited datasets and complex nonlinear relationships are among the chall...
research
07/09/2021

Transformer-Based Behavioral Representation Learning Enables Transfer Learning for Mobile Sensing in Small Datasets

While deep learning has revolutionized research and applications in NLP ...
research
03/14/2023

Understanding Model Complexity for temporal tabular and multi-variate time series, case study with Numerai data science tournament

In this paper, we explore the use of different feature engineering and d...
research
04/29/2022

Task Embedding Temporal Convolution Networks for Transfer Learning Problems in Renewable Power Time-Series Forecast

Task embeddings in multi-layer perceptrons for multi-task learning and i...

Please sign up or login with your details

Forgot password? Click here to reset