Comparison of predictive models for forecasting timeseries data

Özen S., Atalay V., YAZICI A.

3rd International Conference on Big Data Research, ICBDR 2019, Cergy-Pontoise, France, 20 - 21 November 2019, pp.172-176 identifier

  • Publication Type: Conference Paper / Full Text
  • Volume:
  • Doi Number: 10.1145/3372454.3372482
  • City: Cergy-Pontoise
  • Country: France
  • Page Numbers: pp.172-176
  • Middle East Technical University Affiliated: Yes


© 2019 Association for Computing Machinery.Dramatic increase in data size enabled researchers to study analysis and prediction of big data. Big data can be formed in many ways and one alternative is through the use of sensors. An important aspect of data coming from sensors is that they are time-series data. Although forecasting based on time-series data has been studied widely, it is still possible to advance the state-ofthe- art by constructing new hybrid deep learning models. In this study, Random Forest, Convolutional Neural Network, Long Short Term Memory and hybrid Convolutional Neural Network- Long Short Term Memory models are applied and assessed on meteorological time-series data. Vector Auto-regression model and Multi-layer Perceptron model are used as the baseline forecasting methods for comparison purposes. Root Mean Square Error of the models for predictions are calculated for performance assessment which reveals the performance of these deep learning methods for forecasting based on time-series data.