@article{DEHOOG20191451,
title = "Data visualization and forecast combination for probabilistic load forecasting in GEFCom2017 final match",
journal = "International Journal of Forecasting",
volume = "35",
number = "4",
pages = "1451 - 1459",
year = "2019",
issn = "0169-2070",
doi = "https://doi.org/10.1016/j.ijforecast.2019.02.004",
url = "http://www.sciencedirect.com/science/article/pii/S0169207019300226",
author = "Julian de Hoog and Khalid Abdulla",
keywords = "Load forecasting, Probabilistic forecasting, Data visualisation, Neural network quantile forecast, Model selection, Data preparation, Forecast combination",
abstract = "This paper describes the methods used by Team Cassandra, a joint effort between IBM Research Australia and the University of Melbourne, in the GEFCom2017 load forecasting competition. An important first phase in the forecasting effort involved a deep exploration of the underlying dataset. Several data visualisation techniques were applied to help us better understand the nature and size of gaps, outliers, the relationships between different entities in the dataset, and the relevance of custom date ranges. Improved, cleaned data were then used to train multiple probabilistic forecasting models. These included a number of standard and well-known approaches, as well as a neural-network based quantile forecast model that was developed specifically for this dataset. Finally, model selection and forecast combination were used to choose a custom forecasting model for every entity in the dataset."
}