Multi-Target Regression via Random Linear Target Combinations
This work addresses multi-target regression problems, such as ecological modelling and energy forecasting, with an incremental improvement over existing methods.
The paper tackles multi-target regression by proposing an ensemble method that creates new target variables via random linear combinations of existing targets, achieving significant performance improvements over strong baselines and favorable comparisons to state-of-the-art methods on 12 datasets.
Multi-target regression is concerned with the simultaneous prediction of multiple continuous target variables based on the same set of input variables. It arises in several interesting industrial and environmental application domains, such as ecological modelling and energy forecasting. This paper presents an ensemble method for multi-target regression that constructs new target variables via random linear combinations of existing targets. We discuss the connection of our approach with multi-label classification algorithms, in particular RA$k$EL, which originally inspired this work, and a family of recent multi-label classification algorithms that involve output coding. Experimental results on 12 multi-target datasets show that it performs significantly better than a strong baseline that learns a single model for each target using gradient boosting and compares favourably to multi-objective random forest approach, which is a state-of-the-art approach. The experiments further show that our approach improves more when stronger unconditional dependencies exist among the targets.