Multicriteria approaches for predictive model generation: A comparative experimental study

This study investigates the evaluation of machine learning models based on multiple criteria. The criteria included are: predictive model accuracy, model complexity, and algorithmic complexity (related to the learning/adaptation algorithm and prediction delivery) captured by monitoring the execution...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2014 IEEE Symposium on Computational Intelligence in Multi-Criteria Decision-Making (MCDM) s. 64 - 71
Hlavní autoři: Al-Jubouri, Bassma, Gabrys, Bogdan
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.12.2014
Témata:
Accuracy
Artificial neural networks
Complexity theory
Mathematical model
Optimization
Prediction algorithms
Predictive models
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:This study investigates the evaluation of machine learning models based on multiple criteria. The criteria included are: predictive model accuracy, model complexity, and algorithmic complexity (related to the learning/adaptation algorithm and prediction delivery) captured by monitoring the execution time. Furthermore, it compares the models generated from optimising the criteria using two approaches. The first approach is a scalarized multi objective optimisation, where the models are generated from optimising a single cost function that combines the criteria. On the other hand the second approach uses a Pareto-based multi objective optimisation to trade-off the three criteria and to generate a set of non-dominated models. This study shows that defining universal measures for the three criteria is not always feasible. Furthermore, it was shown that, the models generated from Pareto-based multi objective optimisation approach can be more accurate and more diverse than the models generated from scalarized multi objective optimisation approach.
DOI:10.1109/MCDM.2014.7007189