Empirical decision model learning

One of the biggest challenges in the design of real-world decision support systems is coming up with a good combinatorial optimization model. Often enough, accurate predictive models (e.g. simulators) can be devised, but they are too complex or too slow to be employed in combinatorial optimization....

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Artificial intelligence Ročník 244; s. 343 - 367
Hlavní autoři: Lombardi, Michele, Milano, Michela, Bartolini, Andrea
Médium: Journal Article
Jazyk:angličtina
Vydáno: Amsterdam Elsevier B.V 01.03.2017
Elsevier Science Ltd
Témata:
Accuracy
Analytics
Approximation
Artificial neural networks
Combinatorial analysis
Combinatorial optimization
Complex systems
Computer simulation
Constraint programming
Decision support systems
Decision trees
Empirical analysis
Encapsulation
Linear programming
Local search
Machine learning
Mathematical models
Mixed integer
Mixed integer non-linear programming
Neural networks
Nonlinear programming
Optimization
SAT modulo theories
Simulators
Solvers
Workload
SAT modulo theories
Local search
Mixed integer non-linear programming
Constraint programming
Machine learning
Artificial neural networks
Combinatorial optimization
Decision trees
Complex systems
ISSN:0004-3702, 1872-7921
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:One of the biggest challenges in the design of real-world decision support systems is coming up with a good combinatorial optimization model. Often enough, accurate predictive models (e.g. simulators) can be devised, but they are too complex or too slow to be employed in combinatorial optimization. In this paper, we propose a methodology called Empirical Model Learning (EML) that relies on Machine Learning for obtaining components of a prescriptive model, using data either extracted from a predictive model or harvested from a real system. In a way, EML can be considered as a technique to merge predictive and prescriptive analytics. All models introduce some form of approximation. Citing G.E.P. Box [1] “Essentially, all models are wrong, but some of them are useful”. In EML, models are useful if they provide adequate accuracy, and if they can be effectively exploited by solvers for finding high-quality solutions. We show how to ground EML on a case study of thermal-aware workload dispatching. We use two learning methods, namely Artificial Neural Networks and Decision Trees and we show how to encapsulate the learned model in a number of optimization techniques, namely Local Search, Constraint Programming, Mixed Integer Non-Linear Programming and SAT Modulo Theories. We demonstrate the effectiveness of the EML approach by comparing our results with those obtained using expert-designed models.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0004-3702
1872-7921
DOI:10.1016/j.artint.2016.01.005