Search Results - subject:"Gradient boosting"

GEFCom2012 hierarchical load forecasting : gradient boosting machines and Gaussian processes

Lloyd, James Robert - In: International journal of forecasting 30 (2014) 2, pp. 369-374

Persistent link: https://www.econbiz.de/10010510900

Hedonic price models and indices based on boosting applied to the Dutch housing market

Kagie, M.; Wezel, M.C. van - Erasmus University Rotterdam, Econometric Institute - 2006

We create a hedonic price model for house prices for six geographical submarkets in the Netherlands. Our model is based on a recent data mining technique called boosting. Boosting is an ensemble technique that combines multiple models, in our case decision trees, into a combined prediction....

Persistent link: https://www.econbiz.de/10005450900

Hedonic price models and indices based on boosting applied to the Dutch housing market

Kagie, Martijn; van Wezel, van Wezel, M.C. - Faculteit der Economische Wetenschappen, Erasmus … - 2006

Persistent link: https://www.econbiz.de/10010731586

Boosting the accuracy of hedonic pricing models

Kagie, Martijn; van Wezel, van Wezel, M.C.; Potharst, … - Faculteit der Economische Wetenschappen, Erasmus … - 2005

Hedonic pricing models attempt to model a relationship between object attributes and the object's price. Traditional hedonic pricing models are often parametric models that suffer from misspecification. In this paper we create these models by means of boosted CART models. The method is explained...

Persistent link: https://www.econbiz.de/10010731892

Boosting the accuracy of hedonic pricing models

Wezel, M.C. van; Kagie, M.; Potharst, R. - Erasmus University Rotterdam, Econometric Institute - 2005

Analysis, Data Mining, Gradient Boosting, Ensemble Learning, Hedonic Pricing, Marketing, Pricing. 1 Introduction Hedonic …-of-sample prediction performance. In this paper we use a relatively new non-parametric technique, gradient boosting in combi- nation with … literature. In principle, the gradient boosting algorithm can be used with any di erentiable loss function L and any base learner …

Persistent link: https://www.econbiz.de/10005000463