optimal pruned K-nearest neighbors: op-knn application to financial modeling

Eric Severin (1, 2, 3) , Yoan Miche (3) , Amaury Lendasse (3, 4) , Anti Sorjamaa (5) , Qi Yu (5)

1 CES - Centre d'économie de la Sorbonne
2 SAMOS - Statistique Appliquée et MOdélisation Stochastique
3 CIS - Laboratory of Computer and Information Science
4 DICE-MLG - Machine Learning Group
5 TKK - TKK Helsinki University of Technology

The paper proposes a methodology called OP-KNN, which builds a one hidden- layer feedforward neural network, using nearest neighbors neurons with extremely small com- putational time. The main strategy is to select the most relevant variables beforehand, then to build the model using KNN kernels. Multiresponse Sparse Regression (MRSR) is used as the second step in order to rank each kth nearest neighbor and finally as a third step Leave-One- Out estimation is used to select the number of neighbors and to estimate the generalization performances. This new methodology is tested on a toy example and is applied to financial modeling

Domaines: Economies et finances

Eric Severin, Yoan Miche, Amaury Lendasse, Anti Sorjamaa, Qi Yu. optimal pruned K-nearest neighbors: op-knn application to financial modeling. 2008. ⟨hal-00286065⟩