Instance-Based Regression by Partitioning Feature Projections Export

@article{citeulike:3431569, abstract = {A new instance-based learning method is presented for regression problems with high-dimensional data. As an instance-based approach, the conventional method, KNN, is very popular for classification. Although KNN performs well on classification tasks, it does not perform as well on regression problems. We have developed a new instance-based method, called Regression by Partitioning Feature Projections (RPFP) which is designed to meet the requirement for a lazy method that achieves high levels of accuracy on regression problems. RPFP gives better performance than well-known eager approaches found in machine learning and statistics such as MARS, rule-based regression, and regression tree induction systems. The most important property of RPFP is that it is a projection-based approach that can handle interactions. We show that it outperforms existing eager or lazy approaches on many domains when there are many missing values in the training data.}, author = {Uysal, \.{I}lhan and G\"{u}venir}, citeulike-article-id = {3431569}, citeulike-linkout-0 = {http://dx.doi.org/10.1023/B:APIN.0000027767.87895.b2}, comment = {This has a nice comparison of a lot of different systems on a large number of classification problems. They normalize their data in a particular way, though, so you have to be a little careful in reading their table.}, day = {1}, doi = {10.1023/B:APIN.0000027767.87895.b2}, journal = {Applied Intelligence}, keywords = {artificial-intelligence, classification, machine-learning, symbolic-regression}, month = {July}, number = {1}, pages = {57--79}, posted-at = {2008-10-20 20:21:54}, priority = {2}, title = {Instance-Based Regression by Partitioning Feature Projections}, url = {http://dx.doi.org/10.1023/B:APIN.0000027767.87895.b2}, volume = {21}, year = {2004} }

TY - JOUR ID - citeulike:3431569 L3 - citeulike-article-id:3431569 N2 - A new instance-based learning method is presented for regression problems with high-dimensional data. As an instance-based approach, the conventional method, KNN, is very popular for classification. Although KNN performs well on classification tasks, it does not perform as well on regression problems. We have developed a new instance-based method, called Regression by Partitioning Feature Projections (RPFP) which is designed to meet the requirement for a lazy method that achieves high levels of accuracy on regression problems. RPFP gives better performance than well-known eager approaches found in machine learning and statistics such as MARS, rule-based regression, and regression tree induction systems. The most important property of RPFP is that it is a projection-based approach that can handle interactions. We show that it outperforms existing eager or lazy approaches on many domains when there are many missing values in the training data. IS - 1 JF - Applied Intelligence EP - 79 TI - Instance-Based Regression by Partitioning Feature Projections VL - 21 SP - 57 KW - artificial-intelligence KW - classification KW - machine-learning KW - symbolic-regression N1 - This has a nice comparison of a lot of different systems on a large number of classification problems. They normalize their data in a particular way, though, so you have to be a little careful in reading their table. AU - Uysal, İlhan AU - Güvenir PY - 2004/07/01/ UR - http://dx.doi.org/10.1023/B:APIN.0000027767.87895.b2 ER -