A Review and New Contribution on Conic Multivariate Adaptive Regression Splines (CMARS): A Powerful Tool for Predictive Data Mining

This study aims at critically reviewing the research that has been conducted to improve the backward part of the Multivariate Adaptive Regression Splines (MARS) method that leads to the development of Conic MARS (CMARS) method. Several studies have been carried out to apply the method to various fields of study including life, finance, industry, business, energy, and environment. Moreover, the performance of CMARS method is empirically compared to that of Classification and Regression Trees, Generalized Additive Models and Infinite Kernal Learning for classification, and to that of Multiple Linear Regression and MARS for prediction. For this purpose, real-life and simulation data sets with different characteristics such as size, the number and type of predictors, application areas are used. Comparative studies indicate that the CMARS method is a very promising tool for establishing computational models between variables of complex data sets. Yet, in other studies, CMARS have been improved and extended further. The improvement leads to the development of Bootstrapping CMARS method to build less complex CMARS models while the extension robustifies CMARS to enable modeling random input and output variables more precisely. To sum up, this review indicates that currently the CMARS method is a powerful alternative to the MARS algorithm as well as the other predictive data mining tools, and thus, deserves more attention to evaluate and develop it even further.

[1]  Gerhard-Wilhelm Weber,et al.  CMARS and GAM & CQP - Modern optimization methods applied to international credit default prediction , 2011, J. Comput. Appl. Math..

[2]  Peter Craven,et al.  Smoothing noisy data with spline functions , 1978 .

[3]  Gerhard-Wilhelm Weber,et al.  Electricity Price Modelling for Turkey , 2011, OR.

[4]  R. Tibshirani,et al.  Generalized Additive Models: Some Applications , 1987 .

[5]  G. Weber,et al.  CMARS: a new contribution to nonparametric regression with multivariate adaptive regression splines supported by continuous optimization , 2012 .

[6]  Wei-Yin Loh,et al.  Classification and regression trees , 2011, WIREs Data Mining Knowl. Discov..

[7]  Robert Tibshirani,et al.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd Edition , 2001, Springer Series in Statistics.

[8]  Angel R. Martinez,et al.  Computational Statistics Handbook with MATLAB , 2001 .

[9]  S. T. Buckland,et al.  An Introduction to the Bootstrap. , 1994 .

[10]  İnci Batmaz,et al.  Overview of Knowledge Discovery in Databases Process and Data Mining for Surveillance Technologies and EWS , 2013 .

[11]  Nur Evin Özdemirel,et al.  Defect Cause Modeling with Decision Tree and Regression Analysis , 2007 .

[12]  Clifford H. Thurber,et al.  Parameter estimation and inverse problems , 2005 .

[13]  Yurii Nesterov,et al.  Interior-point polynomial algorithms in convex programming , 1994, Siam studies in applied mathematics.

[14]  P. Taylan,et al.  New approaches to regression by generalized additive models and continuous optimization for modern applications in finance, science and technology , 2007 .

[15]  Leo Breiman,et al.  Classification and Regression Trees , 1984 .

[16]  Inci Batmaz,et al.  A review of data mining applications for quality improvement in manufacturing industry , 2011, Expert Syst. Appl..

[17]  Gerhard-Wilhelm Weber,et al.  EVALUATING THE CMARS PERFORMANCE FOR MODELING NON‐LINEARITIES , 2010 .

[18]  Gerhard-Wilhelm Weber,et al.  A new approach to multivariate adaptive regression splines by using Tikhonov regularization and continuous optimization , 2010 .

[19]  Kweku-Muata Osei-Bryson,et al.  Evaluation of decision trees: a multi-criteria approach , 2004, Comput. Oper. Res..

[20]  G. Weber,et al.  RCMARS: Robustification of CMARS with different scenarios under polyhedral uncertainty set , 2011 .

[21]  Gerhard-Wilhelm Weber,et al.  Infinite kernel learning via infinite and semi-infinite programming , 2010, Optim. Methods Softw..

[22]  Klaus Schittkowski,et al.  More test examples for nonlinear programming codes , 1981 .

[23]  J. Friedman.  Multivariate adaptive regression splines , 1990 .