Application of Data-Mining Techniques on Predictive Analysis
Journal Title: International Research Journal of Applied and Basic Sciences - Year 2013, Vol 4, Issue 12
Abstract
This paper compares five different predictive data-mining techniques on some data sets. The characteristics of these data are few predictor variables, many predictor variables, highly collinear variables, very redundant variables and presence of outliers. First, these data are preprocessed and prepared. In the first step after, preprocessing data, we must select a minimal number of variables that can completely predict the response variable. Different data-mining techniques is used in this research including: multiple linear regression MLR, principal component regression (PCR), an unsupervised technique based on the principal component analysis; ridge regression, the Partial Least Squares (PLS), and the Nonlinear Partial Least Squares (NLPLS). Each technique has different methods of usage; these different methods were used on each data set first and the best method in each technique was noted and used for global comparison with other techniques for the same data set.
Authors and Affiliations
Mohammad Reza pourmir *| Computer Engineering Department, Faculty of Engineering, Zabol University, Zabol, Iran, mohammadrezapourmir@yahoo.com, Ahmad Kazemi| Centeral Department Of Sistan&Balochestan Telecommunication Co., Zahedan, Iran
Keywords
Related Articles
- EP ID EP5831
- DOI -
- Views 250
- Downloads 8
Influence of Meta Learning the effectiveness of dialectical behavior therapy in reducing symptoms in patients with borderline personality disorder
This study was a quasi-experimental design and pretest-posttest control group. The population consisted of patients under treatment at a counseling center in Tehran. According to the inclusion criteria, 15 subjects were...
Evaluatingthe relationship betweenliquidityandactivityratiosandstock returnsin thepharmaceutical and chemicalindustries
In addition of predict in g future and changes in the market, understanding the exchange from different aspects can reduce investments risk and achieve greater efficiency. One of the most important factors in choosing th...
The Effects of age, gender, education level and work experience of accountant on ethical decision making by using fuzzy logic
Despite the amount of accounting ethics research conducted over many years, ways to improve the measurement instruments and to make them appropriate for application in other cultures or countries are still needed. Accoun...
Designing A Multi-Agent Mechanism For Energy Management In A Photovoltaic System
Several studies have been conducted on the energy management, but procedures performed on management have been less by the artificial intelligence algorithms. In the present study, we try to solve the management problem...
Comparing two methods of circular and transects samplings in terms of biodiversity indices
Species diversity is considered as an index to compare the ecological conditions of forest ecosystems. This study aims to preserve biodiversity by considering 60 plots with an area of 316 ha in Darabkola forest, which wa...