Natural phenomenon’s and swarms behavior are the warm area of research among the researchers. A large number of algorithms have been developed on the account of natural phenomenon’s and swarms behavior. These algorithms have been implemented on the various computational problems for the sake of solutions and provided significant results than conventional methods but there is no such algorithm which can be applied for all of the computational problems. In 2009, a new algorithm was developed on the behalf of theory of gravity and was named gravitational search algorithm (GSA) for continuous optimization problems. In short span of time, GSA algorithm gain popularity among researchers and has been applied to large number of problems such as clustering, classification, parameter identification etc. This paper presents the compendious survey on the GSA algorithm and its applications as well as enlightens the applicability of GSA in data clustering & classification.

Most of the researchers/ scientists are facing data explosion problem presently. Large amount of data is available in the world i.e. data from science, industry, business, survey and many other areas. The main task is how to prune the data and extract valuable information from these data which can be used for decision making. The answer of this question is data mining. Data Mining is popular topic among researchers. There is lot of work that cannot be explored in the field of data mining till now. A large number of data mining tools/software’s are available which are used for mining the valuable information from the datasets and draw new conclusion based on the mined information. These tools used different type of classifiers to classify the data. Many researchers have used different type of tools with different classifiers to obtained desired results. In this paper three classifiers i.e. Bayes, Neural Network and Tree are used with two datasets to obtain desired results. The performance of these classifiers is analyzed with the help of Mean Absolute Error, Root Mean-Squared Error, Time Taken, Correctly Classified Instance, Incorrectly Classified instance and Kappa Statistic parameter.

In the field of Machine learning & Data Mining, lot of work had been done to construct new classification techniques/ classifiers and lot of research is going on to construct further new classifiers with the help of nature inspired technique such as Genetic Algorithm, Ant Colony Optimization, Bee Colony Optimization, Neural Network, Particle Swarm Optimization etc. Many researchers provided comparative study/ analysis of classification techniques. But this paper deals with another form of analysis of classification techniques i.e. parametric and non parametric classifiers analysis. This paper identifies parametric & non parametric classifiers that are used in classification process and provides tree representation of these classifiers. For the analysis purpose, four classifiers are used in which two of them are parametric and rest of are non-parametric in nature.