• P.Pandi Selvi

In order to predict future results in a better way, predictive data mining techniques are used. In this paper, the predictive analytic approach is used in waste water treatment. The parameter values were calculated first. After computing, if the range value of these parameters were at its desired level, relevant to the predictive value, the water was in its purified form. It can be predicted to be used in the future. Waste water samples were collected from industries, and sample dataset was first created containing 500 records. Preprocessing operation is then carried out to remove any unwanted information in the data set. In order to perform classification between the predictive data and the current data three models were utilized. They were Linear regression model, multilayer perceptron model and SMOreg model. The results of the three models were then compared. With the results, it is evident that linear regression and multilayer perceptron models prove to be better in predicting the data.

Predictive data mining, preprocessing, Linear regression model, Waste water treatment

"Waste Water Treatment - An Application Of Predictive Data Mining", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.5, Issue 9, page no.679-683, September-2018, Available :http://www.jetir.org/papers/JETIR1809241.pdf

"Waste Water Treatment - An Application Of Predictive Data Mining", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.5, Issue 9, page no. pp679-683, September-2018, Available at : http://www.jetir.org/papers/JETIR1809241.pdf