Prediction technique for time series data sets using regression models

Abstract

Data mining techniques are the set of algorithms intended to find the hidden knowledge from the data sets, some of the popular techniques of data mining are prediction, sequential patterns, association, classification, clustering, and decision tree. Classification and regression are used for forecasting. Regression algorithms are based on various regression model i.e. linear regressions, non-linear regression, multiple regressions, logistic regression, and probabilistic regression. Forecasting of time series data sets with improved parameters has been discussed in the proposed methodology. For preprocessing the data set, sliding window or classification algorithms are used. Then coefficients values for the regression model are identified to fit the regression model.