Knowledge discovery in database is an iterative process. The steps involved in it are selection of data from various resources where operation to be performed, preprocessing or data cleaning in which the remove the unwanted data, transform / consolidate into a new format for processing, data mining – identify desired result and interpretation or evaluation to produce result. Data mining means collecting relevant information from unstructured data. So it is able to help achieve specific objectives. The purpose of a data mining effort is normally either to create a descriptive model or a predictive model. A descriptive model presents, in concise form, main characteristics of the data set. The purpose of a predictive model is to allow data miner to predict an unknown (often future) value of a specific variable, the target variable 29. A. Predictive techniques – Classification- allows the user to classify large populous data into a model which sorts them into a predefined set of classes. Classification maps the data into various predefined categories. The goal of classification is to find a general mapping to predict classes for unknown data objects and to find a compact and understandable class model for each class. Classification process employs supervised learning and classification, mostly used for predictive modeling. Some of the popular algorithmic models employed in classification are Decision Trees, Neural Networks, Bayesian classification, SVM and classification based on association. Regression – Regression is a technique used for predictive model. It includes SVM. The idea is to model a relationship between one or more attributes in the dataset, so that the change in one of the variables can be used to predict the values of the other. It can also be used to predict the advantages and disadvantages. Since, real world prediction requires the integration of many complex attributes, different models have to be used to implement prediction. CART is a decision tree algorithm which uses classification trees to classify the dependent (response) variables and regression trees to predict the values of the response variables continuously. Different regression methods used are logistic regression, linear regression, multivariate linear regression, nonlinear regression and multivariate nonlinear regression 30. Forecasting – Forecasting estimates the future value based on a record patterns. Prediction estimates numeric and ordered future values based on the future values base on patterns of data set. Time series data can be used for business gain if the data is converted into information and then into knowledge. Time Series Analysis- Time series analysis is the process of using statistical techniques to model and explain a time-dependent series of data points. Time series forecasting is a method of using a model to generate predictions (forecasts) for future events based on known past events. For example stock market. Prediction – It is one of a data mining techniques that discover the relationship between independent variables and the relationship between dependent and independent variables. This model based on continuous or ordered values.