K Nearest Neighbor is one of the simplest method for classification as well as regression problem. That is the reason it is widely adopted. KNN is a supervised method that uses estimation based on values of neighbors. Though KNN came into existence in decade of 1990, it still demands improvements based on domain in which it is being used. Now the researchers have invented methods in which multiple techniques can be combined in some order such that advantages of each technique covers the disability of techniques being combined for example, KNN-Kernel based algorithms are being used for clustering. Though heavy applicability of KNN in classification problems, it is not that much used in function estimation problems. This paper is an attempt in using KNN as function estimation problem. The approach is made for linear as well as nonlinear regression problem. We have made an assumption that supervisor data given is reliable. We have considered here two dimensional data to illustrate the idea which is equally applicable to n-dimensional data for some large but finite n. © 2015 IEEE.