We present a sequential method for approximating an unknown function sequentially using random noisy samples. Unlike the traditional function approximation methods, the current method constructs the approximation using one sample at a time. This results in a simple numerical implementation using only vector operations and avoids the need to store the entire data set. The method is thus particularly suitable when data set is exceedingly large. Furthermore, we present a general theoretical framework to define and interpret the method. Both upper and lower bounds of the method are established for the expectation of the results. Numerical examples are provided to verify the theoretical findings. (C) 2018 Elsevier Inc. All rights reserved.