Pre-silicon analog and mixed signal (AMS) design verification involves exorbitant compute and manual effort and time to verify the design against the specification of an IC. This paper proposes a Machine Learning (ML) based behavioral model to predict the output response of AMS circuits that can be used in the automated verification process including automation of waveform review sign-off, and fast simulation models. The ML based behavior model is constructed using the time domain features. To address both linear and non-linear behaviors of the circuit, this paper proposes waveform segmentation and circuit partitioning approaches as a divide and conquer strategy to identify the appropriate suite of ML algorithms for the different segments. The best performing ML models in each segment are concatenated to stitch the complete response. We also propose SNR as a metric to evaluate the prediction accuracy. An OpAmp benchmark circuit has been used as a proof of concept to demonstrate this approach and an average SNR measure of 32dB has been obtained in the prediction of the output waveform.