Miniaturization of electronic products has resulted in proliferation of package-on-package (PoP) architectures in portable electronics. In this study, daisy-chained double-stack PoP components have been used for early-identification of drop-shock impact damage. Time-spectral feature vector based damage pre-cursors have been identified and measured under applied shock stimulus. Experimental strain data has been acquired using strain sensors, digital image correlation. Continuity has been measured suing high-speed instrumentation for identification of failure in the PoP assemblies. The time-evolution of spectral content of the damage pre-cursors has been studied using joint time frequency analysis (JTFA). The Karhunen-Loéve transform (KLT) has been used for feature reduction and de-correlation of the feature vectors for input to an artificial neural network. The artificial neural net has been trained for failure-mode identification using simulated data-sets created from error-seeded models with specific failure modes. The neural net has then been used to identify and classify the failure modes experimentally observed in tested board assemblies. Supervised learning of multilayer neural net in conjunction with parity has been used to identify the hard-separation boundaries between failure mode clusters in the de-correlated feature space. Pre-failure feature space has been classified for different fault modes in PoP assemblies subjected to drop and shock.