Rapid changes in technology have led to an increasingly fast pace of product introductions. New components offering added functionality, improved performance and quality are routinely available to a growing number of industry sectors (e.g., electronics, automotive, and defense industries). For long-life systems such as planes, ships, nuclear power plants, and more, these rapid changes help sustain the useful life, but at the same time, present significant challenges associated with managing change. Obsolescence of components and/or subsystems can be technical, functional, related to style, etc., and occur in nearly any industry. Over the years, many approaches for forecasting obsolescence have been developed. Inputs to such methods have been based on manual inputs and best estimates from product planners, or have been based on market analysis of parts, components, or assemblies that have been identified as higher risk for obsolescence on bill of materials. Gathering inputs required for forecasting is often subjective and laborious, causing inconsistencies in predictions. To address this issue, the objective of this research is to develop a new framework and methodology capable of identifying and forecasting obsolescence with a high degree of accuracy while minimizing maintenance and upkeep. To accomplish this objective, current obsolescence forecasting methods were categorized by output type and assessed in terms of pros and cons. A machine learning methodology capable of predicting obsolescence risk level and estimating the date of obsolescence was developed. The machine learning methodology is used to classify parts as active (in production) or obsolete (discontinued) and can be used during the design stage to guide part selection. Estimates of the date parts will cease production can be used to more efficiently time redesigns of multiple obsolete parts from a product or system. A case study of the cell phone market is presented to demonstrate how the methodology can forecast product obsolescence with a high degree of accuracy. For example, results of obsolescence forecasting in the case study predict parts as active or obsolete with a 98.3% accuracy and regularly predicts obsolescence dates within a few months.