A product obsolescence forecast system comprises machine instructions stored in a non-transitory computer readable storage medium. A processor executes the machine instructions to access data items related to a first product and one or more second products designated as similar to the first product, the first product and each of the one or more second products belonging to a same class of products; extract data elements from the data items; reformat the data elements as analyzable data elements and store the analyzable data elements in an analyzable data structure; apply a probabilistic model to selected ones of the analyzable data elements to provide a forecast obsolescence date for the first product; and using the forecast obsolescence date, determine one or more impacts based on the forecast obsolescence date.