Mississippian reservoirs are among the most prolific oil and gas producing reservoirs in the mid-continent. Understanding regionally and locally where Mississippian sweet spots for petroleum exploitation are located is a key to fully exploiting their resources. Assuming a petroleum system exists, rock properties as determined from petrophysical logs are one of the most important factors in determining how a well will perform. As decline curves can be used to predict future performance of a well, based on direct production measurements, petrophysical log signatures should be related to predicting future well performance. Based on this premise, a novel approach using petrophysics and data science is tested to find and rank similar packages of rock to each other based on percent sameness using cosine similarity and K-means clustering. This study explores the methodology, practicality, and limitations of evaluating the relationship of basic petrophysical log signature packages to production volumes within the Anadarko Basin, as well as the greater ancient “Oklahoma Basin” using an integrated petrophysical, data science, and sequence stratigraphic approach. The workflow discussed herein is designed to search through a data set comprised of 25,673 petrophysical well logs in search of Gamma Ray signatures that are correlative with that of a designated Mississippian sweet spot from one given well. Not only is this method important in the search for petroleum, but it can also be applied to other commercial means of global resource exploitation.