In baseball, the goal of the pitcher is to prevent runs. To do so, they must make it difficult for the batter to hit the ball. There are a variety of techniques and methods the pitcher can use to achieve their goal including manipulating the speed that they throw, changing the spin to create horizontal and vertical movement, and modifying their release point. My investigation uses machine learning algorithms to cluster groups of similar pitches together and calculate the expected number of runs that pitch should induce. From there, we can map pitches, or the average pitch for a given pitcher, to each cluster and calculate the expected runs with the final output being an easy to read grader that coaches and players can use. The grader can help baseball teams with determining which pitchers to recruit, scouting opposing pitchers to determine their weaknesses, and develop their own pitchers more effectively in a quantitative manner.