In 1901 the Ullmann reaction was initially discovered by the homocoupling of two aryl halides, under harsh conditions (high temperature, long reaction times, etc.). Harsh conditions tend to be leveraged with copper catalyzed couplings due to the sluggish nature of copper to undergo oxidative addition. There are competitors to the Ullmann reaction, like the Buchwald-Hartwig reaction which uses palladium catalyst that undergoes oxidative addition more readily making reaction conditions much milder. However, the inexpensive cost of copper makes copper catalyzed Ullmann reactions the more attractive alternative. Over the years since the first reaction the Ullmann reaction has been more refined to the point where the reaction condition is more favorable, this is due in part to the addition of bidentate ligands. For example, anionic type ligands such as diketones can aid in the catalysis of C-N couplings by stabilizing higher oxidation states of copper. Understanding the structure function relationship of diketones can help enhance the functionality of this scaffold and allow for more robust C-N coupling to become more generalized. Using machine learning clustering algorithms, we employed the development of a commercial library of diketone ligands. Using High-Throughput experimentation we aim to develop a computational model to aid in the understanding of Diketone ligands and their role in Ullmann Catalysis.