Metabolomics is a growing field where researchers identify and quantify the metabolites in a given system or organism. The use of LC-MS/MS (liquid chromatography, tandem mass spectrometry) helps to achieve this via untargeted and targeted approaches. Untargeted analysis involves running samples and looking at global detection of metabolites, whereas targeted runs focus on precise measurement of one or a small group of related metabolites. Most available software heavily utilizes MS fragmentation spectra and biological network mapping to make putative compound matches. Although the LC aspect of metabolomics is important in separating compounds to allow for distinguishable MS peaks, actual retention time data is rarely used to assist in metabolite identification. This is due to several variables that affect retention time, from mobile phase gradients to more system specific changes such as different columns and instruments. The goal of this project was to create a robust, scalable model that could identify retention time ranges for each molecule based on the retention times of standards separated on the same LC system. This model addresses most of the problems with retention time models listed above with the use of standards, which are typically a part of most procedures. This pilot program identified 536 compounds as false hits, reducing the number of putative matches to 51.7% (total of 1035 matches). This false hit detection rate persisted across three different tissue types of this experiment.