Correcting meter to transformer ties has been a problem electric utilities have been facing for years. Now that more companies are adopting Advanced Meter Infrastructure (AMI), granular voltage data makes the problem more appealing. Having correct meter to transformer ties can positively impact distribution planning, customer experience and reliability. It can also help maintain the accuracy of Geospatial Information Systems (GIS). While other analyses have been completed, they typically relied on more than just interval voltage data. The purpose of this analysis was to see how accurately incorrect ties could be identified and corrected with interval voltage and location data. Using a mixture of Dynamic Time Warping (DTW) and Euclidean Distance (ED) a criteria-based model was designed to detect and correct errors in American Electric Powers Ohio operating company. These results were used to build a Random Forest Classifier that can be utilized in other operating companies. The intent is to build a analytics based approach to identifying and correct issues without sending employees to the field for manual verification.