QBE North America is a global insurer offering a broad of spectrum insurance products. To support the variety of products that it offers, QBE utilizes several processing systems which has consequentially resulted in a challenging data environment. Working off this challenging data environment, QBE has found it difficult to extract meaningful insights from its data in a wholistic sense. As an insurance company, continuous monitoring of the types of losses that are incurred is vital to ensure that QBE is successful, so a focus has been placed on being able to produce quality data. Literature research and market trends have shown that machine learning techniques can effectively aid in improving data quality if implemented properly. To improve the quality of the cause of loss data at QBE, this project aimed to design, create, and implement an effective and efficient data governance process to maintain a standardized hierarchy of cause of loss values, which can then be used to extract meaningful and actionable insights throughout the organization. An interactive dashboard utilizing the resulting standardized cause of loss hierarchy was also created to showcase opportunities around cause of loss insights that were previously not possible due to poor data.