On-shelf availability (OSA) is key in the Consumer Packaged Goods (CPG) industry. In this project, out of stock (OOS) patterns are identified, grouped, and analyzed in order to gain meaningful insights to improve OSA. The approach is to normalize a time-series dataset, search for similar OOS patterns, and analyze some particular patterns. By focusing on a particular type of pattern, in which an OOS event happens within a pre-defined time period, some behaviors are observed from this study: first, as the time period is decreased (from 7 days to 4 days), the similar OOS pattern happens more frequently; second, a steep inventory drop appears to be an infrequent event, based on the sample dataset. The purpose of this study is to draw a common approach that could possibly be used by practitioners; the firm could possibly use the index and similarity search approach to identify patterns in all GTINs. The potential insights of this study are: first, stock outs don’t seem to be predictable based solely on DC data, since steep inventory drops appear to be infrequent events; and second, a firm could possibly use the identified patterns to connect point of sale data with OOS events and then identify the drivers of out of stocks.