Customer projects are major do-it-yourself (DIY) undertakings, involving a considerable amount of planning, money, and effort. Examples of customer projects include installing a paver patio, tiling kitchen walls, building a backyard football toss, and renovating the bathroom. Such projects require several cross-category purchases through multiple shopping trips (Wolf and McQuitty 2011). Identifying and understanding customer projects provides novel insights into customer behavior, which in turn, improve advertising planning and the development of effective marketing decisions. In this work, we seek to contribute to the growing literature that utilizes graph mining techniques to identify persistent multi-trip purchase patterns (Dhar et al. 2014; Kim, Kim, and Chen 2012; Oestreicher-Singer et al. 2013; Videla-Cavieres and Ríos 2014). We do so, by presenting an analytical method for the identification of customer projects from retail sales transactions and by demonstrating the utility, validity, and replicability of our approach using a data set of 20,000 customers across two years from a Fortune 500 specialty retailer.