Look-Alike modeling is one of the most popular methods for expanding the size of ad segments to provide advertisers increased reach. Facebook introduced Look Alike modeling to its platform in 2013 and several ad-tech providers offer a version of look-alike modeling natively within their products. However, as we will show in this post, Look Alike models in practice often result in brittle and inaccurate segments. A variety of other machine learning (ML) approaches -- including classification and uplift -- almost always yield superior performance compared to Look Alike models. Because of these limitations, we believe Look Alikes should be used sparingly, only when other techniques are unavailable.