The document discusses common issues that can arise from bad or problematic data when applying machine learning. It provides nine examples of real problems the author has encountered, ranging from simple issues like double counting cancelled orders, to more complex issues involving schema changes not being properly communicated. The key message is that even simple systems can encounter data problems, and it is important to audit data for errors or inconsistencies, detect schema changes, and clearly define metrics to avoid "garbage in, garbage out" situations that produce bad machine learning models.