The tendency of machine learning algorithms to lose accuracy over time as a result of changing business factors such as changing market conditions. Model drift includes concept drift (link) and data drift (link).
Added Perspectives
Most importantly, data teams must rinse and repeat. They must identify data drift—i.e., changes in market conditions or other aspects of your environment—then pull their ML models out of production, re-train those models and re-implement them. Figure 1 illustrates the three stages of the ML lifecycle.