Data Drift

Data Drift concept is used in Data Science practice, and it is one of the most expected behaviors in every data modelling. One must have automated ways to keep tracking and identifying Data Drifts as after Data Drift, there are high chances the model will not produce or predict the expected accuracy which was planned. Wrong prediction means wrong decisions.

We all know what a Drift is. Drift is about shifting or moving from one point to another but not in a standard approach. This term is mostly referred in Data Science practice, to evaluate trained vs actual., performances of Machine Learning (ML) Models.

Data Drift is also known as covariate shift, virtual drift, or virtual concept drift. When we create and run a ML model, just like any traditional query, it inputs a dataset and outputs a dataset. In ` ML modelling, we select certain data elements to build its logic. Data Drift is about change of data within same select data element.

For example, there were 10 types of products available in a dataset while training the model but when you go in Production, the list of products increases from 10 to 15. So, the model was trained based on 10 types of products and now it has 5 more, so for sure the model which was giving e.g., 85% accuracy now might have gone down below, maybe 70%. Please note in this case the model didn’t change, nor did its data elements i.e., product. It’s not like that instead of products, now salary data has started to come in. No, still relevant product is coming in but now 5 more product types got added. So, it’s not because there is something wrong with your model but because there is a Data Drift. A list of products which were not expected while training the model are now in there and model is unable to recognize those. To cater for this, you can retrain your model again in the training environment quickly and deploy it again.