You work for a global footwear retailer and need to predict when an item will be out of stock based on historical inventory dat a. Customer behavior…

TFX ModelValidator is a tool that allows you to compare new models against a baseline model and

evaluate their performance on different metrics and data slices1. You can use this tool to validate

your models before deploying them to production and ensure that they meet your expectations and

requirements.

k-fold cross-validation is a technique that splits the data into k subsets and trains the model on k-1

subsets while testing it on the remaining subset. This is repeated k times and the average

performance is reported2. This technique is useful for estimating the generalization error of a model,

but it does not account for the dynamic nature of customer behavior or the potential changes in data

distribution over time.

Using the last relevant week of data as a validation set is a simple way to check the model’s

performance on recent data, but it may not be representative of the entire data or capture the long-

term trends and patterns. It also does not allow you to compare the model with a baseline or

evaluate it on different data slices.

Using the entire dataset and treating the AUC ROC as the main metric is not a good practice because

it does not leave any data for validation or testing. It also assumes that the AUC ROC is the only

metric that matters, which may not be true for your business problem. You may want to consider

other metrics such as precision, recall, or revenue.