Choose storage tiers from predicted file access

A cloud storage service can keep each user file in a fast, expensive tier or a cheap, slow archive tier, and moving data or reading from the archive costs money. Decide which tier each file should live in. Frame it as predicting how likely a file is to be read soon, then turning that prediction into a placement decision that minimizes expected cost. Cover the features, labels, the model, how the decision threshold follows from the price of each tier, and how you check that it saves money.