Catalogs are messy. A shopper clicks a lipstick because it is on discount, ignores a better product because the thumbnail is dull, buys a cable for someone else, and later returns to search for something completely unrelated. A recommender system sees all of this as signal. Some of it is useful. Some of it is noise wearing a very confident jacket. ...
A product page has a photo. A description. A category. A few user clicks. Maybe a rating, if the platform is lucky. The ordinary recommender-system reflex is to pour all of that into the model and call it “multimodal.” Image embedding here, text embedding there, concatenate, pool, sum, ship. Then, when performance disappoints, add another feature extractor, another graph layer, another auxiliary objective, and hope the leaderboard blushes. ...