How to maximise recommendations generated by the Related Products model without relying on content-based filtering.
The only way to optimise the Related Products model to generate more recommendations without using content-based filtering is by sending more click and conversion events. This approach may seem counterintuitive but Related Products is a hybrid model (content-based and collaborative), which means more events are needed to compensate when one part of the model isn't used. By adding content-based filtering, you can also get recommendations for the products that don’t have enough events and even improve the recommendations for the ones that do.
The way the hybrid model works is by combining, for each product, the recommendations based on events with the recommendations based on the attributes you choose. Meaning some products will have a set of recommendations from only one model, whereas some will have a combination of the two.