Product recommendation in e-commerce is a widely applied technique which has been shown to bring benefits in both product sales and customer satisfaction. In this work, we address a particular product recommendation setting—small-scale retail websites where the small amount of returning customers makes traditional user-centric personalization techniques inapplicable. We apply an item-centric product recommendation strategy which combines two well-known methods—association rules and text-based similarity—for generating recommendations based on a single ‘seed’ product. Furthermore, we adapt the proposed approach to also recommend products based on a set of ‘seed’ products in a user’s shopping basket. We demonstrate the effectiveness of the recommendation approach in the product-seeded and basket-seeded scenarios through online and offline evaluation studies with real customer data.