Intelligent Selling Services in SAP Commerce Cloud: AI-Powered Personalisation

Personalisation in e-commerce isn’t optional — it’s expected. Customers assume the products they see are relevant to them. When they’re not, they leave. Intelligent Selling Services (ISS) is Commerce Cloud’s built-in AI layer that makes product recommendations, search results, and merchandising adapt to each customer’s behaviour.

This guide covers what ISS actually does, how its four core capabilities work, and what results to expect.

TL;DR: SAP has over 34,000 AI customers across its portfolio, with plans to reach 100,000 by 2027 (SAP News, 2024). Intelligent Selling Services (ISS) is Commerce Cloud’s AI personalisation engine — it handles product recommendations, adaptive search, dynamic merchandising, and context-driven personalisation. ISS analyses clickstream and purchase data to show each customer the products most likely to convert.

What Is Intelligent Selling Services?

SAP has over 34,000 AI customers with plans to reach 100,000 by 2027 (SAP News, 2024). ISS is one of the ways AI shows up in Commerce Cloud.

Intelligent Selling Services is a cloud-based AI service integrated into SAP Commerce Cloud. It analyses customer behaviour — clicks, searches, cart additions, purchases — and uses that data to personalise four aspects of the shopping experience:

1. Product recommendations — “Customers who bought X also bought Y”
2. Adaptive search — search results ranked by individual relevance
3. Dynamic merchandising — category pages that reorder products per customer
4. Context-driven personalisation — content and offers tailored to browsing context

ISS runs as a cloud service, not on the Commerce Cloud application server. It ingests behavioural events from the storefront, processes them through machine learning models, and returns personalised results via API.

How Do Product Recommendations Work?

Global retail e-commerce reached $6.334 trillion in 2024 (eMarketer, 2024). Product recommendations directly influence what share of that spending goes to your store.

ISS offers several recommendation strategies:

Collaborative filtering. “Customers who bought this also bought…” Based on purchase patterns across your entire customer base. Works best with high transaction volumes — the more data, the better the recommendations.

Content-based filtering. Recommends products with similar attributes (category, brand, price range) to what the customer has viewed or purchased. Works even with limited purchase history.

Context-aware recommendations. Adapts recommendations based on where the customer is in their journey — homepage, product detail page, cart, or post-purchase. A recommendation on the cart page (cross-sell) differs from one on the homepage (discovery).

Trending products. Surfaces products with rising demand across the platform. Useful for seasonal items, new launches, or viral products.

The recommendation engine runs continuously, updating its models as new behavioural data arrives. You don’t need to retrain models manually — ISS handles this automatically.

How Does Adaptive Search Differ from Standard Search?

Gartner has named SAP a Leader in Digital Commerce for 11 consecutive years (SAP News, 2025). ISS’s adaptive search is one of the differentiators that keeps Commerce Cloud competitive.

Standard search (Solr) returns the same results for every customer who searches the same term. Adaptive search adds a personalisation layer on top:

Personalised ranking. Two customers searching “running shoes” see different products first — one sees trail shoes (because they’ve browsed outdoor gear), the other sees road shoes (because they’ve viewed marathon content).

Behavioural boost. Products the customer has previously viewed, carted, or purchased in the same category get boosted in search results. Not to the point of filter bubbles — but enough to surface the most relevant options first.

Merchandising rules. Merchandisers can set rules that interact with adaptive search: boost new arrivals, promote high-margin products, or suppress out-of-stock items. These rules combine with AI-driven personalisation.

Category page optimisation. Adaptive search doesn’t just affect the search box — it also reorders products on category pages. When a customer browses “Men’s Shoes,” the products are ranked by predicted relevance to that specific customer.

What Does Dynamic Merchandising Do?

E-commerce accounts for 34% of B2B revenue globally (McKinsey, 2024). Dynamic merchandising ensures that revenue-driving products are visible to the right customers.

Dynamic merchandising uses ISS data to automatically optimise product placement:

Automated product sorting. Category pages and search results are automatically sorted by predicted conversion probability for each customer. Products the customer is most likely to buy appear first.

Seasonal and trend-based adjustment. ISS detects rising demand patterns and adjusts product visibility accordingly. Winter jackets get boosted as temperatures drop; trending products rise in category rankings.

Inventory-aware placement. Products with low stock can be de-prioritised to avoid overselling. Products with excess stock can be boosted to accelerate sell-through.

A/B testing support. Run merchandising experiments — compare AI-driven sorting against manual curation to validate that ISS actually improves conversion for your specific catalogue and customer base.

What Results Can You Expect?

Sixty-one per cent of B2B buyers prefer a rep-free buying experience (Gartner, 2025). When customers self-serve, AI-driven personalisation replaces the sales rep’s product knowledge.

ISS impact varies by catalogue size, traffic volume, and baseline personalisation maturity. Typical improvements:

• Click-through rate on recommendations: 2–5x improvement vs. static “top sellers” lists
• Search-to-cart conversion: 10–20% improvement with adaptive search vs. standard Solr
• Average order value: 5–15% increase through contextual cross-sell recommendations
• Time to find products: measurable reduction when adaptive search surfaces relevant results faster

These aren’t guaranteed numbers — they depend on your data volume, catalogue depth, and customer behaviour patterns. ISS needs traffic to learn. Low-traffic stores see smaller gains because the models have less data to work with.

FAQ

Is ISS included with Commerce Cloud?

ISS is available as part of SAP Commerce Cloud. Specific features and capabilities depend on your Commerce Cloud edition and licensing. Check with SAP or your implementation partner for feature availability.

How much traffic does ISS need to be effective?

ISS needs meaningful behavioural data to train its models. Stores with fewer than 1,000 monthly sessions may see limited personalisation quality. The recommendation engine improves continuously as more data is collected.

Can I control what ISS recommends?

Yes. Merchandisers can set business rules that override or influence ISS recommendations: boost specific brands, suppress certain products, set minimum margin thresholds, or pin products to specific slots. AI and manual curation work together.

Does ISS work with the Composable Storefront?

Yes. ISS exposes its capabilities through APIs that the Composable Storefront consumes. Recommendation carousels, personalised search results, and dynamic category sorting are all available through the storefront’s standard components.

How does ISS compare to third-party recommendation engines?

ISS has the advantage of deep integration with Commerce Cloud — it shares the same product catalogue, customer data, and order history. Third-party engines (Algolia Recommend, Nosto, Dynamic Yield) may offer more sophisticated algorithms or broader cross-platform support but require additional integration and data synchronisation.