--- title: "Smart Recommender for Beauty & Cosmetics Verticals" slug: "smart-recommender-for-beauty-cosmetics-verticals-1" description: "Smart Recommender for beauty and cosmetics helps Insider One customers recommend skincare routines, shade-matched picks, and add-ons by page type." updated: 2026-10-20T14:04:02Z published: 2026-10-20T14:04:02Z canonical: "academy.insiderone.com/smart-recommender-for-beauty-cosmetics-verticals-1" --- > ## Documentation Index > Fetch the complete documentation index at: https://academy.insiderone.com/llms.txt > Use this file to discover all available pages before exploring further. # Smart Recommender for Beauty & Cosmetics Verticals Beauty and cosmetics purchases are highly personal. Skin type, skin tone, ingredients, and routines shape what each shopper buys, and many shoppers look for guidance before they commit. This article shows how to use Smart Recommender in Insider One to guide that discovery and build loyalty. It includes an A/B test walkthrough for skincare routine bundles and strategies for each page type. > [!NOTE] > **Before you start:** Make sure your product catalog includes the attributes this article filters on, such as Category, Routine Step, Skin Concern, and Kit ID. Create missing custom attributes on the **Product Attributes** page and mark them as filterable. ### What you can achieve with Smart Recommender #### Routine-based discovery Recommend related skincare and makeup products so shoppers can build a full routine, for example, a serum and moisturizer next to a cleanser. #### Trending products Highlight items gaining popularity this week, such as "Customer Favorites This Week," on the homepage and category pages. #### Recommendations by skin type or tone Use behavioral data and declared preferences to suggest, for example, matte foundations for oily skin or warm-toned lipsticks for medium skin tones. #### Re-engagement with new launches Show lapsed shoppers new arrivals that match their past purchases, such as new anti-aging serums for a skincare buyer. #### Complementary add-ons Recommend brushes, applicators, or primers on the cart page to raise average order value (AOV). #### A/B testing Compare recommendation logic, messaging, and widget placement, such as "Top Picks for You" versus "New in Skincare." ### Walkthrough: Increase AOV with skincare routine bundles Many shoppers want help building a complete skincare routine. Recommending the next product in the routine raises order value and customer satisfaction. This walkthrough tests two cross-sell strategies on cleanser product detail pages: - **Variant A:** Recommend toners. - **Variant B:** Recommend serums. #### Step 1: Create the recommendation strategies Navigate to **Recommendation Strategies** and click **Create**. Configure the first strategy as follows: 1. Select **Product Detail Page** as the page type. 2. Select **Purchased Together** as the algorithm. 3. Enter the number of products to recommend. 4. Exclude products purchased in the last four weeks. 5. Add a filter for the category attribute: Category + is + Toners. Create the second strategy with the same settings and change only the category filter: 1. Category + is + Serums. **Note:** Keep every other setting identical between the two strategies. If more than one setting changes, you cannot tell which change caused the difference in results. #### Step 2: Launch the campaign Navigate to **Web Smart Recommender** and click **Create**. 1. Select the integration method for the widget. 2. On the **Segments** step, select customers with a low AOV under **Purchasing Behavior** and set your threshold. 3. On the **Rules** step, use **Page Rules** to target the product detail pages of cleansers. 4. On the **Design** step, assign one strategy to each variant and set the traffic allocation for each variant. 5. Click **Edit Design** to open the **Advanced Product Card Designer** and customize your product cards. 6. Select the locales and stores where the campaign appears. 7. Review the campaign details, confirm that every setting matches your goal, and click **Launch**. **Note:** Every attribute you show on a product card must exist in your product catalog. To show more information, create custom attributes on the **Product Attributes** page. #### Step 3: Track campaign metrics 1. Navigate to **Smart Recommender Analytics**. 2. Find your campaign in the **Campaign and Variant Metrics** table. When the test period ends, click the campaign name. 3. Compare Direct Revenue, Average Order Value (AOV), and Conversion Rate for the two variants. This shows whether toners or serums raise AOV more for low-spending customers. 4. If one variant clearly wins, set its traffic allocation to 100% so every visitor sees the better strategy. After you find a winner, test other pairings, such as moisturizers or SPF products, by changing the category filter. #### Step 4: Optimize your campaigns After the campaign has run long enough to collect data, use **Smart Recommender Analytics** to improve it: - **Engagement funnel:** Review product impressions, click-through rate, add-to-cart rate, and conversion rate to see where shoppers drop off. - **Campaign and variant performance:** Compare AOV, Conversion Rate, and Direct Revenue in the **Campaign and Variant Metrics** table, then refine or scale the winning variant. - **Product-level impact:** Open **Top 100 Product Analytics** to see which recommended products perform best. Give extra visibility to strategic products that perform below expectations. - **Category trends:** Use **Category Analytics** to find the categories that drive the most conversions, and decide whether to prioritize them or promote weaker ones. ### Use cases by page type #### Home page ##### New arrivals for you Show returning shoppers new products that match their preferences, such as new serums for frequent skincare browsers. 1. Create a strategy with the **New Arrivals** algorithm. 2. Turn on the **Enhance recommendations based on Attribute Affinity** toggle. This personalizes by attributes such as skin type, tone, or concern. 3. Target returning users on the **Segments** step so shoppers with known affinities see the widget. **Tip:** A/B test the widget at the top versus the bottom of the page. ##### Starter routines for beginners Help new shoppers start a routine with beginner kits, such as cleanser, moisturizer, and SPF. 1. Create a strategy with the **Top Sellers** algorithm. 2. Add the filter Category + is + Starter Kits. 3. Target new users on the **Segments** step. **Note:** To recommend the rest of a kit, create a custom attribute called Kit ID on the **Product Attributes** page. Give every item in a kit the same value (for example, Oily Skin Routine 02), then filter on Kit ID. **Tip:** A/B test different starter kits to find the one that converts best. ##### Recently viewed items Remind returning shoppers of the products they explored earlier, such as a serum they almost added to the cart. 1. Create a strategy with the **Recently Viewed** algorithm. 2. Exclude products the user already purchased. 3. Target returning users on the **Segments** step. **Note:** Recently Viewed and User Based rely on each user's past behavior. Target returning users so these widgets always have data to show. **Tip:** A/B test Recently Viewed against User Based to see which converts more returning visitors. #### Product detail page ##### Picks based on recent browsing Show each shopper products that match their most recent interactions, such as brushes after they view a foundation. 1. Create a strategy with the **User Engagement** algorithm. 2. Exclude recently purchased products. **Tip:** Try widget titles such as "Picked for You" or "Based on Your Browsing." ##### More for this routine or concern Show more products from the same routine step or for the same skin concern. 1. Create a strategy with the **Trending Products** algorithm. 2. Add two filters: Routine Step + matches the item they're currently viewing, and Skin Concern + matches the item they're currently viewing. 3. Connect the filters with an **OR** connector to widen the results. 4. If you need these attributes, create Routine Step and Skin Concern on the **Product Attributes** page. **Tip:** Use dynamic titles such as "More for Your Acne Care Routine." #### Category page ##### Beauty deals in this category Show price-conscious shoppers the most discounted items in the category they are browsing. 1. Create a strategy with the **Highest Discounted** algorithm. 2. Add the filter Category + matches + the category they're currently viewing. 3. Leave Attribute Affinity off. **Tip:** Add discount labels such as "25% Off" and A/B test the widget at the top versus the bottom of the page. ##### Trending in this category Show what is trending in the category the shopper is browsing, such as serums or lipsticks. 1. Create a strategy with the **Trending Products** algorithm. 2. Add the filter Category + contains + the category they're currently viewing. 3. If your categories are hierarchical, select the **Expand the category filter to include recommendations from the next category if there aren't enough products to display** checkbox, so the widget still fills when the current category has few products. 4. Turn on the **Enhance recommendations based on Attribute Affinity** toggle. **Tip:** A/B test headlines such as "Trending Right Now" and "Bestsellers in Skincare." #### Cart page ##### Complete the routine Suggest practical add-ons, such as a setting spray with foundation or an eye cream with a serum. 1. Create a strategy with the **Most Popular** algorithm. 2. Add the filter Category + is one of + Brushes, Tools, Accessories, Minis. 3. Leave Attribute Affinity off. **Tip:** A/B test copy such as "Finish Your Routine" and "Do Not Forget These Essentials." ##### Reach free shipping Show products that help shoppers reach your free shipping threshold. 1. Create a strategy with the **Checkout Recommendation** algorithm and set the spend threshold (for example, 75 USD). 2. No filters are required. Attribute Affinity is optional. **Tip:** Use copy such as "You are 10 USD away from free shipping." If you do not offer free shipping, use **Purchased Together** instead. ### Related articles - [Algorithm Descriptions](https://academy.insiderone.com/docs/algorithm-descriptions) - [Recommendation Strategies](https://academy.insiderone.com/docs/smart-recommender-recommendation-strategies) - [A/B Test Recommendation Strategies](https://academy.insiderone.com/docs/ab-test-recommendation-strategies) - [Smart Recommender Analytics](https://academy.insiderone.com/docs/smart-recommender-analytics)