Smart Recommender for Media & Entertainment Verticals

Prev Next

Media and entertainment is an engagement-driven vertical. Viewing history, genres, moods, and subscription tiers shape behavior, and audiences binge series, follow creators, and switch plans based on perceived value.

This article shows how to use Smart Recommender in Insider One to keep viewers engaged and help them discover new content. It includes an A/B test walkthrough for cross-promotion and strategies for each page type.

Before you start: Make sure your content catalog includes the attributes this article filters on, such as Genre, Series Name, Cast, and Mood. Create missing custom attributes on the Product Attributes page and mark them as filterable.

What you can achieve with Smart Recommender

Personalized watchlists

Show new content that matches each viewer's favorite genres, shows, or creators.

Spotlight fast-rising titles to spark curiosity.

Win back lapsed viewers

Recommend titles based on past watch history and genre preferences.

Suggest sequels, spin-offs, or similar shows on content detail pages.

Genre collections

Curate collections such as "Feel-Good Comedies" with Attribute Affinity.

Family-friendly picks

Highlight family-safe content for relevant profiles.

A/B testing

Test placement, layout, and grouping of recommendations.

Walkthrough: Increase engagement with cross-promotion

When viewers finish a title, they look for what to watch next. A well-placed recommendation keeps them on the platform.

This walkthrough tests two strategies on content detail pages:

  • Variant A: Recommend titles from the same series (sequels and prequels).

  • Variant B: Recommend titles from the same genre.

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 Viewed Together as the algorithm.

  3. Enter the number of titles to recommend.

  4. Exclude titles the user recently watched.

  5. Add the filter Series Name + matches the item they're currently viewing.

Create the second strategy with the same settings and change only the filter:

  1. Genre + matches the item they're currently viewing.

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, target returning users, who have viewing history to build on.

  3. On the Rules step, use Page Rules to target content detail pages of shows and movies.

  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 click-through rate and Conversion Rate for the two variants. This shows whether same-series or same-genre titles get more viewers to start the next title.

  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 content, such as behind-the-scenes clips or related documentaries.

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 impressions and click-through rate to see whether viewers notice and use the widget.

  • Campaign and variant performance: Compare click-through rate and conversions in the Campaign and Variant Metrics table, then scale the winning variant.

  • Title-level impact: Open Top 100 Product Analytics to see which recommended titles get the most clicks.

Use cases by page type

Home page

Because you watched

Recommend titles similar to what each viewer watched before.

  1. Create a strategy with the User Based algorithm.

  2. Turn on the Enhance recommendations based on Attribute Affinity toggle.

  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.

Feature titles gaining the most interest this week.

  1. Create a strategy with the Trending Products algorithm.

  2. Optionally, add a Genre filter.

Tip: Use titles such as "Most Watched Right Now."

Content detail page

More like this

Suggest similar series, spin-offs, or same-genre titles.

  1. Create a strategy with the Viewed Together algorithm.

  2. Add two filters: Genre + matches the item they're currently viewing, and Cast + matches the item they're currently viewing. Connect them with an OR connector.

Tip: Try headlines such as "You Might Also Like."

Category page

Top picks in this genre

Show the titles gaining the most interest in the genre the viewer is browsing.

  1. Create a strategy with the Trending Products algorithm.

  2. Add the filter Genre + matches + the genre they're currently viewing.

  3. Turn on the Enhance recommendations based on Attribute Affinity toggle.

Picked for you in this genre

Show personalized titles in the current genre.

  1. Create a strategy with the User Based algorithm.

  2. Add the filter Genre + matches + the genre they're currently viewing.

  3. Turn on the Enhance recommendations based on Attribute Affinity toggle.

  4. Target returning users on the Segments step.

Use cases with Bundle Strategy

A Bundle Strategy combines several slots in one widget, and each slot follows its own rule:

  • Select from Catalog: shows products you pick by hand.

  • Add from Algorithm: shows products an algorithm recommends.

  • Add from Filter: pulls products straight from your catalog with a filter.

In the tables below, Products is the number of products a slot shows. Where a table says "Up to," choose the count that fits your widget. A slot shows up to 15 products, and a bundle shows up to 90. Sorting applies to Add from Filter slots only. The options you can select depend on the page type.

For setup steps, see Create a Bundle Strategy.

Home page

Premium premieres for free-plan viewers

Show viewers on your free plan what they are missing. Start with the premium originals you are launching this month in fixed positions. Your newest premium-only titles follow, then the premium titles trending this week. The originals stay in front, and the rest of the row follows your release calendar and viewing.

  1. Create a Bundle Strategy for the Home Page, with no trigger.

  2. Add three slots:

Slot

Type

Source

Products

Filters

Sorting

1

Select from Catalog

The premium originals you want to launch

The ones you pick

–

–

2

Add from Filter

Catalog

Up to 15

tier = Premium

Newest first (Created Date, high to low)

3

Add from Algorithm

Trending Products

Up to 15

tier = Premium

–

  1. Select Enhance Recommendations Based on Attribute Affinity to favor the genres and creators each viewer prefers.

  2. In the campaign, set the segment to users on your free plan.

Tip: Add a custom "tier" attribute in Product Attributes, enable the Filterable toggle, and set it to Premium on premium-only titles.

Tip: A monthly launch is only one example. Use the same setup for any moment you program for, such as award season, a sports final, Halloween horror week, holiday movies, Ramadan series, or summer blockbusters. Change the titles in slot 1 and, if you tag the moment, add the tag to the filters; the slots and sorting stay the same.

Tip: Track click-through rate during the launch, and compare plan upgrades in the free-plan segment against your own subscription data.

Back to what you were watching

Viewers rarely finish a series in one sitting. Show returning viewers the two titles they opened last, then the sequels and prequels of those titles, then what other viewers watched with them.

  1. Create a Bundle Strategy for the Home Page, with no trigger.

  2. Add three slots:

Slot

Type

Source

Products

Filters

Sorting

1

Add from Algorithm

Recently Viewed

2

–

–

2

Add from Algorithm

Complementary Product, based on the user's last viewed (2 items)

Up to 5

Category = Sequels & Prequels

–

3

Add from Algorithm

Viewed Together, based on the user's last viewed (2 items)

Up to 15

–

–

  1. Set campaign segments for returning users (for example, last visit in the last 7 days).

Tip: Try headlines such as "Continue Watching" or "Next in Your Series." A/B test this bundle against the Because you watched use case above to see which drives more watch time.

A family row for family profiles

On profiles used by families, open the homepage with the family titles your editors pick, such as holiday specials. The most-watched titles rated for all ages follow, then family-safe picks based on what the household watches.

  1. Create a Bundle Strategy for the Home Page, with no trigger.

  2. Add three slots:

Slot

Type

Source

Products

Filters

Sorting

1

Select from Catalog

The family titles your editors pick

The ones you pick

–

–

2

Add from Filter

Catalog

Up to 15

maturity rating = All Ages

Most viewed first (View Count, high to low)

3

Add from Algorithm

User-Based

Up to 15

maturity rating = All Ages

–

  1. In the campaign, set the segment to users with a kids or family profile.

Tip: Every slot carries the maturity rating filter, or is picked by your editors, so the whole row stays family-safe.

Content detail page

Watch the whole franchise in order

On the page of any film or season of a franchise, show the full franchise in watch order, followed by what other viewers watched with it. A viewer who opens the second film sees the first, third, and fourth in order, then the spin-off series.

  1. Create a Bundle Strategy for the Product Detail Page with one bundle per franchise and a fallback.

Bundle 1: Franchise A (Trigger Rule: Franchise equals Franchise A)

Slot

Type

Source

Products

Filters

Sorting

1

Add from Filter

Catalog

Up to 15

Franchise = Franchise A

Watch order first (Watch Order, low to high)

2

Add from Algorithm

Viewed Together, based on the currently viewed item on page

Up to 10

–

–

Bundle 2: Franchise B (Trigger Rule: Franchise equals Franchise B): the same slots with Franchise = Franchise B.

  1. Mark a third bundle with Complementary Product (based on the currently viewed item on page) as the fallback, for titles that are not part of a franchise.

  2. Select Hide the Currently Viewed Product, so the title the viewer is on does not repeat in the row.

Tip: Create custom "Franchise" and "Watch Order" (number) attributes in Product Attributes and fill them for each title. New titles of a franchise then join the row in the right place without editing the bundle.

Your original next to every genre hit

On the page of a popular title, show its sequels and prequels first. Then show the original you are pushing in the same genre and the most-watched titles of the genre. A viewer on a true crime documentary sees its follow-up, your new true crime original, and the genre's most-watched series.

  1. Create a Bundle Strategy for the Product Detail Page with one bundle per genre and a fallback.

Bundle 1: True Crime (Trigger Rule: genre equals True Crime)

Slot

Type

Source

Products

Filters

Sorting

1

Add from Algorithm

Complementary Product, based on the currently viewed item on page

Up to 3

Category = Sequels & Prequels

–

2

Select from Catalog

Your true crime original

1

–

–

3

Add from Filter

Catalog

Up to 15

genre = True Crime

Most viewed first (View Count, high to low)

Bundle 2: Comedy (Trigger Rule: genre equals Comedy): the same slots with your comedy original and genre = Comedy.

Fallback bundle (for the other genres)

Slot

Type

Source

Products

Filters

Sorting

1

Add from Algorithm

Complementary Product, based on the currently viewed item on page

Up to 3

Category = Sequels & Prequels

–

2

Add from Algorithm

Viewed Together, based on the currently viewed item on page

Up to 15

–

–

  1. Mark the fallback bundle with Set as Fallback. You need a separate bundle because the genre bundles pin an original and filter on their own genre, which would be wrong on a title from another genre.

  2. Select Hide the Currently Viewed Product.

Tip: Swap the title in slot 2 each time you release a new original in the genre. A/B test this bundle against the More like this use case above and compare watch time.

Category page

Hits first, then hidden gems

On each genre page, show what is trending in the genre first, then highly rated titles of the genre that few viewers have found yet. Viewers get the obvious picks and the well-reviewed titles your catalog has but rarely surfaces.

  1. Create a Bundle Strategy for the Category Page with one bundle per genre and a fallback.

Bundle 1: Comedy (Trigger Rule: Category equals Comedy)

Slot

Type

Source

Products

Filters

Sorting

1

Add from Algorithm

Trending Products

Up to 10

Category = Comedy

–

2

Add from Filter

Catalog

Up to 15

Category = Comedy; Rating > 4.5

Least viewed first (View Count, low to high)

Bundle 2: Drama (Trigger Rule: Category equals Drama): the same slots with Category = Drama.

Fallback bundle (for the other genre pages)

Slot

Type

Source

Products

Filters

Sorting

1

Add from Algorithm

Trending Products

Up to 10

–

–

2

Add from Filter

Catalog

Up to 15

Rating > 4.5

Least viewed first (View Count, low to high)

  1. Mark the fallback bundle with Set as Fallback. You need a separate bundle because the genre bundles filter on their own genre.

Tip: On the Category Page, Trigger Rules can use only the Category attribute.

A/B test this bundle against the Top picks in this genre use case above to see which drives more views of lesser-known titles.

Your originals, then picks for each viewer

On each genre page, put the originals you want to grow in that genre first. Titles of the genre picked for each viewer from what they watch follow. A viewer who watches dark, slow-burn dramas sees your new drama original first, then the dramas that match their taste.

  1. Create a Bundle Strategy for the Category Page with one bundle per genre and a fallback.

Bundle 1: Drama (Trigger Rule: Category equals Drama)

Slot

Type

Source

Products

Filters

Sorting

1

Select from Catalog

Your drama originals

The ones you pick

–

–

2

Add from Algorithm

User-Based

Up to 15

Category = Drama

–

Bundle 2: Comedy (Trigger Rule: Category equals Comedy): the same slots with your comedy originals and Category = Comedy.

Fallback bundle (for the other genre pages)

Slot

Type

Source

Products

Filters

Sorting

1

Add from Algorithm

Real-Time User Engagement

Up to 10

–

–

2

Add from Algorithm

Trending Products

Up to 15

–

–

  1. Mark the fallback bundle with Set as Fallback.

  2. Select Enhance Recommendations Based on Attribute Affinity to favor the moods, cast, and creators each viewer prefers.

  3. Set campaign segments for returning users.

Tip: User-Based relies on a viewer's past behavior. A/B test this bundle against the Picked for you in this genre use case above to see which drives more watch time.