Context-Aware Creative Decisioning
Deliver relevance at scale. Use advanced logic to adapt your creative message based on the viewer’s immediate environment and behavior.
If This, Then That (at Scale)
Take control of your creative strategy with a powerful decision graph. Set specific rules that determine exactly which message is served to which user.
Example: “If it’s raining AND the user is near a store ⇢ Show ‘Umbrellas on Sale’ creative.”
Environmental Triggers:
- Weather: Rain, snow, heat index, pollen count.
- Time: Dayparting, countdowns to sales events.
- Location: City, zip code, proximity to store.
Behavioral Triggers:
- Retargeting: Products viewed, cart abandonment.
- Audience: New vs. returning visitor, loyalty tier.
Automated Relevance
Combine these triggers with your product feed to dynamically assemble thousands of ad variations in real-time. Ensure every impression is relevant, engaging, and performance-optimized.
The Right Recommendation Engine is the Difference Between a Sale and a Missed Opportunity
Traditional recommendation engines operate in batch mode. And often by the time product recommendations have been processed, the user is no longer in the market for that product or service. In today’s fast-paced retail environment driven by mobile users, it is critical to deliver messaging and creative about a relevant product or service in real-time.
With our Recommendation Engine, customers are able to predict and serve messages with increased precision, moving beyond simple retargeting to more sophisticated personalization.
| CAPABILITIES | BENEFITS |
|---|---|
| Machine Learning Based | Elimination of the guesswork of product recommendations |
| Real-time Recommendations | Relevant recommendations since the consumer will still be in the market for the product or service |
| Continuous Machine Learning | A smarter system that updates and improves recommendations increasingly over time |
| Scalability to millions of products and consumers | Increased efficiency of marketing campaigns and cost savings |
Collaborative Filtering Recommendations
Our Recommendation Engine uses a hybrid of collaborative filtering and content-based methods to increase relevance, through a combination of personalization strategies, such as predictive product recommendations with environmental and date/time-based messages.
- Automatically predicts and serves products based on preferences of other consumers within a large consumer base.
- Uses Behavioral Clustering to identify clusters based on a person’s past behavior, as well as similar historical activities by other people.
- Example: A male consumer that is a sports enthusiast from Indiana and viewed products on the Sony PlayStation site is put into a cluster, a microsegmentation of shoppers.
Behavior Clustering: Micro-Segmentation of Shoppers
Content-Based Recommendations
- Automatically predicts and serves products based on a consumer’s interest and similar products available from the brand.
- Uses Product Clustering, which are tags, categories, pricing, and similar attributes to identify and recommend additional items with similar properties.
- Example: A female consumer is looking for climbing gear on the REI website. Her shopping behavior feeds into the Personalization Hub and the Recommendation Engine predicts and serves ads showing categories of products she has searched or clicked on.
