In the evolving landscape of ecommerce, understanding the key concepts behind Generative Discovery and tackling search abandonment is essential for creating seamless shopping experiences. This glossary covers important terms that help define this technology as well as other related terms and topics you’ll want to familiarize yourself with to better understand the tools and technologies shaping the future of ecommerce.
Generative Discovery
An AI-powered ecommerce solution that understands customers’ intent, predicts their needs, and delivers precise, personalized product discovery. This technology increases engagement, conversions, and average order value (AOV) by connecting shoppers with relevant products effortlessly.
- Behavioral Analysis: The process of analyzing past customer behaviors and purchase data to better anticipate future actions and preferences.
- Semantic Search: Enhances basic AI search functionality by understanding the context and intent behind user queries, delivering more relevant results even if exact keywords aren’t used.
- Natural Language Processing (NLP): Uses large language models (LLMs) to analyze product descriptions across a merchant’s full catalog, increasing the discoverability of products through expanded keyword and synonym coverage.
Personalized Recommendations
Unlock the potential of AI to deliver tailored product suggestions based on shopper behavior and preferences.
- Collaborative Filtering: AI algorithms analyze patterns from multiple users with similar tastes to suggest products others have purchased or viewed.
- Content-Based Filtering: Recommends products based on an individual shopper’s interactions, such as previously viewed items or search queries.
- Hybrid Models: A combination of collaborative and content-based filtering that offers more accurate recommendations by leveraging both personal and collective shopping behaviors.
Voice Search
Provide seamless, hands-free shopping experiences using AI-powered voice search.
- Voice-Activated Shopping: AI-driven voice assistants allow customers to search for and purchase products using voice commands, enhancing the shopping experience when paired with semantic search.
Dynamic Pricing
Stay competitive with real-time price control based on market factors.
- Real-Time Price Adjustments: AI algorithms adjust pricing dynamically based on demand, competition, and customer data, enabling personalized discounts and deals that help reduce cart abandonment.
Visual Search
Utilize images to drive precise search results and enhance product discovery.
- Image Recognition: AI-powered image recognition allows users to upload pictures and find similar products, while merchants use it to generate optimized product titles and categories. Especially useful in fashion and home décor.
- Style Matching: Suggests complementary items based on visual similarity, helping shoppers complete an outfit or a home décor scheme.
Predictive Merchandising
AI anticipates what products customers might want to buy, boosting overall sales.
- Predictive Bundling: AI predicts related products that a customer is likely to add to their cart, increasing basket size and AOV.
- Customer Behavior Prediction: AI models assess the likelihood of purchase or abandonment and suggest timely interventions, such as special offers or reminders.
Augmented Reality (AR)
Enhance the shopping experience by bringing products to life with virtual interactions.
- Virtual Try-Ons: AR-powered tools enable customers to see how products like clothing, accessories, or furniture would look on them, building confidence in purchase decisions.
Customer Segmentation
Target the right customers with the right products every time.
- Behavioral Clustering: AI segments customers based on their behaviors, such as browsing history and purchasing patterns, enabling personalized marketing and recommendations.
- Real-Time Personalization: Continuously updates customer segments to ensure recommendations and messaging are always relevant to their current behavior.
Dynamic Custom Profiles & Landing Pages
Create personalized experiences with real-time adjustments to product recommendations and landing pages.
- Static Custom Profiles: These profiles use pre-configured filters, boost rules, and sorts to produce a fixed set of results that update when catalog data changes. Merchants set these profiles up in advance, associating them with specific pages, such as the home page, product detail pages (PDPs), or the shopping cart.
- Dynamic Custom Profiles: These profiles offer greater flexibility by generating product recommendations in real-time, adapting to each customer’s interactions. Instead of relying on pre-set configurations, dynamic profiles adjust based on search terms or filters applied by the shopper. For example, a dynamic profile could display all available colors for a product on a PDP or suggest related items, such as other books by the same author or artwork by the same artist.
Dynamic profiles enhance personalization by selecting items based on real-time variables, providing a more responsive and engaging shopping experience.
Slotted Merchandising
Boost cross-selling opportunities with optimized product placement.
- Frequent Product Pairing: AI identifies products that are often bought together and arranges them side-by-side in merchandising slots to encourage cross-sell and upsell opportunities.
Product Discovery Optimization
Fine-tune how customers find your products to improve the shopping experience and drive more sales.
- Faceted Navigation: Enables customers to filter products by specific attributes, such as size, color, or brand, refining their search results efficiently.
- Auto-Suggestions: AI helps narrow down search results by suggesting popular queries or products as customers type in the search bar.
Predictive Search
Allow customers to find what they need before they even finish typing.
- Autocomplete: Uses AI to predict and suggest search queries in real-time as users type, improving the speed and accuracy of product discovery.
Customer Retention Analytics
Retain customers and foster loyalty with data-driven insights.
- Churn Prediction: AI models analyze behavioral patterns to identify customers at risk of leaving, allowing businesses to take proactive steps to retain them.
- Customer Lifetime Value (CLV) Prediction: AI forecasts a customer’s long-term value based on past purchases and behaviors, guiding retention strategies and marketing efforts.
