AI Amazon advertising strategy in practice: how a top yoga brand used Xnurta to move beyond search term data and optimize multi-variant ASIN campaigns for stronger ad performance.
April 17, 2025
The Limitations of Search Term Data in Ad Optimization
As Amazon Advertising grows increasingly competitive, brands must implement precise keyword targeting to maximize visibility and optimize ad spend. While Amazon’s Search Term Report provides insights into consumer intent and keyword performance, it has several limitations that hinder advertising strategies.
For brands managing multi-variant ASINs—such as apparel, electronics, and CPG products—advertising campaigns often group multiple ASINs into a single ad group, creating challenges such as:
These limitations result in inefficient budget allocation and reduced campaign effectiveness, preventing brands from maximizing their return on ad spend (ROAS)
AI-Powered Keyword Optimization with AMC Data
To address these challenges, Xnurta’s AI-driven AMC keyword optimization introduces a data-driven approach to automating keyword expansion and refining targeting at the ASIN level.
By leveraging Amazon Marketing Cloud (AMC) data, brands using Xnurta can:
Breaking the Barriers of Search Term Data
Since AMC data became available for Sponsored Ads, advertisers have primarily focused on audience segmentation and bid adjustments. However, AMC also unlocks valuable keyword insights, revealing deep correlations between search terms, ASINs, and ad placements—previously inaccessible through traditional reporting.
Enhancing Keyword Precision
Traditional keyword targeting methods failed to distinguish which ASIN within a multi-ASIN campaign was responsible for a keyword’s success. This lack of visibility often resulted in inconsistent performance and ineffective budget allocation when scaling ads across product variations.
With AMC data, brands can now precisely match high-performing search terms to the ASINs generating conversions, ensuring ad spend is directed toward the most impactful keywords while reducing wasted spend on irrelevant ones.
Improving Operational Efficiency
In the past, users had to manually create multiple single-ASIN ad groups and cross-compare search term reports to evaluate keyword effectiveness—a time-consuming and inefficient process.
Xnurta’s AI-powered automation eliminates this complexity by:
AI-Powered Real-Time Adjustments
As the first eCommerce SaaS platform to integrate AMC data for AI-driven keyword optimization, Xnurta has developed an advanced machine-learning model that:
Efficient Execution and Smart Adjustments
To eliminate ineffective keyword harvesting and prevent unnecessary competition, Xnurta’s system leverages a pruning algorithm that automatically refines keyword selection by:
For specific ad groups, such as brand defense and competitor targeting, the system maintains a structured and clean ad group hierarchy, ensuring that irrelevant keywords do not interfere with optimization efforts.
As illustrated in the diagram:
By dynamically pruning unnecessary elements, Xnurta’s AI-driven system ensures that keyword expansion remains precise, structured, and efficient, allowing brands to maximize their ad performance with minimal manual intervention.
How a Top-Selling Yoga Brand on Amazon Optimized Ads with AI-Powered Keyword Targeting
A leading yoga apparel brand on Amazon, managing multiple ASINs in their ad campaigns, faced challenges in optimizing keyword targeting. Their previous strategy relied on broad keywords like "women leggings", which led to mixed search term data and inconsistent ad performance.
By implementing Xnurta’s AI-powered AMC keyword optimization, the system automatically identified high-converting long-tail keywords, such as “red leggings for women with pockets”, and precisely mapped them to the best-performing ASINs.
Results in Two Weeks:
A representative from the brand shared their experience:
“When structuring ad campaigns for multi-variant products, we often had to group multiple ASINs of different sizes into the same campaign to simplify management and consolidate the budget. However, this approach often resulted in mixed search term data, making it difficult to accurately evaluate individual ASIN performance, leading to unstable optimization results.
Xnurta’s new feature solved this issue perfectly. By combining AMC data with AI algorithms, it establishes a direct correlation between ASINs and customer search terms. The AI optimizes keywords intelligently based on the performance of each ASIN.
During the beta testing phase, we saw significant improvements—conversion rates increased, and ACoS dropped noticeably.
This exceeded our expectations and gave us a new perspective on AI.
FAQ:
How do brands activate AMC keyword optimization in Xnurta?
How does Xnurta determine which ASIN a search term belongs to?
How does AMC data enhance DSP and Sponsored Display (SD) ads?
What’s next for Xnurta’s AI advertising solutions?
Xnurta continues to expand its AI-driven optimizations for AMC, with upcoming enhancements focused on:
Let your data work harder. Join the brands using Xnurta to transform AMC insights into high-performing, AI-driven campaigns.
No fluff. Just what's working.
