📚Key Concepts

To effectively work with the Karsa Labelizer tool and understand the principles of advanced product segmentation, it's important to familiarize yourself with several key concepts. This glossary provides a brief and clear explanation of them.

---

Cluster : A group of products that, based on analysis of their performance metrics (using AI in Karsa Labelizer), have been identified as similar and are therefore grouped together. Each cluster in Karsa Labelizer typically corresponds to one future Google Shopping campaign or a specific segment in a PMax campaign.

Clusterization (Clustering) : The process of automatically dividing products into meaningful groups (clusters) based on their similarity within chosen parameters (metrics). Karsa Labelizer's goal is to create highly consistent and predictable clusters.

Cluster Designer : A tool (module) within Karsa Labelizer that allows users to define criteria and parameters for creating a new product clusterization. This is where limits are set, metrics are selected, and behavior for new products or movements between clusters is defined.

Custom Label : An attribute in Google Merchant Center (GMC) that allows advertisers to add custom designations to products (e.g., custom_label_0 to custom_label_4). Karsa Labelizer uses these labels to mark products with their cluster affiliation, which subsequently enables their segmentation in Google Ads campaigns.

Dynamic Product Movements : The process by which Karsa Labelizer automatically moves products between individual clusters (campaigns) based on changes in their current performance. The goal is to maintain the highest possible consistency and efficiency of clusters. This process can be controlled using set limits.

Cluster Consistency : A metric indicating how stably and similarly products in a given cluster maintain their performance characteristics (e.g., ROAS, conversion value) over time. Higher consistency means that the cluster is more internally homogeneous and its performance is more predictable for Google algorithms.

Operation Manager : A component of Karsa Labelizer where you can monitor the status and progress of running operations, especially the clusterization creation process.

Product Segmentation : The process of dividing products into smaller, more specific groups based on shared characteristics (e.g., category, brand, price, performance). The goal is to enable more targeted marketing strategies and better optimization.

Stabilization Value : A parameter in Cluster Designer that helps control the rate of changes within a cluster during product movements. Products are moved so that this value of each cluster changes only within the allowed limit.

Campaign Predictability : The ability of the Google Ads algorithm to reliably predict how a campaign will behave and what performance it will deliver under various settings (e.g., budget, target ROAS). Higher predictability leads to more efficient optimization.

Performance Metrics : Quantifiable indicators used to measure and evaluate the performance of products and campaigns. Common metrics include ROAS, CPC, CTR, Conversion Value, Number of Conversions, Impressions, Clicks, etc.

PLA (Product Listing Ads) : An advertising format in Google Ads, also known as Google Shopping ads, that displays products directly in search results and on other Google platforms. Karsa Labelizer is primarily focused on optimizing these campaigns.

PMax (Performance Max campaigns) : A type of campaign in Google Ads that automates targeting and ad display across all Google channels (Search, Display Network, YouTube, Gmail, Discovery, Maps, Shopping). Effective segmentation of the product feed using Custom Labels is important for PMax as well.

ROAS (Return On Ad Spend) : A key metric indicating how much revenue is generated by each € (or other currency) spent on advertising. It is calculated as (Conversion Value / Advertising Cost). Higher ROAS generally means higher efficiency.

GMC (Google Merchant Center) : A tool from Google that allows uploading and managing product data (feeds) for use in Google Shopping, Performance Max, and other Google advertising formats. Karsa Labelizer exports the resulting Custom Labels to GMC.

Conversion Rate (CR) : The percentage of visits (clicks on an ad) that led to a completed conversion (e.g., purchase). It is calculated as (Number of Conversions / Number of Clicks) * 100%.

Machine Learning (ML) : A subfield of artificial intelligence where systems learn and improve from data without explicit programming for each individual case. Karsa Labelizer uses ML models to identify optimal clusters.