Automated Product Variant Detection and Grouping

Automated product variant detection uses SKU pattern parsing and AI analysis to identify which products in your catalog are variants of each other — different sizes, colors, or styles of the same item. Instead of manually grouping hundreds of SKUs under parent products, the system detects relationships automatically and creates the correct parent/variant hierarchy for your e-commerce store.

You define a SKU naming pattern per brand using a visual pattern builder. For example, if a brand uses the format BRAND-MODEL-COLOR-SIZE, you map each segment to a variant attribute. The system then parses every SKU matching that pattern, extracts the color and size values, and groups matching products under the same parent. Once configured per brand, it works automatically for every new import.

SKU pattern parsing is rule-based — you define the pattern, and the system applies it consistently. It works best when brands use structured, predictable SKU formats. AI auto-detection analyzes product titles, descriptions, images, and attributes to identify variant relationships even when SKUs are inconsistent or unstructured. Most retailers use both: patterns for brands with clean SKUs, AI detection for everything else.

Yes. Every auto-detected grouping is a suggestion you can accept, modify, or reject. You can drag and drop products between parent groups, split incorrectly merged variants, merge groups the AI missed, reorder options, and assign variant-specific images and prices — all before publishing to Shopify.

Brainova supports up to three option types per parent product (matching Shopify's limit) — typically Size, Color, and Style. The system detects which attributes vary across the product group and creates the appropriate option combinations. For example, a shoe that comes in 3 colors and 5 sizes generates 15 variant records under one parent.

No automated system is perfect, which is why every detected grouping goes through a review step before publishing. Products flagged with low confidence scores are highlighted for manual review. You can split, merge, or reassign variants with drag-and-drop controls. Over time, the AI learns from your corrections to improve accuracy for future batches.

SKU pattern parsing is near-instant — once the pattern is defined, thousands of SKUs are grouped in seconds. AI auto-detection takes longer because it analyzes product data across multiple dimensions. A batch of 500 products typically completes variant analysis in 5-10 minutes. Both run as background jobs so you can continue working while processing completes.

Yes. Brainova AI Inventory is built for Shopify publishing. Detected parent products map directly to Shopify's product/variant model. When you publish, parent products become Shopify products with the correct options (Size, Color, etc.), and each variant gets its own price, inventory quantity, images, and SKU — all synced via the Shopify Admin API.

Absolutely. Each brand in your catalog gets its own SKU pattern configuration. Brand A might use COLOR-MODEL-SIZE while Brand B uses MODEL-SIZE-COLOR. The visual pattern builder lets you define unique parsing rules per brand, and saved configurations apply automatically to future imports from the same brand.

That is exactly where AI auto-detection shines. When SKUs are inconsistent, randomly assigned, or follow no pattern at all, the AI analyzes product titles, descriptions, and attributes to identify variant relationships. It can detect that "Blue Widget 10in" and "Red Widget 12in" are variants of the same product even without structured SKU data.