Verkkokauppa.com
Product search
Text matching failed on complex queries in a 50k catalog. Now, LLMs interpret intent to rank products by likelihood to convert.
- 8% improvement in conversion per visitor
- 4% increase in products added to cart
Exact-match search missed synonyms. AI now maps intent—linking "cooling goods" to inventory—turning vague queries into sales.
A lifestyle and apparel retailer operating approximately 60 brands, offering a diverse catalog ranging from fashion items to general merchandise.
Legacy search tools relied on exact keyword matching, failing to retrieve products when customers used synonyms, spelling variations, or different...
“膨大な商品数と指標をすべて見続けることは困難ですが、AI が状況を言語化してくれることで、担当者は『そうなっているのか』とパッと理解でき、一旦の概況確認がスムーズに行えるようになりました。”
Retailer of apparel, accessories, and lifestyle products across specialty brands.
Implemented the Looker and Gemini integration and Vertex AI Search for commerce for Pal.
Cloud computing services, AI infrastructure, and data analytics platforms for enterprises.
Pal Group's E-commerce search is part of this use case:
Related implementations across industries and use cases
Text matching failed on complex queries in a 50k catalog. Now, LLMs interpret intent to rank products by likelihood to convert.
Keyword limits and manual workflows bottlenecked sales. Semantic search raised purchase amounts 14.2% and halved listing creation time.
Vendors missed demand targets by 30%. Now, ML automates SKU-level forecasts and GenAI extracts insights from customer service tickets.
Adding one attribute to a 300M-item catalog took days of rebuilds. Unifying vector and product data unlocked real-time hybrid search.
Thousands of daily touchpoints, one goal: every sailor feels known. AI surfaces each guest's preferences to crew before they even ask.
Bolted-on voice felt like a chatbot with a mic—customers reverted to one-word commands. Native audio made it a real conversation.
Two homegrown bots drained the engineers who built them. Claude Tag catches alerts, traces root causes, and opens PRs—without being asked.
Passive demos left the value of AI analytics abstract. A Cloud Lab where customers ran real tasks in their own data made it concrete.
Range questions once meant days waiting on sales engineers across time zones. Now sellers get live answers mid-conversation.
Exact-match search missed synonyms. AI now maps intent—linking "cooling goods" to inventory—turning vague queries into sales.
A lifestyle and apparel retailer operating approximately 60 brands, offering a diverse catalog ranging from fashion items to general merchandise.
Legacy search tools relied on exact keyword matching, failing to retrieve products when customers used synonyms, spelling variations, or different...
“膨大な商品数と指標をすべて見続けることは困難ですが、AI が状況を言語化してくれることで、担当者は『そうなっているのか』とパッと理解でき、一旦の概況確認がスムーズに行えるようになりました。”
Retailer of apparel, accessories, and lifestyle products across specialty brands.
Implemented the Looker and Gemini integration and Vertex AI Search for commerce for Pal.
Cloud computing services, AI infrastructure, and data analytics platforms for enterprises.
Pal Group's E-commerce search is part of this use case:
Related implementations across industries and use cases
Text matching failed on complex queries in a 50k catalog. Now, LLMs interpret intent to rank products by likelihood to convert.
Keyword limits and manual workflows bottlenecked sales. Semantic search raised purchase amounts 14.2% and halved listing creation time.
Vendors missed demand targets by 30%. Now, ML automates SKU-level forecasts and GenAI extracts insights from customer service tickets.
Adding one attribute to a 300M-item catalog took days of rebuilds. Unifying vector and product data unlocked real-time hybrid search.
Thousands of daily touchpoints, one goal: every sailor feels known. AI surfaces each guest's preferences to crew before they even ask.
Bolted-on voice felt like a chatbot with a mic—customers reverted to one-word commands. Native audio made it a real conversation.
Two homegrown bots drained the engineers who built them. Claude Tag catches alerts, traces root causes, and opens PRs—without being asked.
Passive demos left the value of AI analytics abstract. A Cloud Lab where customers ran real tasks in their own data made it concrete.
Range questions once meant days waiting on sales engineers across time zones. Now sellers get live answers mid-conversation.