Text matching failed on complex queries in a 50k catalog. Now, LLMs interpret intent to rank products by likelihood to convert.
Finland's most popular online retailer serves millions of monthly visitors with a 50,000-item catalog and an industry-leading Net Promoter Score of over 90.
A traditional on-site search function relied on simple text matching that failed to handle complex or ambiguous natural language queries. Customers...
“We've been a long-time user of Google Cloud, so it made sense to build on our existing data foundation in BigQuery. Google Cloud is a leader in AI innovation, and if anyone understands search, it's Google, so we were confident it would help us deliver the intelligent search we needed.”
E-commerce retailer for consumer electronics, home goods, and leisure products.
Cloud computing services, AI infrastructure, and data analytics platforms for enterprises.
Related implementations across industries and use cases
Exact-match search missed synonyms. AI now maps intent—linking "cooling goods" to inventory—turning vague queries into sales.
Manual rules failed to match 120k products to diverse buyer journeys. Real-time ML now adapts to intent, serving relevant suggestions.
Rigid search struggled with precise TV codes vs. vague web terms. Semantic ML now adapts to both intents, boosting relevance.
Manual fixes slowed order processing to 2.5 hours. AI code optimization cut that to 30 minutes and reduced incidents by 50%.
300+ receipt layouts forced manual entry. GenAI now reads raw images with 98.6% accuracy, cutting costs 90%.
Analysts spent days manually merging data. GenAI now generates localized campaign summaries for 20 audiences across six countries.
Manual ad production took months. Now, teams use AI to predict performance and generate creative in just 5 days.