Smarter banking experiences: GenAI and semantic search in action

According to Deloitte's 2025 banking outlook, AI could drive global banking industry profits to US$2 trillion by 2028, with institutions like J.P. Morgan already reporting 10%–20% increases in product application completion rates through AI-powered customer engagement tools. At the same time, according to the report, only 25% of banking institutions say their data management platforms are adequately prepared for generative AI adoption. 

Their outlook confirms that in transaction search, GenAI semantic search capabilities are improving how customers interact with their financial data, with natural language queries and context-aware categorization that traditional banking systems couldn't achieve. For customer engagement, the report notes that banks are deploying AI-powered chatbots that generate answers from real-time knowledge bases instead of static FAQs, while combining transactional and contextual data to deliver personalized recommendations and messaging.

Brophy demonstrates this transformation through examples of an Elastic-enabled bank. First, he shows how semantic search could understand what customers actually mean when searching transactions — moving beyond exact matches to comprehend context and intent. "Traditional banking systems rely on exact matches," he explains, demonstrating how AI-enhanced search could now understand and categorize transactions intelligently. For customer support, Brophy showcases a chatbot that could pull information from across the bank's knowledge base to answer questions about mortgages, rather than just matching keywords or directing customers through FAQ pages. He demonstrates real-time synthesis of information that makes responses more relevant and natural.

Perhaps most striking is the personalization capability. Using the example of a UK-based wine enthusiast who drives a Porsche, Brophy shows how the system combines transaction history, customer preferences, and available products to make recommendations — from vehicle finance offers to South African wine collection packages.

Watch the webinar to learn how combining semantic search with generative AI helps banks move beyond basic keyword matching to truly understanding the context and meaning of customer needs — whether they're searching transactions, seeking mortgage advice, or looking for personalized services.

The release and timing of any features or functionality described in this post remain at Elastic's sole discretion. Any features or functionality not currently available may not be delivered on time or at all.

In this blog post, we may have used or referred to third party generative AI tools, which are owned and operated by their respective owners. Elastic does not have any control over the third party tools and we have no responsibility or liability for their content, operation or use, nor for any loss or damage that may arise from your use of such tools. Please exercise caution when using AI tools with personal, sensitive or confidential information. Any data you submit may be used for AI training or other purposes. There is no guarantee that information you provide will be kept secure or confidential. You should familiarize yourself with the privacy practices and terms of use of any generative AI tools prior to use. 

Elastic, Elasticsearch, and associated marks are trademarks, logos or registered trademarks of Elasticsearch N.V. in the United States and other countries. All other company and product names are trademarks, logos or registered trademarks of their respective owners.