Real-time Analytics
BBVA needed to help customers manage spending, savings, investments, and future outgoings with personalized guidance, while also coping with inconsistent transaction data from other banks that was too sparse for simple rule-based categorization.
Reported impact
BBVA increased engagement with its digital financial health features and improved customer satisfaction by providing real-time transaction categorization, more tailored financial proposals, forward-looking expense forecasts, and alerts on unusual bills or balance deviations.
BBVA built an AI-driven financial health workflow around its BBVA app and transactional website to turn raw banking activity into personalized guidance. The serving layer is the customer-facing app, website, and Budgets experience, where users see categorized spending, savings and investment views, forward-looking cash-flow estimates, and alerts. Upstream, BBVA ingests account and card transactions from its own systems plus aggregated transaction records from other banks when customers request it, along with comments left inside the financial health features. Compute is split by data quality: deterministic algorithms classify richly described BBVA transactions in real time, while a neural network model using NLP infers categories from sparse external-bank descriptions. BBVA also uses advanced analytics for segmentation, language models to mine feedback themes, ensemble machine learning to forecast recurring transactions, and an account balance prediction model to flag deviations. The source does not name a separate storage platform.
BBVA pulls account and card transactions from its own banking systems and, when authorized, aggregated transaction data from other banks into classification pipelines. Deterministic rules process detailed BBVA records, while a neural network with NLP interprets sparse external descriptions. The resulting categories, forecasts, segments, and anomaly signals are served through the BBVA app, transactional website, and Budgets tools, where customer edits and comments feed back into model improvement.
"BBVA customers are increasingly using the bank's app and website to track spending, make informed financial decisions, and boost savings."
"BBVA developed a neural network model, inspired by brain processes and adept at natural language processing (NLP) tasks."
"BBVA has also developed an account balance prediction model that allows estimating its future evolution and detecting out-of-the-ordinary values."
"BBVA's app and transactional website categorize banking transactions into spending, income, and savings/investment, including accounts from BBVA and other banks upon request."
"Since June 2023, in Spain, credit card transactions are classified in real time, showing customers how each expense impacts their income and its category immediately."
"Spanish customers interacted with AI features 70 million times in Q1 2024, a 23 percent year-over-year increase."
"This strong adoption highlights AI's potential in personal finance. BBVA's data scientists use advanced algorithms and AI models to enhance these financial health features, driving higher engagement and satisfaction."
"Using ensemble machine learning, which combines multiple models, BBVA predicts future transactions, their amounts, and dates."
"With such inconsistent data, we needed a model to infer categories from descriptions," says María Ruiz.
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
Related
In-house Sample Oct 9, 2026 BBVA BBVA's trading desk needs to respond to institutional client requests for bond, interest-rate swap, and foreign-exchange quotes within milliseconds while balancing competitiveness, profitability, portfolio risk, and… within milliseconds Atalaya · Bloomberg · Viriato In-house Sample Apr 23, 2026 PayPal PayPal needed to give employees conversational access to company data at enterprise scale without requiring SQL, dashboards, or intermediary engineering teams, while still meeting strict security and compliance… answers in minutes instead of hours Looker · MCP In-house Sample Apr 16, 2026 UBS Asset Management UBS Asset Management needs to support multi-asset investing decisions across strategy design, tactical asset allocation, portfolio construction, security selection, research, and portfolio implementation while rapidly… Automated trade scheduling · Dendrogram clustering · Execution optimization algorithms 