Developing a big data analytical model for measuring financial well-being in an open finance ecosystem
Pilar Beatriz Alvarez-Franco et al.
What the paper says
Purpose This paper develops and empirically tests a novel big data analytic model to measure financial well-being (FWB) throughout the customer life cycle. The study uses a comprehensive, proprietary dataset that encompasses demographic and transactional data for nearly 430,000 clients across multiple financial products, approximating an “open finance” setting. Design/methodology/approach The model combines objective indicators of financial behavior with subjective measures of perceived well-being into a composite, customer-level index. To ensure robustness and practical relevance, the model was refined using feedback from nearly one hundred industry experts and validated through extensive sensitivity analyses. Furthermore, the composite index is closely aligned with independent and nationally representative studies conducted by the Development Bank of Latin America and the Caribbean (CAF), which highlights its external validity. Findings The study shows that the big data analytics model can capture the main features of the proposed conceptual model for measuring FWB at different stages of life. The model produces data-driven analytical weight loads that reflect most of the implications of the lifecycle consumption theory. The results validate the analytical model's suitability to be scaled and implemented in an open finance setting. Originality/value By providing a scalable, actionable, and empirically validated tool, this research contributes to the literature on FWB measurement and offers financial institutions and consumers the ability to continuously monitor their financial health, while accommodating AI-driven recommendations tailored to improve well-being.
Evidence weight
Balanced mode · F 0.40 / M 0.15 / V 0.05 / R 0.40
| F · citation impact | 0.50 × 0.4 = 0.20 |
| M · momentum | 0.50 × 0.15 = 0.07 |
| V · venue signal | 0.50 × 0.05 = 0.03 |
| R · text relevance † | 0.50 × 0.4 = 0.20 |
† Text relevance is estimated at 0.50 on the detail page — for your query’s actual relevance score, open this paper from a search result.