Interdisciplinary research spanning applied econometrics, urban economics, and AI safety
This study examines how first sizable industry entries reshape local and neighboring labor markets across Puerto Rico using over a decade of quarterly municipality-industry data (2014Q1-2025Q1). Employing robust staggered difference-in-differences estimators and doubly robust frameworks with spatial interference modeling, the research identifies large persistent direct employment and wage gains in treated municipalities while accounting for spillover effects through contiguity networks.
Key Topics: Labor markets, Economic development, Spatial econometrics, Causal inference, Regional economics
VIEW ON ARXIV →An evaluation of San Juan's late-night alcohol sales ordinance using multi-outcome synthetic control methods that pool economic and public-safety indicators. The study demonstrates how common-weight estimators can clarify policy mechanisms under low-rank outcome structures, finding economically meaningful reallocations in targeted sectors (restaurants, bars, hospitality) without clear departures in public disorder or violent crime metrics.
Key Topics: Policy evaluation, Synthetic control, Urban economics, Public safety, Alcohol regulation
VIEW ON ARXIV →This paper provides tract-level evidence on post-disaster gentrification patterns following Hurricane María in Puerto Rico. Using vulnerability models and XGBoost classification, it demonstrates that strong post-shock upgrading occurs selectively in tracts combining low baseline incomes with higher educational attainment and lower residential mobility. The findings reveal path-dependent gentrification shaped by pre-existing socioeconomic conditions and provide vulnerability measures to inform anti-displacement policy.
Key Topics: Urban gentrification, Disaster economics, Machine learning, Housing policy, Socioeconomic vulnerability
VIEW ON SSRN →Bio-inspired AI is increasingly presented as overcoming externally imposed objectives by internalizing regulation through drives, homeostasis, or predictive control. This Perspective argues that this narrative is often mistaken: in many contemporary designs, normativity is not eliminated but relocated, with constraints compiled into internal variables, learning rules, or deployment infrastructures while authorship remains external. To make this relocation explicit, this Perspective introduces a lifecycle map that locates where normative "whistles" enter AI systems from training through deployment, and proposes a constructive design pattern — the separation of an explicit Safety Envelope from an internal Adaptive Space — that preserves robust control while making normative authorship auditable and governable.
Key Topics: AI safety, Bio-inspired AI, Normativity, Rule relocation, Safety envelope, Adaptive space
VIEW ON SSRN →Puerto Rico faces persistent electricity reliability challenges, raising a key question: can standard aggregate stress indicators detect the spatial incidence of the economic burden? This paper estimates municipal incidence of monthly shortfalls by combining island-month variation in shortfall measures with predetermined cross-municipality differences in electricity-dependence. Exposure is constructed from 2019 sector composition using electricity-intensity weights; outcomes include real retail sales and municipal employment over 2020-2025. The results indicate that aggregate shortfall metrics are not a reliable basis for detecting granular economic incidence.
Key Topics: Electricity reliability, Infrastructure economics, Puerto Rico, Spatial analysis, Economic burden, Energy policy
VIEW ON SSRN →This paper constructs a 2002-2022 panel from IRS Statistics of Income tabulations to map the controlled U.S. corporate footprint associated with SOI-assigned foreign owner jurisdictions. Using co-equal measures of balance-sheet scale, reported income, and profitability, the research documents persistent concentration among a small set of jurisdictions and a weak alignment between asset scale and reported returns. The analysis situates Puerto Rico within cross-jurisdiction distributions, highlighting recent years in which moderate scale coincides with relatively high reported profitability. The results provide a transparent, replicable baseline for interpreting owner-jurisdiction labels in U.S. corporate tax data.
Key Topics: Foreign-controlled corporations, IRS Statistics of Income, Owner jurisdiction, Corporate profitability, Offshore financial centers, Tax policy, Puerto Rico
VIEW ON SSRN →This paper argues that Puerto Rico's core macroeconomic interpretive problem is institutional rather than technical: the island is economically "external" yet statistically "internal" to U.S. survey and accounting architectures, preventing a consistently implemented resident/non-resident boundary across production, income, and financial accounts. Drawing on primary-source documentation and official reports from 1989–2023, the analysis reconstructs the evolution of Puerto Rico's macroeconomic accounts and demonstrates why GDP modernization alone cannot resolve ambiguity about resident income and external dependence.
Key Topics: National accounting, GDP/GNP measurement, Statistical boundaries, Macroeconomic systems, Puerto Rico economy, BEA methodology, Accounting closure
VIEW ON SSRN →A diagnostic companion document that examines whether Puerto Rico's published aggregates (GDP, GNP, BOP, and related tables) form a closed and internally coherent macroeconomic system. Using direct quotations from official PRPB and BEA methodology documents, this Q&A identifies specific measurement gaps, residual calculations, and structural blind spots that prevent system closure. Each entry concludes with a policy implication describing what users cannot do reliably when that data gap persists.
Key Topics: Data quality assessment, Statistical methodology, Measurement limitations, PRPB documentation, BEA methodologies, Policy implications, Forensic analysis
VIEW COMPANION →Post-restructuring Puerto Rico GO bond spreads achieve strong in-sample fit but fail dramatically in walk-forward evaluation. Using transaction-level yields from EMMA for Series 2022A maturities matched to U.S. Treasury benchmarks, this paper constructs a monthly fiscal-stress signal and documents that a one-lag predictive regression produces high burn-in R² (~0.52) and a permutation p-value of 0.006 — yet out-of-sample R² collapses to approximately −6.4 to −8.3, with a simple AR(1) benchmark dominating throughout. A forensic preprocessing audit identifies the rolling standardization window as the smoking gun: short 126-day Z-scores manufacture apparent predictability by adapting to local regimes, while extending to 252 days substantially reduces the walk-forward collapse but eliminates in-sample significance entirely.
Key Topics: Spurious regression, Thin market microstructure, Preprocessing forensics, Walk-forward validation, Municipal bonds, Puerto Rico economy, Forecasting
VIEW MANUSCRIPT →Puerto Rico exhibits a sharp divergence between territorial production and resident welfare. This paper documents and quantifies two interacting structural conditions over 2002–2025. First, non-resident primary-income outflows: multinational firms book large IP-attributed returns that elevate measured GDP ($129.4 billion in FY2025) while the associated property income accrues to non-resident owners, leaving gross national product at $87.6 billion — a $41.8 billion gap. Second, transfer dependence: resident income is insufficient to sustain household consumption without federal transfer payments that constitute about 40 percent of personal income. Using national accounts, balance-of-payments, and international investment position tables, the paper reconciles production, income allocation, external balances, and household closure within a single integrated accounting system.
Key Topics: National accounting, GDP-GNP divergence, IP-attributed returns, Transfer dependence, Household accounts, Puerto Rico economy, Accounting closure
VIEW MANUSCRIPT →Periods of market stability often coincide with rising financial fragility. Standard risk measures appear reliable until liquidity constraints bind, at which point losses escalate rapidly and decision-making becomes forced. This article reframes fragility as a diagnostic and governance problem rather than a forecasting failure. It explains how leverage, funding dependence, crowding, and intermediary balance-sheet constraints accumulate quietly during calm periods and are transmitted through liquidity constraints under stress, and offers practical guidance for monitoring fragility, stress testing liquidation mechanics, constructing resilient portfolios, and establishing governance rules that prioritize robustness over precision.
Key Topics: Financial fragility, Liquidity risk, Leverage, Balance-sheet constraints, Stress testing, Portfolio resilience, Risk governance
VIEW MANUSCRIPT →Comprehensive financial modeling solutions for strategic decision-making and business growth.
Ideal for: CFOs, startup founders, investors evaluating PR opportunities, M&A transactions
End-to-end BI solutions leveraging Microsoft Azure cloud platform for actionable insights.
Ideal for: Operations leaders, IT/BI heads, organizations with data silos, cloud migration projects
xP&A Consultant Specializing in Financial Planning & Advanced Analytics
With over 10 years immersed in finance and analytics, I saw a critical need among local businesses: the need to bridge the gap between complex financial planning and the wealth of operational data often locked away in separate systems. SENS ADVISOR was born from an idea to address this: to empower organizations by integrating these domains through expert Extended Planning & Analysis (xP&A) and full-stack enterprise application development that transforms how businesses manage their financial and operational workflows.
I mainly focus on designing and deploying cloud-based xP&A and Business Intelligence systems using Microsoft Azure, Power BI, and advanced Excel techniques, while also architecting sophisticated full-stack business applications with enterprise-grade security, role-based access control, and real-time data synchronization.
Since 2022, I've pursued AI and LLM research as a purposeful hobby to stay current with rapidly evolving technology and to rigorously test what works versus what doesn't in real business implementations. This is how I maintain a ground-truth understanding of AI's current capabilities and limitations which allows me to provide clients with realistic assessments of AI opportunities, honest guidance on implementation risks, and evidence-based recommendations for efficiency gains.
SENS ADVISOR
Grupo Cabrera
Public Corporation for Supervision and Insurance of Cooperatives
Government Development Bank for Puerto Rico
NYU Stern Executive Education
BarcelonaTech
University of Illinois Urbana-Champaign
University of Puerto Rico
University of Puerto Rico
Ready to transform your planning and analytics? Let's discuss your specific needs.