M&A · Portfolio Optimization · Financial Modeling · Decision Systems
Boutique advisory focused on capital allocation, financial strategy, and decision systems across international markets.
We design and implement financial decision systems that improve capital allocation, risk management, and operational performance — from M&A through portfolio construction to automated analytics infrastructure.
Rigorous financial thinking combined with quantitative methods and data engineering — applied to the problems that move capital and grow firms.
Quantifiable outcomes across active portfolio management, predictive modeling, automation, and operational improvement.
Five flagship engagements across portfolio management, risk modeling, market prediction, real estate, and operational strategy.
Advisors were spending 4+ hours per client manually computing optimal portfolio allocations, creating bottlenecks and limiting the firm's ability to scale without adding headcount.
Applied Bloomberg Terminal data with Fama-French 5-factor model and Efficient Portfolio Theory. Automated selection using graph theory and log regression — first in R, then refactored to Python for performance.
Reduced advisor time per client from 4+ hours to under 30 minutes. Enabled the firm to serve significantly more clients with the same headcount — directly improving revenue per advisor.
M&A processes require rapid, reliable assessment of counterparty financial health. Manual Altman Z-score analysis was slow, subjective, and limited in predictive power for modern balance sheets.
Combined classical Altman Z-score variants with gradient boosting classifiers trained on financial ratios. Feature engineering incorporated leverage, liquidity, profitability, and market signals.
Produced a robust, interpretable distress prediction model applicable to M&A screening, credit analysis, and portfolio risk management. Significantly reduced time-to-signal on counterparty risk assessments.
Systematic signal generation required a reproducible pipeline from raw data ingestion to strategy evaluation — with rigorous out-of-sample validation.
Built end-to-end ML pipeline for financial time-series prediction. Implemented LSTM and transformer architectures for multi-horizon forecasting, combined with technical factor signals and a full backtesting engine.
Delivered a modular research framework supporting strategy development, walk-forward testing, and performance attribution — the quantitative foundation for systematic trading decisions.
A developer needed to determine the optimal ratio of luxury vs. standard units in a new residential complex to maximize profitability — without reliable local demand data.
Scraped and analyzed comparable sales data using MySQL. Applied EDA and Log-Linear Regression in R to quantify price drivers and predict demand elasticity by unit type.
The 91% accurate model identified the optimal unit mix and key price-influencing variables. Implementing the recommendation generated 27.65% more profit than the developer's original estimate.
Individual clients required personalized investment strategies balancing risk tolerance, liquidity needs, and return expectations — while remaining competitive against market benchmarks across volatile periods.
Deployed proprietary portfolio software alongside Excel and Power BI. Applied Fama-French 3 and 5-factor models combined with behavioral finance principles to tailor each portfolio to the client's unique risk-return profile.
Achieved benchmark outperformance in 78.6% of cases. Integrating quantitative models with behavioral insights helped clients maintain strategic discipline during volatile periods — significantly reducing costly emotional decisions.
We work with capital partners and institutions, and with firms seeking quantitative and analytical capabilities.
GLEZ works selectively with a small number of engagements at a time — ensuring focused, senior-level attention on every mandate.
I operate at the intersection of corporate finance, quantitative analysis, and data science — with a focus on financial modeling, M&A, portfolio optimization, and decision systems that translate complex data into actionable strategies.
Active across nine financial centers — Europe, Latin America, and Asia — supporting investment decisions, capital allocation, and operational transformation in high-stakes environments. Fluent in four languages.
PhD candidate in Applied Economics (UNAM). Executive education at MIT, Wharton, Columbia, EDHEC, Yale, and HEC Paris.
A snapshot of what we are currently working on and researching — updated regularly.
Open to advisory engagements, full-time roles, and strategic partnerships. We respond within 24 hours.
Send a message and we'll respond within 24 hours.