Blog

Projects & analysis

14 articles

2026.03.30

CreditGraph: Topological Credit Risk with Neo4j, PySpark, and LightGBM

Traditional credit analysis treats each loan as independent, but guarantee chains, circular guarantees, and ownership concentration create correlated exposure that relational models cannot express. This project models a 500-client portfolio as a Neo4j knowledge graph, processed with PySpark on Databricks and scored with calibrated LightGBM, to surface structural risk patterns that SQL keeps hidden.

Neo4jPySparkDatabricksCredit riskCypher

Projects & analysis

2026.03.22

Actuarial Regulation Assistant: Why RAG Is the Right Approach for LISF and CUSF

Interpreting LISF and CUSF means navigating articles that cross-reference each other across laws, and a Ctrl+F can't tell the article defining technical reserves from one that mentions them in passing. AI makes it possible to absorb that entire volume without losing a single detail. This agent uses RAG to index every article individually with a cross-reference graph, eliminating citation hallucinations and ensuring the model only reasons over real legal text. The result is an assistant that amplifies the actuary's memory without replacing their judgment.

RAGLISFCUSFCNSFFTS5

Projects & analysis

2026.03.21

GMM Explorer: Three Hospitalization Levels to Price What the Industry Treats as a Single Risk

How classifying 5.1M Major Medical Expenses claims into three hospitalization levels changes the way you price a risk the industry treats as one. A UNAM team project that became a complete pricing system.

GMMpricingCNSFhospitalizationClaude AI

Projects & analysis

2026.03.19

Auto Insurance Claims Platform: three questions every insurer needs to answer

In Mexico, roughly 70% of vehicles circulate without insurance. For the insurers covering the rest, the business boils down to three questions: how much to charge, how much to reserve, and where the fraud is. This platform builds a dashboard that answers all three with data calibrated to the Mexican market, separating frequency from severity for pricing, estimating what remains unpaid with two complementary methods, and flagging anomalous claims before they reach adjustment.

RShinyGLMIBNRMonte Carlo

Projects & analysis

2026.03.19

Risk Analyst: 13 Quantitative Risk Analysis Projects

Financial risk models lose credibility when they exist only as formulas in a PDF. These 13 modules implement them in typed Python with automated tests: from portfolio VaR and Monte Carlo simulation to copulas, EVT, deep hedging, and graph neural networks for systemic contagion. Each module pairs LaTeX theory with reproducible results on public market data.

PythonFinancial RiskVaRMonte CarloMachine Learning

Projects & analysis

2026.03.19

suite_actuarial: open-source actuarial platform for the Mexican insurance market

There is no open-source actuarial library built for Mexican regulation. suite_actuarial fills that gap: it covers eight insurance domains (life, P&C, health, pensions, reserves, reinsurance, regulatory, and configuration) with EMSSA-09 mortality tables, CNSF circulars, and SAT tax articles built into the design. It installs with pip, deploys with Docker, and exposes 28 REST endpoints alongside a bilingual Next.js dashboard.

PythonPydanticLISFCUSFCNSF

Projects & analysis

2026.03.18

Insurance Claims Data Platform on GCP

Actuarial teams generate valuable data that gets trapped in spreadsheets and manual processes that do not scale. This platform builds the complete pipeline on GCP, from streaming claims intake to Tweedie GLM pricing, with Dataform and BigQuery as the backbone. The result is an automated, tested, and reproducible flow that turns raw data into inputs ready for the regulator.

BigQueryTerraformPub/SubApache BeamDagster

Projects & analysis

2026.03.18

What 5.74 Million Flights Taught Me About PostgreSQL, BigQuery, and Knowing When to Use Each

Airlines generate millions of flight, delay, and revenue records, but analyzing that data requires choosing the right database for each question. This project takes 5.74M real records, analyzes them first in PostgreSQL with engine-level optimization, migrates to BigQuery to compare both paradigms, and presents the trade-offs with real timing, real costs, and real query plans.

PostgreSQLBigQueryPythonETLEXPLAIN ANALYZE

Projects & analysis

2026.03.16

IMSS Pension Simulator: Ley 73, Ley 97, and Fondo Bienestar in One Tool

Most Mexican workers do not know which pension regime they contribute under or what they will actually receive at retirement, and official sources do not simplify the comparison between Ley 73, Ley 97, and Fondo Bienestar. This simulator implements all three formulas with current data (UMA, CONSAR tables, EMSSA 2009 mortality) and lets users explore scenarios with interactive sensitivity analysis. The result is an educational estimate that shows what you control and what you do not.

RShinyIMSSAFOREPensions

Projects & analysis

2026.03.15

SIMA: From Raw INEGI Data to Solvency Capital Requirements Under Mexican LISF, End-to-End

SIMA centralizes actuarial techniques for pricing life insurance: it takes raw mortality data from INEGI/CONAPO, graduates it with methods like Whittaker-Henderson and Lee-Carter to obtain curves that respect human biology, and projects forward to calculate premiums, reserves, and capital requirements under LISF. Everything exposed as an API, allowing it to connect with other systems, automate sensitivity analysis, and meet CNSF requirements. Open source and built to expand into other lines of business.

Lee-CartermortalityLISFCUSFCNSF

Projects & analysis

2026.03.14

Insurance Pricing with ML: What Mexico Can Learn from Europe's Actuarial Data Science Revolution

Frequency-severity pricing models on freMTPL2: Poisson GLM vs XGBoost vs LightGBM with SHAP explainability, fairness audits, and a cross-border analysis of what European ML pricing techniques mean for Mexico's 70% uninsured auto market.

pricingGLMXGBoostLightGBMSHAP

Projects & analysis

2026.03.13

Data Analyst Portfolio: 7 End-to-End Projects

Business decisions depend on questions that data can answer, but only if someone turns raw rows into actionable findings. These 7 projects cover that full arc across different domains: e-commerce cohorts, actuarial reserves, A/B testing, executive KPIs, and financial risk, each with an interactive deployed dashboard.

portfoliodata-analystSQLPythonStreamlit

Projects & analysis

2026.03.05

Reserves and Loss Experience: Interactive P&C Insurance Dashboard

Actuarial reserve analysis using Chain-Ladder and Bornhuetter-Ferguson methods on NAIC Schedule P regulatory data. Interactive dashboard with loss triangles, IBNR estimates, and combined ratios across 6 lines of business.

reserveschain-ladderBFIBNRP&C

Projects & analysis

2026.02.15

Building a Transformer from Scratch: The Proust Attention Machine

I wanted to understand what really happens inside a language model. I built one from the first matrix multiplication, trained it on all 7 volumes of Proust, and what taught me the most wasn't the architecture; it was realizing that everything is just numbers.

deep-learningtransformersNLPPyTorchNumPy

Projects & analysis