Statistician and Data Scientist with 10+ years of experience in credit risk modeling, fraud detection, and big data analytics. PhD candidate at PPGMNE/UFPR specializing in statistical inference and machine learning applications in financial services. Expert in developing scoring models, Weight of Evidence (WoE) methodologies, and optimal binning algorithms for risk assessment. Proficient in R, Python, SQL, and PySpark with proven track record in transforming complex data into actionable business insights.
Research Interests: Bayesian Networks | Optimization | Computational Statistics | GLM/GAM | Time Series | Machine Learning | AI
|
gkwreg |
gkwdist |
OptimalBinningWoE |
Statistical Modeling Predictive Analytics Machine Learning Time Series Forecasting A/B Testing Causal Inference Ensemble Methods XGBoost LightGBM Neural Networks
Credit Scoring PD/LGD/EAD Modeling Fraud Detection Anti-Money Laundering Behavioral Scoring Collection Scoring Portfolio Analytics Stress Testing
R (Advanced) Python (Advanced) SQL (Advanced) PySpark Julia C++ TMB Databricks Git
Bayesian Statistics GLM/GAM/GLMM Survival Analysis Multivariate Analysis Spatial Statistics Bootstrap MCMC Maximum Likelihood EM Algorithm
-
Ph.D. in Statistics (In Progress) - PPGMNE/UFPR
- Research: Statistical Inference and Bayesian Networks
- Advisor: Wagner Hugo Bonat (PhD)
-
M.Sc. in Statistics - PPGMNE/UFPR
I'm open to collaborations on: Statistical Modeling | Credit Risk | Machine Learning | R Package Development
Research: Bayesian Networks | Causal Inference | MAchine Learning for Finance
Industry: Credit Risk Models | Fraud Detection Models | Real-time Scoring
Open Source: R Packages | Statistical Libraries | ML Frameworks
personal_attributes <- list(
coffee_level = "Infinite ☕",
coding_hours = "24/7",
favorite_distribution = "(gkw) Generalized Kumaraswamy Distribution",
life_motto = "In Data We Trust",
superpower = "Finding patterns in chaos",
weakness = "Can't resist a good dataset"
)