Publications

2020 – 2021

• Relational Graph Neural Networks for Fraud Detection in a Super-App Environment, KDD Workshop on ML in Finance, 2021, [paper]
• Enhancing User’s Income Estimation with Super-App Alternative Data, Industrial Conference on Data Mining, 2021, [paper]
• Supporting Financial Inclusion with Graph Machine Learning and Super-App Alternative Data,  Intelligent Systems Conference, 2021, [paper]
• Super-App Behavioral Patterns in Credit Risk Models: Financial, Statistical and Regulatory Implications,  Expert Systems with Applications, 169(1), 2020, [paper]
• Combining behavioral biometrics and session context analytics to enhance risk-based static authentication in web applications,  International Journal of Information Security, 2020, [paper]

2015 – 2019

• Risk-Based Static Authentication in Web Applications with Behavioral Biometrics and Session Context Analytics,  Proceedings of the International Conference on Applied Cryptography and Network Security, 2019, [paper]
• Hunting Malicious TLS Certificates with Deep Neural Networks,  Proceedings of the 11th ACM Workshop on Artificial Intelligence and Security, 2018, Toronto, Canada. [paper]
• DeepPhish: Simulating Malicious AI,  IEEE APWG Symposium on Electronic Crime Research (eCrime), 2018, San Diego, USA. [paper][slides]
• Fraud Detection by Stacking Cost-Sensitive Decision Trees, Data Science for Cyber-Security Symposium, 2017, Imperial College London, UK. [paper] [slides]
• Classifying Phishing URLs Using Recurrent Neural Networks, IEEE APWG Symposium on Electronic Crime Research (eCrime), 2017, Scottsdale, USA. [paper] [slides]
• Knowing your enemies: leveraging data analysis to expose phishing patterns against a major US financial institution, IEEE APWG Symposium on Electronic Crime Research (eCrime), 1-10, 2016, Toronto, Canada. [paper] [slides]
• Phishing Classification using Lexical and Statistical Frequencies of URLs, Analytics Forum 2016, Universidad de los Andes, Bogota, Colombia. [abstract] [poster]
• Feature Engineering Strategies for Credit Card Fraud Detection, Expert Systems with Applications, 51(1), 134-142, 2016 [paper]
• PhD Thesis: Example-Dependent Cost-Sensitive Classification, University of Luxembourg, 2015. [thesis] [slides] [repo]
• Detecting Credit Card Fraud using Periodic Features, IEEE International Conference on Machine Learning and Applications, December, 2015, Miami, US [paper]
• A novel cost-sensitive framework for customer churn predictive modeling, Decision Analytics, 2015. [paper] [slides]
• Ensemble of Example-Dependent Cost-Sensitive Decision Trees, arxiv, 2015. [paper] [slides] 
• Example-Dependent Cost-Sensitive Decision Trees, Expert Systems with Applications, 42(19), 6609–6619, 2015 [paper]

2014 –

• Example-Dependent Cost-Sensitive Logistic Regression for Credit Scoring, International Conference on Machine Learning and Applications, December 3, 2014, Detroit, US [paper] [poster] [slides] 
• Improving Credit Card Fraud Detection with Calibrated Probabilities, SIAM International Conference on Data Mining, April 25, 2014, Philadelphia, US [paper] 
• Cost Sensitive Credit Card Fraud Detection using Bayes Minimum Risk, IEEE International Conference on Machine Learning and Applications, December 3, 2013, Miami, US [paper] 
• Using the Boosting Technique to Improve the Predictive Power of a Credit Risk Model, SAS Global Forum, April 28, 2013, San Fransisco, US [paper]

  Parallel Computing in SAS®: Genetic Algorithms Application, SAS Global Forum, April 22, 2012, Orlando, US [paper][slides]
• Constructing a Credit Risk Scorecard using Predictive Clusters, SAS Global Forum, April 22, 2012, Orlando, US [paper]
• Evolutionary algorithms for selecting the architecture of a MLP Neural Network: A Credit Scoring Case, IEEE International Conference on Data Mining, December 10, 2011, Vancouver, Canada [paper] [slides]
• Genetic Algorithm Optimization for Selecting the Best Architecture of a Multi-Layer Perceptron Neural Network: A Credit Scoring Case, SAS Global Forum, April 4, 2011, Las Vegas, US [paper] [slides]