Resume

Economics student at PUCP (tenth semester) with solid experience in data analysis, programming in Stata and Python, and advanced econometric modeling. Passionate about microeconomics, data science, and machine learning, with a focus on solving complex problems using technological tools. I have contributed to academic and research projects applying Machine Learning techniques, analysis of large datasets, and causal inference methods. Known for being proactive, a quick learner, and highly adaptable to new technologies.

Download CV

Summary

Karl Willem Janampa Aparicio

Economics student at PUCP with expertise in data science, econometric modeling, and machine learning. Focused on delivering actionable insights through advanced analytical tools and methods.

  • Av. Los Dominicos, San Martín de Porres
  • +51 999002286
  • kjanampa@pucp.edu.pe

Education

Bachelor's Degree in Economics

2018 - 2024

Pontifical Catholic University of Peru (PUCP)

Highlighted Courses: Econometrics, Advanced Microeconomics, Data Analysis with Python, and Machine Learning.

Complementary Training in Software

2019 - 2021

CEDHINFO, Lima, Peru

  • SQL Server: Design and management of relational databases
  • Advanced Excel: Data analysis, visualization, and macros
  • Power BI: Creation of interactive dashboards

Professional Experience

Research Assistant at the Pontifical Catholic University of Peru

2024 - Present

Lima, Peru

  • Provided technical support on the CSDID project, optimizing code and solving implementation issues.
  • Computer Vision Expert:
    • Implemented Machine Learning models for pothole detection and classification using computer vision techniques.
    • Developed interactive geolocation maps with Streamlit to visualize precise pothole locations.
    • Created performance metrics (Accuracy, Precision, Recall) to evaluate and optimize the detection model.

Domain Expertise

  • Regresión Lineal y Alta Dimensión: Experto en mínimos cuadrados y regresiones penalizadas (Lasso, Double Lasso) para inferencias predictivas en contextos moderados y altos (p > n).
  • Inferencia Causal y Técnicas Modernas: Dominio en ensayos de control aleatorio (ECA), Random Forest, redes neuronales profundas, y Debiased Machine Learning (DML) para modelos no lineales.