John Kevin Barrera Contreras

Leveraging data science for development impact

Research project focused on measuring risk and accessibility to health systems across multiple countries. Developed innovative approaches combining:

• Graph theory and geographic datasets for accessibility modeling
• Machine learning models for risk assessment and prediction
• Comparative analysis with existing country-specific methodologies
• Mathematical modeling and algorithm development for large-scale data processing

Technologies: Python, Machine Learning, Graph Theory, Geospatial Analysis, Big Data

This project is part of my master’s degree research.

Building scalable data architectures for enterprise clients

Led multiple high-impact data architecture projects:

Liga MX Data Architecture (Mexico & LATAM)

• Designed and implemented end-to-end data architecture using Azure ecosystem
• Built scalable pipelines connecting multiple sources through Bronze, Silver, and Gold layers
• Enabled data-driven decision making for one of Latin America’s premier football leagues

BICE Bank Foundation Platform (Chile)

• Architected batch processing platform on Google Cloud Platform
• Designed secure data governance framework for financial institution
• Enabled large-scale data processing and analytics capabilities

InStride Platform Enhancement

• Collaborated on proof-of-concept development and platform improvements
• Defined comprehensive data taxonomy for multi-environment deployments
• Contributed to development team as architecture consultant

Technologies: Azure (Databricks, ADF, Data Lake Storage, Functions), GCP, Python, PySpark, SQL

Empowering fintech innovation through data

Data Engineer at RAPPIBANK, providing comprehensive business support for data-related initiatives across LATAM:

• Developed end-to-end data solutions, proposals, and ETL/ELT pipelines
• Specialized in graph-based data storage for complex relationship modeling
• Implemented data governance and quality frameworks
• Supported analytical models requiring geographical analysis, degree-of-separation calculations, and transaction data
• Explored and implemented CDC (Change Data Capture) solutions

Technologies: Snowflake, PySpark, Apache NiFi, Airflow, Fivetran, dbt, S3, AWS Glue, Neo4j, PostgreSQL

Advancing research at the intersection of data science and social impact

Collaborated on diverse research projects spanning public health, consumer behavior, and blockchain:

World Bank & PCM Projects

• Co-authored research published in “Analysis of the Health Network of Metropolitan Lima Against Large-Scale Earthquakes”
• Developed contact tracing algorithms and COVID-19 contagion probability models
• Simulated emergency scenarios and optimized routes using graph theory

Consumer Behavior Analysis

• Applied unsupervised machine learning and NLP to mine customer buying patterns
• Led by M. Núñez del Prado, Ph.D. and H. Alatrista S., Ph.D.

Blockchain Research

• Created educational cryptocurrency from Bitcoin fork
• Developed DApps on Ethereum platform with API integration
• Algorithm development in R and Julia (Led by F. Rosales M., Ph.D.)

Telecommunications Data Lake Project:

• Modeled data domains for enterprise data lake architecture
• Improved data quality processes across Raw, Silver, and Gold layers
• Implemented data ingestion pipelines using Hortonworks stack

Big Data implementations for Peruvian banking sector:

• Developed solutions using Apache ecosystem (Hadoop, Hive, Spark, Sqoop, Kafka, HBase, Zookeeper)
• Worked with Databricks, Cassandra for distributed data processing
• Created multiple proof-of-concepts for client evaluation
• Completed comprehensive Big Data training and certification

Electoral data processing and validation:

• Developed ETL processes for political organization reports
• Implemented data cleaning and validation against RENIEC database
• Created error verification and user confirmation workflows

Advanced studies in artificial intelligence, machine learning, and computational methods.

Master’s Thesis: Research project with The World Bank on measuring risk and accessibility to health systems using graph theory and machine learning.

Comprehensive foundation in computer science, mathematics, and software engineering.

Recipient of Alianza del Pacífico Scholarship

International exchange program focused on economics and business analytics.

Developed contact tracing algorithms and contagion probability models for Peru’s Ministry of Health. Applied graph theory and machine learning to public health crisis response.

Multi-country research project analyzing health system accessibility and risk in seismic-prone regions. Published research informing policy decisions for disaster preparedness.

Collaboration with INIA, UP, and UALM to create mobile application for artisanal milk production. Implemented neural networks for quality prediction and production optimization.

Created educational cryptocurrency based on Bitcoin and Learncoin source code. Developed comprehensive video tutorial series for blockchain education.

Developed decentralized applications on Ethereum blockchain platform. Explored smart contract development and blockchain-based solutions.

Innovation through collaboration

2020

• 🥈 2nd Place - Hackathon Contact Tracing (COVID-19 Response)

2018

• 🥇 1st Place - HACKATHON ARTTEC (Art & Technology)
• 🥇 1st Place - IBM CODING DAY: Hackathon for a Peru #SINANEMIA (Social Impact)

2016

• 🎓 Recipient of Alianza del Pacífico Scholarship
• Competitive international exchange program across Pacific Alliance countries