Profile Picture
Hey, I'm Felipe Papa Capalbo.
I’m a Production Engineer specialized in data analysis and pragmatic problem-solving, with expertise in Digital Twin applications, simulation, and optimization of manufacturing and logistics processes. I regularly employ predictive and explanatory data analytics, leveraging machine learning and advanced statistical methods to achieve impactful results.
Check out my projects arrow
My Background / About Me
I'm a Production Engineer currently working as a Business Analyst at FlexSim Brasil, where I focus on data-driven solutions and Digital Twins. I’ve optimized preventive maintenance scheduling for Brazil’s largest mining company (improving operational efficiency by 12%), developed causal demand forecasting models using advanced machine learning, and built custom multi-agent LLM chatbots with RAG to streamline simulation development and onboarding.
My background also includes prototype development with IoT, data integration (SQL/NoSQL), and an ongoing pursuit of a Master's in Production Engineering at UFSCar. I'm passionate about leveraging technology to solve real-world problems, whether in manufacturing, logistics, or new product development.
My Work / Projects
Diet Solver Project
Diet Solver
An interactive Python program that generates personalized meal plans to hit daily macro goals (protein, carbs, and fats) while respecting caloric and portion constraints. Uses integer linear programming (pulp) to deliver up to 5 solutions with minimal deviation.
Read More arrow
Brazilian E-commerce Analysis
Brazilian E-commerce Analysis
A research project using the Olist dataset (Kaggle) to identify key variables, formulate hypotheses, and plan advanced statistical analyses for real Brazilian e-commerce data. Explores customer behavior, logistics, and more.
Read More arrow
Final Paper Project
Autonomous Digital Twin Protocol
Final paper integrating Reinforcement Learning (PPO) and Discrete Event Simulation for cotton blending in textile spinning. Addresses uncertainties in fiber properties, real-time data, and logistics to optimize yarn quality and reduce production costs.
Read More arrow