On this page, I present my skills in solving business problems using Data Science concepts and tools, through projects based on public datasets.
You will also find my professional experience, technical skills, tools, and core concepts related to Data Science.
Feel free to get in touch through the links at the bottom of the page.
I hold a degree in Systems Analysis and Development from the São Paulo State College of Technology and currently work as a Data Scientist in the consultancy services.
I work in the Data Science area, building and presenting Machine learning and Analytics project results in a clear and understandable way for all stakeholders involved. In addition, I apply Data Science methods to develop indicators and solutions that enhance the company’s products and services. I actively collaborate with cross-functional teams to ensure that data science projects are aligned with business goals, delivering innovative solutions that generate tangible results.
I work on both personal and professional projects related to Data Science, Machine Learning/AI and Analytics, continuously strengthening my ability to solve real-world business problems and deepening my mastery of analytical tools.
I'm seeking opportunities to work professionally in an international environment, contributing to improved decision-making through the development of data-driven solutions.
Delivered production-ready data solutions for real client challenges, covering the full lifecycle from business problem framing and data engineering to model deployment and monitoring in cloud environments.
Led the design and implementation of analytics and machine learning solutions to support strategic decision-making, transforming complex data into clear insights and executive-level KPIs.
I specialize in bridging business and technology, combining strong data engineering, advanced analytics, and machine learning to drive measurable business impact and scalable, data-driven decisions.
Development of a customer segmentation model for a banking credit card portfolio using K-Means clustering, aimed at increasing profitability through targeted CRM strategies. The project grouped 8,950 clients into 8 behavioral clusters based on spending patterns, credit usage, cash advance behavior, and payment profile. As a result, the segmentation enables actionable strategies for revenue growth (upsell/cross-sell), cost reduction (more efficient campaigns), and risk mitigation (loss prevention). The expected annual ROI ranges from ~$30K (conservative) to ~$250K+ (optimistic), with a moderate expected impact around ~$100K/year, subject to A/B testing validation.
Development of a sales forecasting model for the Rossmann pharmaceutical retail chain using time series regression algorithms, aimed at cost reduction. The model reduced the average forecasting error from 36% to 4.65% (-31%) for the next six weeks, representing approximately €19 million in additional monthly revenue, using Kaggle data.
Identification of properties priced below market average and definition of optimal resale prices through exploratory data analysis in Python.
Development of an interactive web application for exploratory analysis of nutritional data from various cereal brands. The dashboard enables comparison of key nutritional metrics such as calories, sugars, sodium, and protein across manufacturers.
Analytical dashboard focused on inferential statistics. The application performs hypothesis tests (ANOVA and T-test) and real-time correlation analyses to determine the statistical significance of factors such as sleep, frequency, and study hours on students' final performance.
This project aimed to develop a Machine Learning model using Convolutional Neural Networks (CNNs) to classify chest radiography images and predict the Agatston coronary calcium score. The internally developed model achieved a 32% cost reduction and reached a ROC-AUC of 0.75 using the VGG-19 architecture, demonstrating its ability to distinguish patients with different levels of coronary calcification—an important indicator of cardiovascular risk.
This project focused on establishing reference intervals for testosterone tests using mass spectrometry, implemented in R. Accurate reference intervals are critical for correct clinical interpretation. The resulting reference values improved diagnostic accuracy and supported more informed clinical decision-making.
Application of Generative AI to unstructured MRI and CT scan reports to build a patient journey dashboard for spine orthopedics within Digital Health. The solution enabled strategic decision-making for Primary Care and Digital Emergency services, resulting in R$3.9 million in additional revenue through optimized resource allocation and an 11% improvement in patient retention.
Use of Generative AI on unstructured MRI, CT, and colonoscopy reports to identify patients undergoing colonoscopy and biopsy, extract critical information for colorectal cancer detection, and identify gaps in care. The solution supported oncology screening, population health management, and cost reduction for health insurance providers.
Feel free to reach out.