Created an AI-powered Chatbot for data queries via WhatsApp, designing and developing the data architecture in Google Cloud Platform, using Big Query for

Data Warehousing, Cloud Run to deploy the bot API and Twilio to handle messages in WhatsApp. Used OpenAI's GPT models to identify questions from

users and convert them into SQL queries so the LLM model would return the results from the query to the user as a message with the requested data.

Built for directors and managers in the administrative, finance and marketing areas from shopping centers and media platforms.

Developed several media data analyses, discovering the best advertisement content to increase revenue and business metrics.

This is done using Python, AWS (get data from Athena) and GCP (get analytical data from Big Query), implementing data pipelines to get the data from the data sources and apply data processing techniques to refine it and get valuable insights.

These analyses helped optimize media investments for a news and media company.

Developed a delivery time prediction product for the logistics teams of many different malls in Brazil, based the roadmap of this product development on

CRISP-DM, finishing with a Decision Tree-based regression model to help logistics areas organize their delivery queue and decrease product delays.

Created dashboards for various stakeholders about shopping, e-commerce, and media performances using Metabase and Power BI, getting the data from a Data Lake and Google Analytics for a News platform in Brazil.

Skills: Data Science · Machine Learning · SQL · Large Language Models (LLM) · Generative AI · MLOps · Exploratory Data Analysis · Google Cloud Platform (GCP) · Data Analysis · Microsoft Power BI · Data Engineering · Python (Programming Language) · AWS SageMaker · Business Intelligence (BI) · PostgreSQL

Built data pipelines with Databricks and Big Query and ETL process using Python and Spark at a waiting time forecasting for patients in the ER product. Also, applied Machine Learning techniques that decreased the average model error by 30%, using better data cleaning and pre-processing techniques such as outlier detection and categorical feature encoding. Allowing hospitals in Brazil to have a better user experience for their patients in the ER, increasing the total hospital’s NPS (Net Promoter Score). 

Skills: Data Science · Machine Learning · MLOps · PySpark · Apache Spark · Google Cloud Platform (GCP) · Data Engineering

Member of the Research and Development Data Science team, developing innovative projects from data modeling to image classification and data analytics.

Contributed to three key projects for a Brazilian Traffic Equipment company's R&D department. Projects encompassed data modeling, vehicle classification, and image quality classification. Utilized Python for ETL, including prediction processes and model evaluations, while employing Kafka and Airflow for architectural infrastructure. Employed Python frameworks like TensorFlow and OpenCV for image classification. Achievements included reducing anomaly detection time from 1 day to 3 hours, significantly enhancing operational efficiency.

Developed a hardware recommender system in Python with traffic equipment data that helped the company that produced this equipment to assign the best-fit hardware for each piece of equipment, optimizing their investment in traffic equipment development.

Skills: Data Science · Machine Learning · MLOps · MLflow · Apache Kafka · Apache Airflow · Exploratory Data Analysis · Data Analysis · Python (Programming Language) · PostgreSQL

Used decision tree-based models in vehicle speed forecasting, in which the Random Forest Regressor was the most performative, using Python and traffic sensors data for a traffic equipment company. This project gave the company better measurements for their vehicle calculation equipment.

Developed dashboards for traffic equipment and contractual data analytics for a Traffic Equipment company using several Python libraries, including NumPy and Pandas for data processing, Plotly and Mapbox for data visualization, and the Streamlit framework to build an app for interactive dashboards. This allowed the operations teams to understand what metrics were decreasing the overall performance of traffic equipment.

Built an MLops environment for model tracking and deployment using MLflow to track several Deep Learning models from an R&D department in a traffic equipment company. This helped the company to monitor their computer vision models and track its performance metrics in real-time.

Skills: Data Science · Machine Learning · Python

Applied Time Series forecasting techniques in power generator equipment analysis for Predictive Maintenance using Autoregressive Models, mostly ARX models for an energy industry Artificial Intelligence provider. This allowed our clients in the energy industry to optimize their maintenance costs for power generation machines.

Developed Data Science projects concerning sales forecasting, recommender systems, and customer segmentation applied to the retail market. Used Python and Power BI for the reports and analysis. Also, KMeans Algorithm concerning client clustering and Apriori Algorithm to recommend products based on user interaction for a Brazilian mobility systems and sales force automation company.

Skills: Data Science · Python (Programming Language)