Joyce Liz Borges Email & Phone Number

Rio De Janeiro, Brazil

- Created a data process to monitor financial portfolios in a big data system (over 70 million clients).- Deployed and maintained machine learning model processes produced by the data scientists' team.- ETL data from financial institutions to ensure strong governance and data quality.Tools used include Python, Spark, Hadoop, and SQL.

Build and maintain robust data solutions and guarantee high-quality financial information through data analysis and automation processes with Spark.- Developed several automation scripts and implemented ETL pipelines with Python and Spark.- Empowering financial analysis and decision-making through customer evaluation and credit portfolio monitoring.- Credit portfolio evaluation based on performance metrics and KPIs (30x3, 60x6, and 90x12).Some achievements:- Created a Python program to automate backtesting, KS evaluation, and rating distribution on customer databases.- Built pipelines to produce highly reliable reports and reduce errors with regulatory bodies.- Produced dashboards and KPIs for real-time evaluation by the company's top management.- Tools used include Python, PySpark, and SQL (Athena).

Rio De Janeiro, Brazil

Worked with product managers and business partners to come up with innovative solutions and create new data products. I acted on multi-disciplinary projects that required both data science and development skills.- Development of 10+ automatizations to produce high-quality data at scale- Design and implement ETL pipelines- Crawler development and web scrapping to enrichment databases and support the data scientist teams (BS4, Selenium and others)- Perform data analysis (pandas, numpy, pyspark, scikit-learn) to support business decisions to several players in the Brazilian market- Machine Learning /Modeling for classification, clustering, and insight generation (keras, TensorFlow)- Create a dashboard and KPIs creation (Quicksight, Power BI, Tableau, and streamlit)Some achievements: - Started data product creating a Python web scrapper that monthly collects data from +400 websites- Developed a Python process that collects +10000 points of interest (PDI) and calculates metrics and KPIs- Started a data quality Python program that reduces time to cleanse client's database

Rio De Janeiro, Rio De Janeiro, Brazil

Managed applied research, analysis, and data visualization in the environmental field.- Conducted a survey and organized social and environmental variables from different sources (Extract, Transform, Load - ETL)- Applied data science and ML techniques, such as regression, classification, and unsupervised learning algorithms, to model and describe the drivers of socio-environmental changes in land use.- Engaging in technical communication, creating both reports and data visualizations for environmental agencies, technical staff, and lay audiences.Tools used include R software (tidyverse, dplyr, ggplot), Python (pandas, numpy, scikit-learn, Keras, SciPy), and geotools (QGIS).