NICKSSON CKAYO ARRAIS DE FREITAS
Santa cruz - Rio Grande do Norte State
Summary
Experienced data scientist specializing in data analysis, software development, machine learning, and deep learning. Since 2012, I've built data-driven solutions with artificial intelligence to enhance business growth and global safety in many sectors, including public security, industry 4.0, education, virtual assistants and chatbots, renewable energy, sports, and health. At SiDi Recife, one of the largest CCTs in Brazil, I'm responsible for leading data science and AI projects, demonstrating expertise in cross-functional team leadership and agile methodologies. I crafted commercial proposals with innovative solutions for complex business challenges. I've played a pivotal role in attracting new business opportunities and empowering stakeholders to make informed decisions. I have significantly contributed to cultivating a data-driven culture, accelerating digital transformation, and delivering measurable outcomes in value generation and operational cost efficiency.
Overview
12
12
years of professional experience
1
1
Certification
Work History
Lead Data Scientist
SiDi
04.2023 - Current
- Developed deep learning models using transformer architectures for AI-assisted smartphone apps, such as machine translation, natural language understanding, and punctuation restoration.
- Reduced time to access information from 3 days to mere seconds by developing a Big Data platform for a national public lighting company, leveraging open-source tools to monitor and manage IoT sensor data.
- Enhanced a private system for urban mobility and public safety in Brazil, leveraging vehicle trajectory data from external sensors. I provided new insights to stakeholders, identified system errors through data analysis, and introduced novel AI algorithms for vehicle cloning and convoy detections.
- Led an educational technology residency project in information security, focusing on data science and artificial intelligence. Delivered over 900 hours of data science and machine learning training to 20 students, published five papers at national and international conferences, and achieved a grade 9 in student satisfaction.
- Created a platform for time series forecasting using data science methods and machine learning algorithms for supply chain demand forecasting, improving production and inventory efficiency, accelerating decision-making, optimizing the production chain, and lowering operational costs.
Senior Data Scientist
SiDi
08.2021 - 04.2023
- Collaborated in developing a project that reduced the gas consumption of a sustainable chemical company by up to 7% in 2022
- Led two technological residency projects in Data Science and Computer Vision (postgraduate), respectively
- Developed data science, machine learning, and computer vision projects and produced seven papers accepted in national and international conferences with qualifications above A4.
- Developed a decision support system in the Cloud (AWS Services) for a market-leading company in public lighting management to increase the security of the operations, minimize manual human effort, and save operational costs.
Senior Data Scientist
SiDi
02.2021 - 02.2023
- Uncovered critical insights by conducting comprehensive exploratory data analysis of undergraduate student exam results. This analysis illuminated vital trends and patterns, providing managers and teachers with actionable intelligence to inform their decision-making processes.
- Developed descriptive and exploratory data analysis and built machine learning models to predict COVID-19 from time series data
Data Scientist
Insight Data Science Lab
02.2018 - 02.2022
- Analyzed data on robberies, violent crimes, and murders and implemented machine learning models to discover patterns and insights on Citizen Platform of Government of Ceará project
- Revealed patterns of semi-open prisoners using trajectory data and implemented deep learning models for human and vehicle identification to support public security agencies SSPDS-CE and PRF on Scientific and Technological Intelligence project in Public Security project.
- Developed scientific studies to create a platform that will allow integration and analysis of public security data from Brazilian states, enabling implementation of a new governance model using data science and machine learning for anomaly detection and crime prediction from Big Data on the Big Data and Artificial Intelligence applied to the Public Security project.
Senior Data Scientist
DHAUZ
06.2021 - 08.2021
- Developed a demand forecasting system for a leading telecommunications company to predict sales trends for various plans using time series analysis.
Machine Learning Researcher
Rio Grande do Norte State University (UERN)
01.2016 - 12.2016
- Collected and integrated various data types, such as satellite images and weather data, focusing on the Caatinga biome in a semi-arid region in Brazil
- Cleaned data to correct noise or errors and ensure higher data quality
- Implemented predictive data analysis and algorithms to predict weather conditions and phenomena
- Developed novel approaches to weather forecasting, integrating advanced image processing techniques and meteorological knowledge.
Data Scientist
Funceme
08.2015 - 03.2016
- Responsible for data preparation, analysis, designing, testing, and applying complex algorithms to accurately differentiate cloud cover from other natural elements in remote sensing data using Geospatial Data Analysis Tools on the Application of Pattern Recognition Techniques for Cloud Identification project
- Responsible for data collection and preparation, image processing and analysis, development of Normalized difference vegetation index (NDVI), geospatial analysis, data processing, and results interpretation and visualization to explore the dynamics between precipitation patterns and vegetation vigor in semi-arid regions on the Response of the Semi-Arid Vegetation to Precipitation Estimated by Weather Radar project.
IT Manager
Cred Carlos Camocim e Região
02.2015 - 07.2015
- Responsible for the IT infrastructure of a furniture industry.
Software Engineer
Centro de Oncologia e Hematologia de Mossoró
09.2013 - 03.2014
- Worked on developing a system for hospital management.
Artificial Intelligence Researcher
Universidade do Estado do Rio Grande do Norte
01.2012 - 12.2013
- Development of an Expert System for the early diagnosis of Diabetes Mellitus.
Education
Ph.D. - Computer Science
Federal University of Ceara (UFC)
Fortaleza06.2024
M.D. - Computer Science
Universidade Federal Rural Do Semi-Árido - Ufersa
Mossoro, Rio Grande Do Norte, Brazil02.2018
Bachelor of Science - Computer Science
Universidade Do Estado Do Rio Grande Do Norte
Mossoro, Rio Grande Do Norte, Brazil02.2015
Skills
- Machine Learning
- Natural Language Processing
- Python Programming
- Advanced data mining
- Problem-solving abilities
- Decision-Making
- Analytical Thinking
- Predictive Analytics
Certification
- Fluência Duolingo em Inglês: Elementar (estimativa) - Duolingo
- AI For Everyone - Coursera
- Introduction to TensorFlow for Artificial Intelligence, Machine Learning, and Deep Learning - Coursera
- Python para Data Science e Machine Learning - Udemy
- 5 diseases ailing research - and how to cure them - Elsevier
- 10 tips for writing a truly terrible review - Elsevier
- Construct Stock Market Indices - Coursera
- Machine Learning for All - Coursera
- Extreme Gradiente Boosting with XGboost - DataCamp
- Data Science for Everyone - DataCamp
- Introduction to Python - DataCamp
- Python Data Science Toolbox (Part 1) - DataCamp
- Python Data Science Toolbox (Part 2) - DataCamp
- Distributed Computing with Spark SQL - Coursera
- Tools for Data Science - Coursera
- PowerBI Report Development Crash Course - Coursera
- Data Visualization with Python - Coursera
- Parallel Programming with Dask in Python - DataCamp
- Introduction to Natural Language Processing in Python - DataCamp
- Fairness em Machine Learning - SiDi
- Desenvolvendo um projeto de Machine Learning end-to-end - SiDi
- Introduction to Designing Data Lakes on AWS - Coursera
- Introduction to Machine Learning in Production - DeepLearning.AI
- Introduction to Data Engineering - Coursera
- Supervised Machine Learning: Regression and Classification - DeepLearning.AI
- Visualização de Dados com Power BI - Stack Tecnologias
- Data Engineering usando a Modern Data Stack - Stack Tecnologias
- Introduction to Relational Databases (RDBMS) - Coursera
- Como Liderar e Trabalhar em Equipe - LinkedIn
- Programa de Mentoria Bússola Executiva - Bússola Executiva
- A Crash Course in Data Science - The Johns Hopkins University
- Machine Learning Data Lifecycle in Production - DeepLearning.AI
Skillset Overview
I've extensive experience in data science, data mining methodologies, machine learning, deep learning, statistics, Python, and SQL. My first project was in the healthcare sector in 2012, and I started mining data in 2013 using SQL and tools like Weka and Orange. I have extensive experience in Business and Data Understanding, Data Preparation, Data Mining, Statistical Modeling, Exploratory Data Analysis, and Data Visualization. I can implement dashboards in several tools, including PowerBI. I have also built and deployed supervised and unsupervised machine learning (and deep learning), such as classification, regression, clustering, association rules, anomaly detection, and time series forecasting. I've been using Python tools for data analysis since 2017, such as Pandas, Dask, Numpy, Matplotlib, Seaborn, Plotly, Folium, Leaflet, Scikit-learn, PyCaret, Keras, TensorFlow, and PyTorch. I'm good at building modern data platforms using Airbyte, Spark, Airflow, DBT, Snowflake, and Clickhouse. I have extensive experience in data ingestion (APIs, Web Scraping), databases (SQL and NoSQL), data pipelines, ETL, ELT, Data Warehouses (i.e., star schema), Data Lakes, and Lakehouse. I am adept at building end-to-end projects on AWS, using services like Glue, Lambda, Athena, and Quicksight. Finally, I have been specializing in Machine Translation (MT), Large Language Models (LLMs), Punctuation Restoration, and Automatic Speech Recognition (ASR). I can put a model into production and make continuous improvements (MLOps).
Awards
- PIE Awards: Eficiência in 2023, SiDi, Dec 2023
- Recognition Award of my Manager in 2023, SiDi, Jun 2023
- Award for performance and highlight of my manager in 2022, SiDi
Timeline
Lead Data Scientist
SiDi
04.2023 - Current
Senior Data Scientist
SiDi
08.2021 - 04.2023
Senior Data Scientist
DHAUZ
06.2021 - 08.2021
Senior Data Scientist
SiDi
02.2021 - 02.2023
Data Scientist
Insight Data Science Lab
02.2018 - 02.2022
Machine Learning Researcher
Rio Grande do Norte State University (UERN)
01.2016 - 12.2016
Data Scientist
Funceme
08.2015 - 03.2016
IT Manager
Cred Carlos Camocim e Região
02.2015 - 07.2015
Software Engineer
Centro de Oncologia e Hematologia de Mossoró
09.2013 - 03.2014
Artificial Intelligence Researcher
Universidade do Estado do Rio Grande do Norte
01.2012 - 12.2013
Ph.D. - Computer Science
Federal University of Ceara (UFC)
M.D. - Computer Science
Universidade Federal Rural Do Semi-Árido - Ufersa
Bachelor of Science - Computer Science
Universidade Do Estado Do Rio Grande Do Norte
Similar Profiles
Thiago LoretoThiago Loreto
QA Lead at SIDIQA Lead at SIDI
Mahmoud AbdelazizMahmoud Abdelaziz
Inspection Manager at Sidi Kerir Petrochemicals Co.Inspection Manager at Sidi Kerir Petrochemicals Co.
Marwa JellaliMarwa Jellali
Ingénieur agronome at Union Tunisienne de l'Agriculture et de la Pêche: Union Régionale de Sidi BouzidIngénieur agronome at Union Tunisienne de l'Agriculture et de la Pêche: Union Régionale de Sidi Bouzid