nasa-space-apps-challenge-2021
Repository for the Mapping Space Trash in Real Time project from 2021 Nasa Space Apps Challenge.
Jupyter Notebook
1
0
leet-code
My solutions to some Leet Code questions I have solved.
Jupyter Notebook
0
0
Luan Brasil
Mentor
Rising Codementor
US$8.00
For every 15 mins
ABOUT ME
Senior Data Scientist with 5+ years of experience using Python and SQL
Senior Data Scientist with 5+ years of experience using Python and SQL
Data Scientist with 6 years of expertise in Machine Learning, Generative AI, Data Analysis and Visualization and Data Engineering. From retail segmentation to predictive maintenance, I specialize in crafting impactful solutions utilizing Python, SQL, GCP, AWS, and innovative approaches.
I have transformed data accessibility with an AI-driven WhatsApp Chatbot, providing tangible benefits to directors and managers. Additionally, I have excelled in optimizing media investments, engineering delivery time predictions. Proficiency in ETL design, regression modeling, and agile methodologies underlines my commitment to delivering high-quality solutions.
Beyond technical skills, my strong communication abilities facilitate effective collaboration throughout cross-functional teams and ensure successful project outcomes.
Portuguese, English
Brasilia (-03:00)
Joined January 2024
EXPERTISE
6 years experience
6 years experience
6 years experience
2 years experience
1 year experience
6 years experience
2 years experience
REVIEWS FROM CLIENTS
Luan's profile has been carefully vetted and approved as a Codementor. Connect with Luan now, and leave a review for them once you're done!
SOCIAL PRESENCE
EMPLOYMENTS
Senior Data Scientist
Thomson Reuters
2023-12-01-Present
Developed an AI-driven solution for predictive risk analysis in customer experience (CX) and customer success (CS).
The project f...
Developed an AI-driven solution for predictive risk analysis in customer experience (CX) and customer success (CS).
The project focused on predicting the Net Promoter Score (NPS) for individual customers and classifying them as promoters, neutrals, or detractors.
Using Python as the primary language and GPT-4 as the main LLM, the system combined a regression model for NPS prediction with explainability techniques to analyze customer data obtained via API.
An LLM chain was implemented to automatically generate detailed PDF reports, including actionable plans for the CS team.
The solution streamlined operations, providing data-driven insights and improving customer retention and satisfaction.
Development and maintenance of taxes forecasting using Time Series models (e.g. Exponential Smoothing, Naive Forecasting), including new experiments and results analyzis, at a cross-functional team for the Tax Intelligence product. Responsible for delivering taxes forecasting analysis and communicating with stakeholders and managers.
Python
Data Science
Exploratory Data Analysis
View more
Python
Data Science
Exploratory Data Analysis
Time Series Forecasting
View more
Data Scientist
JCPM Group
2022-04-01-2023-12-01
Created an AI-powered Chatbot for data queries via WhatsApp, designing and developing the data architecture in Google Cloud Platform, usi...
Created an AI-powered Chatbot for data queries via WhatsApp, designing and developing the data architecture in Google Cloud Platform, using BigQuery 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. Also, I leveraged a RAG mechanism using Pinecone for vector storage and search to enhance the bot answers and optimize prompts. 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 BigQuery), 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.
Python
SQL
Machine learning
View more
Python
SQL
Machine learning
Data Science
Google Cloud Platform
Data Visualization
Exploratory Data Analysis
Metabase
OpenAI
AWS
Langchain
View more
Senior Data Scientist Consultant
DASA
2023-03-01-2023-06-01
Built data pipelines with Databricks and BigQuery and ETL process using Python and Spark at a waiting time forecasting for patients in th...
Built data pipelines with Databricks and BigQuery 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 preprocessing 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).
Python
Machine learning
Data Science
View more
Python
Machine learning
Data Science
Google Cloud Platform
Data Engineering
MLOps
View more
PROJECTS
Churn PredictionView Project
2022
The purpose of this project was to develop a classification model for churn prediction for a fictitious company called Alura Voz, in orde...
The purpose of this project was to develop a classification model for churn prediction for a fictitious company called Alura Voz, in order to help them reduce their churn rate.
For this project, I followed the CRISP-DM method, a widely used approach in Data Science projects, which consists of: business understanding, data understanding, data preparation, modeling, evaluation, and implementation. I covered as much as possible of the concepts up to the evaluation phase.
Along the project, I addressed data analysis techniques, preprocessing, feature selection, and the choice and evaluation of the performance of Machine Learning models, besides feature importances analysis.
Python
NumPy
Matplotlib
View more
Python
NumPy
Matplotlib
Pandas
Machine learning
Classification
Data Science
Data Visualization
Exploratory Data Analysis
Seaborn
Plotly
Scikit-learn
View more
The Oracle of BaconView Project
2021
The Oracle of Bacon is a web game where the objective of the game is to start with any actor or actress who has been in a movie and conne...
The Oracle of Bacon is a web game where the objective of the game is to start with any actor or actress who has been in a movie and connect them to Kevin Bacon in the smallest number of links possible. Two people are linked if they've been in a movie together.
This project uses Breadth-First Search in graphs to implement the solution to the challenge. Also, it uses Streamlit to build the app that runs the solution.
Python
Data Science
Graph Algorithms
View more
Python
Data Science
Graph Algorithms
Streamlit
View more