|
Title
Links Contact |
Ah! So you want to learn more about me!
Welcome to my portfolio :)
I am a regular person! Recently graduated with a Master's in Engineering focusing on Applied Mathematics and Computer Science, and a Master's of Research in Artificial Intelligence and Complex Systems. I like to keep up with new research developments.
I enjoy coding, using math to solve problems, and creating things from scratch. I'm interested in statistics, machine learning, and deep learning. I've worked on various projects in different contexts, ranging from optimizing investment portfolios to automatic medical image analysis.
For the past 2 years, I've been working as a freelance Data Scientist & Software Engineer for clients in different industries such as insurance, energy, and marketing. I'm skilled at deploying products and love working on end-to-end projects.
Recent Projects
April 2024
CookinAgent: A RAG Agent for Retrieving Recipes Based on a City's Current Weather
CookinAgent is a recipe retrieval system developed for fun using LangChain. The model is based on the OpenAI LLM API and the wttr API for weather information. To enhance performance and scalability, CookinAgent stores embedded recipe data in a ChromaDB vectorstore. This allows for efficient retrieval and manipulation of recipes, ensuring swift and accurate responses to user queries.
January 2024
Joint Optic Disc and Cup Segmentation Based on Multi-label Deep Network and Polar Transformation
Glaucoma is a chronic eye disease that results in irreversible vision loss. The cup-to-disc ratio (CDR) is a crucial factor in the screening and diagnosis of glaucoma, making the accurate and automatic segmentation of the optic disc (OD) and optic cup (OC) from fundus images a critical task.
December 2023
The 5-Year NBA Career Predictor
This project is a fun side project designed to forecast whether a player will continue their career in the NBA for the next five years. It operates on an XGBoost classifier model trained on various player statistics like points scored and shots attempted.
September 2023
3D Lung Segmentation with a Deep Learning Generative Model
This internship project centers on the enhancement of lung segmentation, a critical process for identifying lung cancer. The primary objective is to refine the accuracy of identifying lung areas, especially in complex cases. Drawing inspiration from Wasserstein Generative Adversarial Networks (WGANs), we are adjusting our approach by fine-tuning how the system learns and incorporating existing knowledge about lung characteristics. By doing so, we aim to improve the precision and dependability of the lung identification process.
January 2023
Modeling Daily Price Variation of Electricity Futures Contracts in France and Germany
This project was completed as part of the Challenge Data, which was managed by the Data team at ENS Paris and carried out in partnership with the Collège de France and the DataLab at Institut Louis Bachelier.
The aim of this project, held by Qube Research and Technologies, is to model the daily price variation of highly volatile electricity futures contracts in France and Germany using multiple explanatory variables, including weather, energy commodity prices, and commercial data.
The goal is to create a model that can provide a good estimation of the daily price variation in these two countries, despite the highly volatile nature of electricity futures contracts.
February 2022
Color Quantization of RGB Images
In computer graphics, color quantization or color image quantization is quantization applied to color spaces; it is a process that reduces the number of distinct colors used in an image, usually with the intention that the new image should be as visually similar as possible to the original image.