I am a recent graduate of the MSc in Statistical Science program at the University of Oxford, where I pursued a double master's degree in parallel with my Master's program at ENSAE Paris. My academic background and interests lie at the intersection of Machine Learning and Economics.
Contact : adrien[dot]chkirate[at]st-hughs[dot]ox[dot]ac[dot]uk
- "Gaining Economic Insights Through Deep Learning on Satellite Imagery" explores the potential of high-resolution satellite imagery for predicting urban wealth levels, as indicated by income per capita. It incorporates a pipeline capable of extracting the complete road network of an area while also detecting various essential infrastructure, such as airports and sports facilities. Paper, Repository
-
A project exploring the performance of logistic regression, random forest, and CatBoost algorithms in classifying galaxies, quasars, and stars. The data consists of 200,000 astronomical objects from the Sloan Digital Sky Survey. Paper, Repository
-
A project exploring The Uppsala Conflict Data Program (UCDP) which is the world’s main provider of data on organised violence and the oldest ongoing data collection project for civil war, with a history of almost 40 years. Dataset, Repository
- A web application simulating the jeep problem also known as the desert crossing problem also integrating an optimal solution. Application, Repository
- A web application developped during an internship at the xlim research institute to facilitate the manipulation of experimental curves and optimize their fitting to Gaussian distributions for researchers. Application, Repository
- 1st place at the 2022 Hi Paris Hackacthon delivered by Capgemini. Segmentation and classification computer vision tasks.