Hi, I'm Pierre Counathe.

I am a data enthusiast, constantly seeking new challenges and opportunities for learning. My interests lie in the fields of Machine Learning, Deep Learning, and Optimization, and I am currently seeking a full-time position in these areas. Please take a look at my work below.

Learn More

Recent Projects

Financial Time Series Generation with GANs

Generate Financial Time Series (returns) with similar statistical properties (mean, standard deviation, skewness, kurtosis, acf, etc.) to a targeted market using GANs acting not in the time domain but in the frequency domain, using FFT and inverse FFT to switch from one domain to the other.
DEEP LEARNING TIME SERIES GAN FFT TENSORFLOW GOOGLE CLOUD PLATFORM

Dynamic Pricing Optimization for Real Estate Assets

Optimize Real Estate prices dynamically to meet financial constraints and deadlines (loan repayment dates) and maximize revenues.
SCRAPING STATISTICAL ANALYSIS MACHINE LEARNING OPTIMIZATION
BEAUTIFULSOUP SCIKIT-LEARN

Droughts Forecasting

Forecast droughts in the US with a 6-week lead time using weather time series and static soil data. Compare LSTM performance to classic ML models.
DEEP LEARNING MACHINE LEARNING TIME SERIES PYTORCH SCIKIT-LEARN
GOOGLE CLOUD PLATFORM

Image Completion with GANs

A Generative Adversarial Network that completes incomplete portraits. From left to right, images are: the original portrait, the incomplete portrait (missing region inside the red rectangle), the completed portrait.
DEEP LEARNING COMPUTER VISION GAN PYTORCH AZURE

NBA Shot Success Probability

Visualization tool for basketball games, incorporating the Shot Success Probability at any time.
MACHINE LEARNING SCIKIT-LEARN