Data scientist focused on fintech & risk analytics. I ship clean, reproducible ML - Python, PyTorch, SQL, PySpark - turning messy data into auditable decisions.
-
University College London
- London
-
20:58
(UTC -12:00) - in/tamerates
Pinned Loading
-
deep-learning-cifar10-routing-net
deep-learning-cifar10-routing-net PublicPyTorch CIFAR-10 with a routed multi-expert CNN (RoutingNet); mixup + cosine LR; reproducible training/eval, modular code, and CI-ready.
Python 2
-
MatchOracle
MatchOracle PublicDeep ensemble EPL prediction engine — 13 base learners, Dixon-Coles statistical model, 376+ features, live season data, NLP sentiment analysis. 60.6% 3-way accuracy (vs market 55.6%).
Python
-
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.