The fastai book, published as Jupyter Notebooks

Financial portfolio optimisation in python, including classical efficient frontier, Black-Litterman, Hierarchical Risk Parity

fklearn: Functional Machine Learning

Analysis and datasets about football (soccer)

PyTorch library for transforming entities like companies, products, etc. into vectors to support scalable Record Linkage / Entity Resolution using Approximate Nearest Neighbors.

A Flexible Deep Learning Approach to Fuzzy String Matching

Work on using Retrieval-Augmented Generation (RAG) to combine Fast Healthcare Interoperable Resources (FHIR) with Generative AI.

This project focuses on DeepER, a deep learning framework for entity resolution (record deduplication). It examines how DeepER performs on benchmark datasets under a variety of conditions and also …

A simple command line interface to the datamade/dedupe library.

A streaming algorithm for graph clustering

Scripts and data for my analysis of the usage of type annotations in the wild

Research code for spectral algorithms/graph sparsification etc.