Brett Drury is a British / Portuguese national who is currently working on cutting edge NLP and ML techniques to extract value from unstructured data.

Brett has worked in both the Private Sector and Academia in Portugal, Ireland, Brazil, and the UK. He specializes in Probabilistic Reasoning and NLP. However, he has worked with other ML techniques such as variants of Deep Learning in areas such as image classification.

The topic of his Ph.D. thesis was text mining applied to stock market prediction, and his Post-Doctoral work was building Bayes Nets from text for the sugar-cane domain. The Bayes Nets were evaluated on the Sao Paulo commodities market. He was also a research fellow on the ROCSAFE H2020 Project ( http://rocsafe.eu) at the National University of Ireland Galway. His research work was applied, and therefore has been cited by organizations such as the Bank of England ( http://eprints.lse.ac.uk/62548/1/Schonhardt-Bailey_text%20mining%20handbook.pdf)

Brett was also a former holder of a PIPE Grant from FAPESP ( https://bv.fapesp.br/en/pesquisador/668348/brett-mylo-drury/), as well as an Innovation Fellow at the Royal Society of Engineering ( http://www.fapesp.br/11277). He is an academic referee for a number of academic journals such as Computer and Electronics in Agriculture, and a PC member for a number of academic conferences such as Intelligent Data Analysis.

PhD Thesis

Title: A Text Mining System for Evaluating the Stock Market’s Response To News

Supervisor: Luis Torgo; Co-supervisor: José João Almeida, University of Minho, Portugal

MAP-i Doctoral Programme in Computer Science

Finished: Apr/2013

Abstract

This thesis presents a text mining system which was designed to predict the direction of a share or financial market. The text mining system is a complete pipeline which: 1. scrapes new stories from the Internet, 2. extracts news text from the scraped news stories, 3. identifies relevant news stories for a specific company or financial market, 4. classifies sentences, news stories and quotes and 5. makes a trading inference using these classifications.

The thesis documents advances in 1. ontology construction and maintenance, 2. fine grained event and sentiment extraction and classification at the sentence level, 3. news story classification, 4. direct speech classification and 5. information retrieval. These advances were also contributions to the fields of semi-supervised learning and ontology engineering.

The advances in the news classification at the document, sentence and direct speech level demonstrate measurable advantages in trading experiments on the FTSE 250 financial markets over competing text classification strategies. The complete system, however, did not demonstrate a measurable trading advantage in experiments conducted on the shares of Apple, Google, IBM and Microsoft. The system, however, provides a blueprint for future systems.