Curriculum Vitae
Doctor Peter J Bleackley
Professional Experience
Consultant Data Scientist
Playful Technology Limited March 2015 - July 2024
Director of a data science consultancy undertaking research and development projects in data science and related technologies.
Clients
- CloudNC
- Research and Development of Bayesian Models to predict the optimal operating parameters for CNC tools
- eFinancialCareers
- Startiing up new data science function for client after demerger from parent company.
- Cross-training a developer as a data scientist and interviewing permanent senior data scientist.
- Investigating possible improvements to existing job matching system, and prototyping content-based recommendation system to match candidates to jobs.
- Arthur D Little
- Developing Natural Language Processing technology for a medical diagnostics startup. Included work on separating sentences containing conjunctions into multiple sentences.
- Adecco
- Named Entity Recognition, Named Entity Linking and document classification for matching CVs to job descriptions.
- Sopra Steria
- Improving the training system for anti-money-laundering software for HSBC.
- GHFP Reseach Institute
- Created an interactive map of the Better Place Index.
- Amey Strategic Consulting
- Created an automatic diagnostic system to detect faults in traffic flow sensors on the strategic road network.
- Cambridge Quantum Computing Limited
- Developed MongoDB-based data capture and postprocessing software for a quantum random number generation system.
- Pentland Brands Limited
- Performed a proof-of-concept study on the use of facial point-cloud data to recommend swimming goggles.
- Rolls Royce AI Hub
- Created a testbed for a specialist search application
- Developed a parser library to extract logically-structured data from technical documents in a variety of formats, including scanned PDFs.
- Advised on tenders and collaborative projects.
- All Street Research
- Rapid-prototyped a document mining system that identified the most relevant paragraphs for given themes in corporate documents.
- Boehringer Ingelheim
- Investigated text mining of healthcare forums for phamacovigilance data. True 212
- Created a computational linguistics pipeline to enable semantic matching between blogs and external content to identify relevant links.
- TechBit
- Developed algorithms to classify swimming strokes and extract performance metrics from motion sensor data.
- Formisimo
- Improved the accuracy of a system that predicted, in real time, whether a user would complete or abandon a web form.
- Social Finance
- Created an ETL system that transformed XML files of social services data into Postgres tables, cleansed inconsistent data, inferred missing data where possible, and prevented deanonymisation.
- Metafused
- Created a system to extract semantic data from free text
- Valtech
- Advised a social media startup on artificial intelligence technology.
Mathematical Software Developer
Arithmetica Limited June 2014 - March 2015
Developed algorithms for lidar point cloud analysis and vector model fitting software.
Product Innovation and Experience Lead
HumanLearning Limited November 2013 - June 2014
Developed content and behaviour based recommendation for a social learning /business communication product.
Contractor
Zooey Consulting September 2013 - October 2013
Investigated specialist document analysis technology.
Chief Data Analyst
MulTplx Limited September 2011 - June 2013
Developed Python software that infers customer behaviour from interactions with display devices in mobile phone shops, and visualisations (HTML 5 and Javascript) and analyses of the data gathered. Clients included Samsung and EE.
Research Engineer
BBC Research and Development April 2001 - July 2011
Projects included:
- Extracting semantic data from free text. I created a database of timed segments of programmes from the BBC’s archive catalogue, and investigated techniques for analysing subtitles, and applications for this data. I later reimplemented one of the algorithms I had investigated and contributed it to the Gensim topic modelling library.
- CALLAS A European Collaborative project to investigate Affective Computing techniques for interactive storytelling.
- Artificial intelligence techniques for broadcast chain diagnostics. Identified suitable technology, and prototyped, using C++.
- Investigating suitable parameters for a low-delay MPEG 2 coder. Software simulation to inform hardware design using C++.
- Hardware implementation of the Dirac video codec. Created Open Source circuits for arithmetic coding / decoding and exp-golomb coding /decoding. Refined algorithms to make them suitable for hardware implementation.
Education
- PhD Astrophysics, University of Leicester, 2000. Spectroscopy and Variability of Narrow-Line Seyfert 1 Galaxies
- MSci Physics, University of Durham, 1996. Class 2:1