A Senior Data Scientist with a track record of designing and project managing complex data initiatives that utilise advanced algorithms to create solutions that dynamically realise business objectives. Key strengths include: analysing requirements and rapidly developing prototypes to drive creation of innovative solutions that facilitate realisation of business aims; aligning detailed scientific knowledge with genuine business acumen to dynamically translate organisational objectives into superior delivery of solutions; driving collaborative analysis of problems in order to identify optimum solutions that yield positive ROI; and translating business objectives to technical teams in order to create solutions which ensure deliverables match business needs. Author of the book Business Applications of Deep Learning, APRESS, New York, May 2018.
- Machine Learning
- Deep Neural Networks
- Computational Physics
- Statistical Analysis
- Amazon Web Services
- Github/ Gitlab
- Pattern Recognition
- Python / R / Matlab / SQL
- Tensorflow & Pytorch
- Support Vector Machines
- Credit Risk Analysis
- Random Forest & Boosting trees
- Bayesian Statistics / Graphical models
Most recent roles:
Jan 2019 – Data Scientist at Hazy.com ▪ Develop and deploy algorithms based on Generative Adversarial Networks for data augmentation and conditional data synthetization.
Sep 2018 – Dez 2018, Data Scientist at Tesco (contractor) ▪ Use of Dynamical Bayesian Networks to predict stock levels in a supermarket. Savings in stock routines by 10 millions.
Apr 2018 – Aug 2018, Data Scientist at British Telecom (contractor) ▪ Applied Machine Learning algorithms for analysis and optimization of information flow and user behaviour at British Telecom.
Ago 2017 – Mar 2018, Data Scientist at Direct Line (contractor) ▪ Develop Machine Learning for risk evaluation for auto insurance in UK. An increase in profitability of up to 30% was achieved through a redesign of models using neural embeddings and generative adversarial networks
Sep 2016 – Jul 2017, Deep Learning Specialist at Contextvision.se (contractor) ▪ Join a team of Data Scientists dedicated to apply deep learning algorithms for medical image and videos (CNNs and LSTMs).
Jan 2016 – Jul 2016, Lead data scientist, BUPA, London ▪ Responsible to build a data science unit, including reorganization of data architectures, algorithms and processes to transform Bupa into a data driven organization with a 360º perspective of customers transversal to operational, marketing and risk management.
May 2015 to August 2015: Data Scientist, Contractor at Stratified Medical, London ▪ Engaged in developing algorithms to extract insights from structured (neo4j graph databases) and unstructured (scientific publications stored in Elastic Search) databases, with millions of records, for drug discovery using deep learning algorithms.
September 2015 – December 2015, DataAI (my own company), London ▪ Co-founder, data scientist and project leader at Dataxyz. Working on a project using topic modelling for social media mentions and a platform for job matching.
Selected Interim Assignments:
10-2013 to 03_2014 – Closer / CCUK Credit Card Payment Defaulting Algorithms: Project Manager ▪ Call Credit UK initiated a project to create algorithms to determine a credit card applicant’s probability of defaulting. Engaged as PM to lead this project. Analysed existing scoring systems; defined project approach; led 4-strong development team; determined relevant algorithms and data processing methods; wrote SQL queries and liaised with customer to ensure correct model calibration. Succeeded in delivering algorithms based on Random Forest, resulting in an increased accuracy of 30%, facilitating 20% reduction in losses.
07-2014 to 03-2015 RedZebra Analytics: Banking Customer Prediction Tool: Data Scientist ▪ Red Zebra wanted to create a solution to predict customer behaviour and segmentation, using transactional data of a bank, which would allow them to match product offerings to customers. Engaged as Chief Data Scientist to create the solution. Analysed data models; identified transactional data patterns; created predictive models; utilised Self-Organized Maps, Neural Networks and Random Forests to created proof of concept.
06-2013 to 08-2013 Closer/Vodafone Portugal: Customer Churn Prediction Solution: Data Scientist ▪ Vodafone initiated implementation of a system to predict the probability of customers leaving their network. Engaged as Data Scientist to develop solution. Analysed complex inter-network data; liaised with stakeholders; created weighted graphs and developed stochastic diffusion model based on CDR data. Succeeded in delivering solution, resulting in Vodafone identifying potential departing customers & facilitating implementation of client retention processes and marketing strategies.
02-2013 to 04-2013 Closer/Turim Hotels, Portugal: Room Demand Algorithms: Data Scientist ▪ Turim Hotels wanted to create algorithms to predict future room demand in order to determine relevant sales & pricing strategy. Engaged as Data Scientist to create algorithms. Analysed historical data; identified Google data trends; utilised Deep Learning neural networks; scrutinised data from competitors; and separated data trends to account for seasonal variations. Succeeded in delivering algorithms, resulting in predicted sales accuracy of 90%, enabling identification of fallow periods which informed Turim’s sales & pricing strategy.
02-2015 to 05-2015 dataAI/Netra.io: Multimodal Image Recognition: Project Manager ▪ Netra.io requested an algorithm to do facial emotion recognition for clients, using images. Engaged as PM, created proof of concept; assigned developers; utilised Convolutional Neural Networks. Succeeded in creating solution – achieving human-level accuracy in identifying seven different emotional states within 30k image databases.
01-2012 to 12-2012 Inesting SA: Digital Marketing Dashboards: Project Manager ▪ Inesting SA initiated a project (Digitaligence.com) to create a dashboard to aggregate data from different social media platforms & Google analytics; to monitor and determine marketing ROI. Engaged as PM to lead project. Identified key KPIs; led 3-strong development team; assisted creation of artificial intelligence model; and configured rules for monitoring activity. Succeeded in delivering dashboards, resulting in defined sales data that facilitated companies’ ability to create effective and targeted sales strategies.
10-2006 to 03-2009 Portuguese Science Foundation: Credit Scoring Research: Project Manager ▪ Engaged as Principal Investigator in a scientific project to create a credit-scoring algorithm to rate SME’s/Big companies (<1000 employees). Led team of 3 research students; developed project approach; designed dashboards and led implementation. Published 15 scientific papers outlining project findings. Succeeded in creating algorithm to calculate and track the credit scoring of 100.000 French companies.
03-2004 to 06-2004 Los Alamos National Laboratory (USA): Postdoctoral Research ▪ Researcher at Center for Nonlinear Studies, working in a project on knowledge extraction from large biomedical datasets. Developed an algorithm for prediction of secondary structure of proteins using and iteration based recurrent neural network.
02-2002 to 03-2004 Portuguese Science Foundation: RBS Algorithm: Data Researcher ▪ Engaged as Principal Investigator in a scientific project using Artificial Neural Network algorithms to analyse Rutherford Backscattering (RBS) data. Analysed previous RBS experiments; scrutinised existing data; wrote code using C++; invented an algorithm called HLVQ;
- 11-2019 to 12-2021: Hazy, UK
- 06-2018 to 10-2019: Tesco Research Lab, UK
- 08-2017 to 05-2018: Contractor Directline UK
- 09-2016 to 07-2017: Deep Learning Research at ContextVision Sweden
- 01-2016 to 08-2016: Lead Data Scientist at BUPA Global
- 02-2015 to 12.2015: co-founder and Data Scientist at dataAI
- 07-2014 to 01-2015: RedZebra Analytics: Data Scientist
- 01-2013 to 06-2014: Closer (EU): Senior Consultant & Team leader
- 12-2011 to 12-2012: Inesting Marketing Tecnologico, Lisbon (PT): Project Manager
- 10-2010 to 01-2012: co-founder and CEO of Sairmais Ltd
- 03-2004 to 08-2004: Los Alamos National Laboratory (USA): Postdoctoral Researcher
- 09-2000 to 08-2010: Instituto Superior Engenharia Porto (PT): Full Professor of Physics
- 09-1998 to 08-2000: Lusofona University, Lisbon (PT): Professor of Computer science
- 07-1997 to 08-1998: CENG, (FR): Postdoctoral Researcher
- PhD Theoretical Physics: University of Coimbra, Portugal
- MSc Physics & Engineering of Plasmas: Nuclear Fusion Centre, Lisbon (grade 17/20)
- BSc (5 years) Physics: Instituto Superior Técnico, Lisbon (grade 15/20) – top engineering university in Portugal.