Skills Overview

Building data-pipelines, feature engineering, modelling and deploying regression models to predict the sales price for a used industrial machinery in multiple territories.
Customer segmentation (k-means clustering) to make behaviour-based personas to personalise a web service.
Natural Language Processing (NLP) of raw text to extract sentiment, keyword pairs and relevant information.
Using Matrix Factorization to predict the responses users would have, based on existing information.
Using hierarchical clustering to identify cancer sub-populations with altered response to chemotherapy.
Predicting quality changes in a manufacturing process, utilising local regression (LOESS regression).
Determining drug response and binding affinity of complex molecules using non-linear regression.
Utilising non-linear regression to determine drug response and binding affinity of complex molecules.

Created a multi-phase financial model capable of predicting the monthly pricings, initial debt, profit and growth rate of commercial projects, which could be altered depending upon payment terms for a project.
Optimising experimental time and costs through utilising design of experiment (DoE) approaches.
Using various AB testing techniques to compare various cohorts to control groups.
Quantitating population differentials using a myriad of statistical tests, such as ROC curves and AUC.
Performed network and relationship analysis of users and the strength of their interactions (R and Neo4J)

Utilising SQL for querying databases and integrating MySQL within R and Python for parameterised queries.
Creating and deploying SQL databases (both locally and on cloud) for storage of datasets, using Docker.
Making interactive analytics dashboards for stakeholders (Power BI, R shiny, Dash and Tableau)
Deploying machine learning within an interactive dashboard for users to make predictions (Dash & Power BI).
Proficient in cleaning, filtering and mining datasets, web scraping and interacting with APIs.
Explored, determined and normalised variations within a service to produce more efficient costing models.
Developed a Pricing Index to show pricing trends over time, using regression to normalise high variance items.

Migrating Jupyter notebooks to automated CI/CD data pipelines in production, complete with data preparation, model training and performance reporting.
Developing ML APIs with multiple endpoints, designed to serve model predictions for different purposes.
Building simple data lakes on AWS and using AWS Glue crawlers to query multiple CSV files as a SQL database.
Re-architecting an on-prem legacy data warehouse for modern infrastructure (data warehouse/data mart and data lake solutions)
Scripting using Python (PyCharm and Jupyter Notebooks), R (including R Markdown and Shiny), SQL and Bash.
Experience using: Git, Docker, AWS Services (Inc. Sagemaker and Athena), DVC, Neo4J, SPSS, Flask

Possess excellent time management skills with a proven track record in project management.
Extensive remote working experience as part of multinational teams or with no geographical location
Adept at working well individually and as part of larger teams to deliver projects to required deadlines.
Assisting agile projects allowing teams to use data-driven approaches to quickly pivot projects to useful areas.
Capable managing the logistics, budget and operations of complex projects (e.g. clinical research trials).
Experience leading international collaborations with large research groups.
Proficient delivering training courses to colleagues and external visitors.
Extensive experience with Microsoft Office, with advanced knowledge of Excel.

Possess outstanding written and communication skills; disseminating technical information to board members, ensuring conclusions are comprehensible to technical and non-technical personnel.
Presenting and report writing in both industrial and academic settings and publishing in scientific journals.
Running workshops and presenting talks at meetups.
Moderating and debating topics at meetups.