Mark is available for hire
Hire MarkMark Farragher
Verified Expert in Engineering
Statistical Methods Developer
Location
Cambridge, United Kingdom
Toptal Member Since
May 13, 2020
Mark is a highly analytical data scientist and open-source developer who most recently worked in a startup environment. He trained as an economist and specializes in statistical modeling, causal inference, and experimentation. He has a breadth of experience, having worked in contracting and employment on data projects for public, private, and third-sector clients. He is an excellent communicator who often gives talks at conferences and writes blog posts on data topics.
Portfolio
Genomics England
Python, Tableau, Agile, Product Roadmaps, Data Analytics
Boutique Health Consultancy (Contract)
Bayesian Statistics, Causal Inference, Data Analysis, Statistical Methods...
Triptease
Bayesian Statistics, Causal Inference, Data Analysis, Google BigQuery...
Experience
Availability
Part-time
Preferred Environment
Google Cloud Platform (GCP), NumPy, Pandas, Linux, MacOS, Windows, STATA, Tableau, Looker, Git, BigQuery, SQL, Python
The most amazing...
...personal project I've worked on is an open-source econometrics library for Python called Appelpy. It reached over 120 stargazers on GitHub.
Work Experience
Performance Analytics Officer
2021 - 2021
Genomics England
- Drove the development of new data products consumed across Genomics England internally and externally, including analytics used by senior stakeholders in government.
- Established analytics capability in a Center of Excellence team to enable self-serve analytics in late 2021 and shaped the analytics roadmap.
- Developed best practices in analytics to support user needs and set the technical end-to-end ELT pipeline.
Technologies: Python, Tableau, Agile, Product Roadmaps, Data Analytics
Data Scientist
2020 - 2020
Boutique Health Consultancy (Contract)
- Developed scalable analytics tools on a healthcare data project for a boutique healthcare consultancy's analytics team. Led software engineering and ETL-intensive tasks.
- Moved Python code away from notebooks, with some refactoring, into a more robust system. Introduced best practices in software engineering, e.g., logging, unit testing, or modularization of code.
- Developed ETL pipelines with Parquet files and analytics tools to reduce the team's time spent on ad-hoc requests, with a long-term view of making the analytics more self-serve for the client.
- Automated the generation and sending of data outputs, e.g., with Microsoft Teams Flows or BAT scheduling.
- Automated advanced Excel outputs, with a mix of Python libraries such as Xlwings or Openpyxl.
Technologies: Bayesian Statistics, Causal Inference, Data Analysis, Statistical Methods, Windows, Microsoft Excel, Pandas, Scrum, Agile, Python, Machine Learning, Tableau, Test-driven Development (TDD), Excel VBA, Parquet, Consulting, Data Analytics
Data Scientist
2018 - 2020
Triptease
- Developed logic for systematically managing hotels' online presence on metasearch advertising channels, harnessing their unique characteristics and multiple data sources. Helped to launch the MVP and iterate logic once we had more customers.
- Built dashboards and tooling to help our cross-functional squad monitor the health of the metasearch product, e.g., anomaly detection system, integration health, or model and product performance.
- Developed internal Python libraries to analyze our data more robustly and systematically. Automated dozens of my common analytics tasks and modeling workflow.
- Delivered a talk at the PyData London 2019 conference on the applications of causal inference to hotel websites.
- Undertook research that influenced the sales process like new guard rails, budget optimization, and models tailored to hoteliers' different objectives, like whether to optimize acquisition or the return on ad spend.
- Upskilled and onboarded new colleagues, such as data analysts, on parts of our tech stack.
- Undertook the largest A/B test of on-site messaging across thousands of hotel websites. Wrote the white paper on the test results and discussed the test in a webinar with customers.
Technologies: Bayesian Statistics, Causal Inference, Data Analysis, Google BigQuery, Statistical Methods, Microsoft Excel, Pandas, Git, Agile, Machine Learning, SaaS, Google Cloud Platform (GCP), BigQuery, SQL, Looker, Python, Scikit-learn, Product Analytics, Data Analytics
Data Analyst
2018 - 2018
Triptease
- Ran multiple A/B tests to demonstrate the value of Triptease's products to the largest hotel groups. The rigorous process and outputs contributed to reducing client churn in Q1 2018.
- Increased the efficiency and effectiveness of the original A/B testing process via, e.g., reporting templates, automation of tasks, or dashboard and tool development.
- Undertook analysis and research that led to developing new product and platform features.
- Analyzed conversational data with NLP to refine the front desk chatbot product, which led to higher accuracy.
- Assisted in hiring new data scientists in H2 2018 and eventually moved into a data science role in a new squad.
Technologies: Bayesian Statistics, Causal Inference, Data Analysis, Google BigQuery, Statistical Methods, Microsoft Excel, Pandas, Google Cloud Platform (GCP), Git, Agile, Machine Learning, SaaS, Python, BigQuery, SQL, Looker, A/B Testing, Product Analytics, Data Analytics
Analyst/Consultant
2017 - 2017
Self-employed
- Contracted at Triptease as a data analyst for one month before moving into a permanent role.
- Developed strategy and evidence bases for supporting the startup of new universities internationally for consultancy for Susan Jackson Associates.
- Undertook quantitative and qualitative analysis on international higher education policy.
Technologies: Data Analysis, Statistical Methods, Economics, Windows, Microsoft Excel, BigQuery, SQL, Looker, Consulting
Consultant
2015 - 2017
Public and Corporate Economic Consultants (PACEC)
- Authored a publication on England's knowledge exchange (KE) policy and developed a database tool for monitoring universities' KE strategies as part of one of our largest consultancy projects (£100,000+). I wrote the proposal.
- Wrote the baseline evaluation report for the Newton Fund, a £735 million fund to develop UK research partnerships in 15 countries. Developed the quantitative analysis methodology and became an SME on international research partnerships.
- Authored dozens of pieces of research on economic policy and higher education policy for clients at different levels of government, e.g., UK central government, local authorities, local enterprise partnerships, public-private consortia, etc.
- Introduced and applied new technology to our analytics, like the use of Tableau.
Technologies: Data Analysis, Statistical Methods, Economics, Windows, STATA, Tableau, Microsoft Excel, Consulting
Experience
The State of the English University Knowledge Exchange Landscape
https://dera.ioe.ac.uk/29698/The client is the Higher Education Funding Council for England (HEFCE).
I was one of the main authors of this publication, and the wider project was one of the largest revenue contracts that the business had secured. The web link above has the full report, so that may be useful for context. Findings from previous PACEC reports on knowledge exchange have been used in the HE sector at workshops and conferences, especially by policymakers, so it is likely to be the same for this report over the next few years.
I was one of the main authors of this publication, and the wider project was one of the largest revenue contracts that the business had secured. The web link above has the full report, so that may be useful for context. Findings from previous PACEC reports on knowledge exchange have been used in the HE sector at workshops and conferences, especially by policymakers, so it is likely to be the same for this report over the next few years.
Appelpy (Applied Econometrics Library for Python)
https://github.com/mfarragher/appelpyI am the developer of the Applied Econometrics Library for Python (Appelpy). It seeks to bridge the gap between the software options with a simple syntax, such as Stata, and other powerful options that use Python's object-oriented programming as part of data modeling workflows.
It was a personal project I worked on over some weekends and evenings. I marketed the project, and it became one of the most starred projects on regression modeling on GitHub.
It was a personal project I worked on over some weekends and evenings. I marketed the project, and it became one of the most starred projects on regression modeling on GitHub.
Newton Fund Baseline Evaluation
The client is The UK's BEIS and DFID government departments.
I undertook quantitative analysis and desk research to develop the baseline evaluation for the Newton Fund by drawing upon international and national literature and datasets encompassing innovation policy. I authored 15 country-level reports assessing the partner countries' innovation capacity and a high-level report.
I undertook quantitative analysis and desk research to develop the baseline evaluation for the Newton Fund by drawing upon international and national literature and datasets encompassing innovation policy. I authored 15 country-level reports assessing the partner countries' innovation capacity and a high-level report.
Skills
Languages
Python, SQL, R, Excel VBA
Libraries/APIs
Pandas, Scikit-learn, NumPy
Tools
Looker, Tableau, Git, STATA, BigQuery, Microsoft Excel
Paradigms
Agile, Scrum, Test-driven Development (TDD)
Other
Google BigQuery, Consulting, Economics, Machine Learning, Statistical Methods, Causal Inference, SaaS, Data Analysis, A/B Testing, Product Analytics, Data Analytics, Bayesian Statistics, Parquet, Biostatistics, Research, Genetics, Product Roadmaps
Platforms
Google Cloud Platform (GCP), Windows, MacOS, Linux
Industry Expertise
Project Management
Education
2021 - 2022
Master's Degree in Population Health Sciences
University of Cambridge - Cambridge, UK
2012 - 2015
Bachelor of Science Degree in Economics
London School of Economics & Political Science - London, United Kingdom
Certifications
OCTOBER 2020 - PRESENT
Chartered Statistician
Royal Statistical Society
Collaboration That Works
How to Work with Toptal
Toptal matches you directly with global industry experts from our network in hours—not weeks or months.
1
Share your needs
Discuss your requirements and refine your scope in a call with a Toptal domain expert.
2
Choose your talent
Get a short list of expertly matched talent within 24 hours to review, interview, and choose from.
3
Start your risk-free talent trial
Work with your chosen talent on a trial basis for up to two weeks. Pay only if you decide to hire them.
Top talent is in high demand.
Start hiring