Andrew Burnie, Data Scientist and Machine Learning Developer in London, United Kingdom
Andrew Burnie

Data Scientist and Machine Learning Developer in London, United Kingdom

Member since May 27, 2020
Andrew is an expert in extracting commercially valuable insights from data, with a specialty in text analysis. He has experience in the retail, insurance, and other financial sectors. Andrew earned a PhD in social media analysis, funded by the UK's national institute for data science and AI, and a master's degree in management and economics from the University of Cambridge. He enjoys using machine learning and statistics to help companies get the most out of their data.
Andrew is now available for hire

Portfolio

Experience

Location

London, United Kingdom

Availability

Part-time

Preferred Environment

Windows, Linux, Python

The most amazing...

...thing I've developed was a groundbreaking NLP algorithm to extract from social media the likeliest causes of major changes in the price of Bitcoin and Ethereum.

Employment

  • Doctoral Student (PhD Completed)

    2017 - 2020
    The Alan Turing Institute
    • Earned a PhD at The Alan Turing Institute, the UK's national institute for data science and artificial intelligence.
    • Created a new, nonparametric NLP algorithm (DDPWI) to extract from social media text the words associated with declining Bitcoin prices. Published in Royal Society Open Science.
    • Applied neural networks in a new Word2vec-based topic modeling algorithm to detect which topics discussed on social media were associated with phasic shifts in Bitcoin prices. Presented at ACM SIGIR 2019.
    • Showed the one-off effect of regulatory bans on Bitcoin and the recurring effects of rival innovations on the Ether price.
    • Demonstrated how nonparametric correlation networks could be applied to explore the associations between the prices of different financial assets. This work has been cited 15 times.
    Technologies: Predictive Modeling, Statistics, Statistical Analysis, Pandas, NumPy, Gensim, SpaCy, Fintech, SciPy, Scikit-learn, Text Analytics, Causal Inference, Natural Language Processing (NLP), Topic Modeling, Neural Networks, Time Series, Windows, Linux, Keras, Python, NLTK, Social Media APIs, Cryptocurrency, TensorFlow, Data Science, Deep Learning, Web Scraping, Artificial Intelligence (AI), Machine Learning
  • Head of Data Science

    2017 - 2017
    ERS (A Lloyd's Syndicate and the UK's Largest Specialist Motor Insurer)
    • Set up the data science team at the UK's largest specialist motor insurer with accountability at the board level.
    • Enabled the fine-tuning of insurance premiums based on customized, specialized, nonparametric technologies rather than the standard linear models offered by Willis Towers Watson software.
    • Pioneered the application of Random Forests, XGBoost, and GLM along with approaches to feature selection that included Random Forest techniques, including Boruta and statistical testing, to generate prediction models.
    Technologies: Regression, XGBoost, Predictive Modeling, Statistics, Statistical Analysis, Pandas, NumPy, Insurance, Tidyverse, Fintech, SciPy, Scikit-learn, Random Forests, Linear Regression, Windows, Python, R, Data Science, Big Data, Artificial Intelligence (AI), Machine Learning, Boruta, Generalized Linear Model (GLM)
  • Data Scientist

    2016 - 2017
    Hitachi Consulting
    • Introduced regression approaches (linear, lasso, ridge, elastic net, and logistic) to feature selection to improve the customer experience by transforming data into actionable insights.
    • Identified potential root causes of sales revenue in a marketing project using machine learning feature selection approaches.
    • Developed data science project templates used in machine learning and customer analytics projects.
    Technologies: Customer Analytics, Regression, XGBoost, Predictive Modeling, Statistics, Statistical Analysis, Pandas, NumPy, Marketing, Tidyverse, SciPy, Scikit-learn, Consulting, Text Analytics, Natural Language Processing (NLP), Random Forests, Time Series, Linear Regression, Windows, SQL, Python, R, Data Science, Web Scraping, Big Data, Artificial Intelligence (AI), Machine Learning, Azure
  • Data Scientist

    2016 - 2016
    Model Citizens Ltd
    • Managed customer data analysis identifying opportunities and threats for a retailer.
    • Performed a data audit and analysis for an entertainment company.
    • Pioneered the use of clustering algorithms to classify customers into different types.
    Technologies: Customer Analytics, Regression, XGBoost, Predictive Modeling, Statistics, Statistical Analysis, Pandas, NumPy, Marketing, Tidyverse, SciPy, Scikit-learn, Consulting, Random Forests, Windows, SQL, Python, R, Data Science, Web Scraping, Big Data, Artificial Intelligence (AI), Machine Learning
  • Postgraduate Student

    2015 - 2016
    Grenoble École de Management
    • Analyzed the financial and nonfinancial drivers of internet company valuations.
    • Determined that financial statements could explain only about one-third of the variation in the price-to-sales ratio.
    • Published in the journal, Bankers, Markets & Investors.
    Technologies: Plotly, Regression, Statistics, Statistical Analysis, Time Series, Linear Regression, R, Data Science
  • Internship

    2014 - 2014
    DN Capital
    • Advised DN Capital on the threats and opportunities facing the European venture capital market.
    • Provided guidance to DN Capital on how best to position itself to mitigate threats and take advantage of opportunities.
    • Published a report that was awarded a First Class Degree by the University of Cambridge.
    Technologies: Web Scraping, CB Insights, Pitch Books

Experience

  • Causal Inference Framework for Extracting Insights from Social Media Text

    I constructed a causal inference framework, based on healthcare epidemiology principles, that identified the likeliest causes of major changes in the price of Bitcoin and Ethereum. This involved using Python, NLTK, and Gensim to code a pipeline that processed social media text and then extracted topics of interest. This was published in Frontiers in Blockchain.

Skills

  • Languages

    Python, JavaScript, R, SQL, Julia, Java
  • Libraries/APIs

    Social Media APIs, SpaCy, NLTK, Scikit-learn, SciPy, TensorFlow, NumPy, Pandas, REST APIs, Keras, Tidyverse, XGBoost
  • Tools

    Gensim, Plotly, IBM Watson
  • Paradigms

    Data Science
  • Storage

    JSON
  • Other

    Machine Learning, Neural Networks, Topic Modeling, Artificial Intelligence (AI), Natural Language Processing (NLP), Causal Inference, Asset Valuation, Cryptocurrency, Linear Regression, Random Forests, Statistical Analysis, Big Data, Text Analytics, Web Scraping, Fintech, Consulting, Time Series, Deep Learning, Algorithms, Sentiment Analysis, NLU, Chatbots, Microsoft Azure, Deep Neural Networks, APIs, Conversational AI, Microsoft Azure Machine Learning (ML), Cloud Platforms, Document Processing, OCR, Custom BERT, Full-stack, Web App UI, Statistics, Predictive Modeling, Generalized Linear Model (GLM), Boruta, Regression, Customer Analytics, Pitch Books, Chatbot Conversation Design, IBM Watson Assistant
  • Frameworks

    Selenium, Azure Bot Framework
  • Platforms

    Azure, Linux, Windows, CB Insights
  • Industry Expertise

    Marketing, Insurance

Education

  • PhD in Computer Science
    2017 - 2020
    University College London (UCL) - London, England, United Kingdom
  • Master of Arts Degree in Management Studies and Economics
    2018 - 2018
    University of Cambridge - Cambridge, England, United Kingdom
  • Master of Science Degree in Finance
    2014 - 2016
    Grenoble École de Management - London, England, United Kingdom
  • Bachelor of Arts Degree in Management Studies and Economics
    2011 - 2014
    University of Cambridge - Cambridge, England, United Kingdom

Certifications

  • Rasa Certified Chatbot Developer
    JANUARY 2021 - PRESENT
    Rasa
  • HackerRank Gold for Java
    NOVEMBER 2020 - PRESENT
    HackerRank
  • HackerRank Gold for Python
    MAY 2020 - PRESENT
    HackerRank
  • Sequence Models
    FEBRUARY 2018 - PRESENT
    deeplearning.ai | via Coursera
  • Neural Networks and Deep Learning
    FEBRUARY 2018 - PRESENT
    deeplearning.ai | via Coursera
  • Machine Learning Specialization
    FEBRUARY 2017 - PRESENT
    University of Washington | via Coursera

To view more profiles

Join Toptal
Share it with others