Philip Spanoudes, MSc Data Science

‌Current MSc Data Science student Philip Spanoudes, from Cyprus, will spend two weeks in San Fransisco this summer, working for Framed Data Inc.

How and why did you choose to work with the business?

"I am working for the business as part of my MSc Data Science. I’m looking to develop my understanding of deep learning, to deliver real innovation to Framed Data, and to enhance both my skills and CV with a great project."

What problem did the organisation face? What did they ask you to do to help them?

"I will be working with Framed Data Inc., investigating the application of deep learning techniques to their analysis of churn prediction. Churn prediction allows a company to determine which of their customers are likely to leave and take steps to prevent this; my project is aimed at finding efficient and effective ways of enhancing this process. I’ll spend most of my time in Lancaster, but will be going to work with Framed Data in San Francisco for a couple of weeks during the summer. I’m really excited to have the opportunity to work with cutting-edge data science in Silicon Valley.

"Framed Data have built an automated machine learning platform that takes in user data and predicts when users are going to churn from an application. It does this by engineering a feature space out of past user behaviour, and then running a list of selection heuristics to pare down the space. Churn prediction allows a company to determine which of their customers are likely to leave and take steps to prevent this."

What skills did you use and develop working with the company? 

"I am gaining experience in programming language Python; machine learning; feature selection; engineering of high-dimensional datasets, statistics, and data visualization, as well as developing my skills using git software and Github hosting service."

What will you do for the businesses?

"I am working with the company’s CEO and data scientists to improve feature selection and engineering heuristics for the company’s predictive analytics pipeline. We are working together on optimizing model accuracy against a subset of sample data (around 10GB/day). The models that we are creating for this subset will be run against Framed Data’s production data (around 600GB/day) to evaluate this accuracy. I will try to find efficient and effective ways of both enhancing Framed Data’s churn prediction process and investigating the application of deep learning techniques to their analysis of churn prediction."

Will you get paid for your work? 

"The company will provide a bursary direct to me in the region of £1,000 to £3,000."

Would you recommend your course to prospective students? If so, why?

"I’ve enjoyed the wide range of topics that are available on the course, and that students are able to choose the areas on which they want to focus. The availability of funded industry placements with prestigious companies is also great."