Chanuki Illushka Seresinhe
Alan Turing Institute/Popsa
Quantifying the Connection Between Scenic Beauty and Our Wellbeing
Intuitively, we often seek out beautiful scenery when we want a respite from our busy lives, but do such settings actually help to boost our wellbeing? While architects and policymakers have puzzled over this question for centuries, quantitative analyses have been held back by a lack of data. Now, vast volumes of online data alongside developments in deep learning are opening up new opportunities to analyse the beauty of our environment. In this talk, I will explain how I used over 1.5 million ratings of over 200,000 images covering Great Britain from a website called Scenic-Or-Not to find answers to this age-old question.
Chanuki Illushka Seresinhe is a data science researcher at the Alan Turing Institute and the Lead Data Scientist at Popsa (using AI to automatically curate photo content into beautifully designed physical products). She formerly worked as a Senior Data Scientist at Channel 4.
Quantitative Engineer & Data Scientist
Working with an industry-leading manufacturer, the goal was to improve the uptime of products in use. Using more than a million repair records across 15 different datasets for three different products, we developed several solutions to identify signals that an issue might be brewing. This enabled us to solve the underlying cause well before it escalated to a problem that required widespread repairs (which would lead to downtime). During this talk Alison will share details on the use case and the solutions developed that helped identify the largest and fastest growing potential issues within product lines.
Maren is an experienced Data Scientist with Maths background and PhD in Probability.
Senior Data Scientist
Royal Mail’s Estimated Delivery Window – Another Successful Data Science Story
One of Royal Mail’s latest initiatives to improve customer experience and convenience was launched in April this year. Customers are now receiving information about their parcel deliveries a day in advance and also get shorter estimated delivery windows, down to a time frame of two hours. I will present some of the data science behind the project, as well as how we managed to make this project another data science success story for Royal Mail.
Following an Academic career in Evolutionary Genetics and Bioinformatics (University of Zurich - PhD; University of Bristol - Senior research scientist), I have switched to professional Data Science.
Since 2016, I have been working on several projects for Royal Mail, supporting the business in making smarter, data-driven decisions. I have supported or lead several ambitious predictive analytics projects for Royal Mail, such as:
(I) Estimated parcel delivery times: Lead a team of 7 (data scientists and data engineers) to successfully implement the technical part for one of Royal Mails capital projects regarding predicting delivery windows. Resposible for all technical data-sciencerelated aspects of the project, interacting with multiple teams within the business and communicating with major stakeholders. (Talk)
(II) Developed and implemented Royal Mails traffic forcast. Finding an end-to-end solution that is running live for two years, supporting Royal Mail's daily resource planning.
(III) Lead, developed and implemented a predictive project with a savings potential in the millions for Royal Mail. Responsible for end-to-end solution, including deployment via webapp and usage evaluation.