As long as I can remember myself, I have always enjoyed looking for patterns in data. However, I only started seriously considering a career in technology and data science while studying Econometrics during the second year of my undergraduate degree at the University of Cambridge. This was my first introduction to the machine learning techniques such as regression models, as well as to simple programming in Stata, and I thoroughly enjoyed it. In my final year I produced a dissertation analysing labour market data, and this experience further convinced me that I should go for a Masters in a STEM field and then pursue a career in tech.

After graduation, I spent the next year working in Consulting at KPMG during the day, and then improving my programming skills and writing applications for Masters during evenings and weekends. I have chosen the Spatio-temporal Analytics and Big Data Mining program at UCL Civil, Environmental and Geomatic Engineering department, over traditional Data Science ones was because I was tired of learning dry theory, and was eager to apply my skills to analysing tangible data from the physical world. I thoroughly enjoyed my degree course, gaining knowledge of a variety of machine learning techniques, and the technologies to apply them to problems involving spatio-temporal data.

During the program, I became interested in a particular application of spatial data science: transport. Growing up in a city with multimillion population, I have seen the scale of transport systems they require and the impact they have on every person’s life. I completed my Master’s thesis on topic of using computer vision technologies to create a program for automatic mapping of cycling infrastructure from images and videos. I received a Distinction overall in my Masters degree, and I was ranked 2nd on my program.

Immediately after, I joined Arup in my first Data Scientist role, within the City Modelling Lab team – a team focused on using Agent-Based Modelling for large scale simulation of transport systems, with the aim of helping transport authorities in policy making. There, I saw how technology is pushing the boundaries of what’s possible: using cloud technologies made it possible for us to access huge amounts of computing power without which running such huge simulations would be impossible. I also enjoyed being able to work on national level projects, using technology to solve unique and complex problems that affect lives of millions.

At the end of 2022, I moved to UBS to join the new AI, Data and Analytics (ADA) team, aimed at accelerating the adoption of technology in the bank. Since joining, I have had a chance to build a machine learning model for identifying anomalies in ESG CO2 data received from vendors, with the goal of using only the highest quality data for calculating CO2 emissions to ensure UBS is progressing towards its sustainability goals.

Outside of my day job, I enjoy meeting other data science and tech professionals, as well as providing mentorship to students looking to get into the field.