Data Science at LIDA - Not in Employment, Education or Training "NEET"

The 4th instalment of our data science mini-series showcasing current research projects here at the Leeds Institute for Data Analytics (LIDA). This weeks features 10 minute lightning talks from three data scientists on using data analytics to inform the prevention of Young People Not in Employment, Education or Training (NEET) with Q&A.

TALK 1 - Intro & Congenital Anomalies as a Risk Factor
Folasayo Ogundipe

Summary - Our project aims to investigate the impact of Congenital Anomalies (CAs) on the likelihood of individuals becoming Not in Employment, Education or Training (NEET). With over 130,000 children born with CAs in Europe annually, we seek to understand the lifelong challenges these individuals face and how it may influence their educational and employment outcomes. Supported by Connected Bradford (CB) and the ESRC Vulnerability & Policing Futures Research Centre, we're crafting our cohort based on specific criteria to explore the complex relationship between CAs, academic attainment and NEET status. Methods like logistic regression and structural equation modelling will be used in this project.

Biography - With nearly a decade in the pharmaceutical industry, I transitioned to data science two years ago. Motivated by the role of data, I went on to obtain an MSc in AI and Data Science. My diverse background in biomedical sciences and industry knowledge informs my multidisciplinary approach to data science. Beyond data, I find joy in football and video games.

TALK 2 - Exploring Early Educational Assessments
Ramaa Thirunarayanan

Summary - Extended periods of NEET (Not in Education, Employment, or Training) status have serious implications, affecting future employment, income, and overall well-being. Identifying early indicators for those at risk of becoming NEET is crucial for resource allocation. Previous research in Bradford suggests that a measure of school readiness, the Early Years Foundation Stage Profile, predicts later academic success, the need for Special Educational Needs support, and later NEET status. Using data from Connected Bradford, this project aims to examine whether specific components of this school readiness measure differentially predict later outcomes through regression analyses and structural equation modelling.

Biography - In parallel to my IT Project Management career of 18 years, I have also taken on the roles of founder and director for three international schools in Tokyo. This unique experience has afforded me a distinctive perspective on the intersections of education, business operations, and data management. The combination of these dual roles has equipped me with a comprehensive understanding of the pivotal role that data plays in shaping strategies and outcomes across diverse sectors.

TALK 3 - School absences as a risk factor
Emily Connell

Summary - How might school absences today shape a young person's path tomorrow? Amid the lingering impact of the COVID-19 pandemic, heightened school absence rates have increased concerns for students when they reach school leaving age. Utilising the extensive Connected Bradford database in collaboration of the ESRC Vulnerability & Policing Futures Research Centre, we explore if absenteeism is associated with the risk of later becoming NEET (Not in Education Employment or Training). Bradford has high concentrations of poor social mobility, educational attainment and health. Unveiling the role of NEET risk factors can help inform essential interventions to enhance social outcomes in Bradford.

Biography - Completing my Ph.D. in Medicine introduced me to the world of data science, seeing first-hand how big data increases public good, by developing a new predictive model of Alzheimer's disease. This ignited my interest to continue in the field, and I’m eager to expand upon this during my time at LIDA.