A Data Science Approach to Predicting Pupils at Risk of School Exclusion in Walsall
PHE ePoster Library. Heath C. Sep 12, 2019; 274499; 59
Dr. Claire Heath
Dr. Claire Heath
Login now to access Regular content available to all registered users.

You may also access this content "anytime, anywhere" with the Free MULTILEARNING App for iOS and Android
Abstract
Rate & Comment (0)
Abstract Introduction
School exclusion is an increasingly important public health issue. Excluded children are more likely to experience poor educational outcomes, unemployment, criminal justice interventions and develop severe mental health problems. In Walsall, children as young as 5 years old have been excluded from school. Identification of the local factors that increase risk of exclusion would enable early and targeted interventions to potentially break the cycle of disadvantage. Methods: We linked 3 datasets (school census, school exclusions logs and social care records) from the academic years 2015/16 - 2017/18 inclusive, using a sequence of methods. Initially, school census and exclusions records were linked using unique pupil number, which were then matched to social care records using a concatenation of surname, first name and date of birth. This rendered a linked dataset of 62,536 Walsall children. Data was interrogated using PowerBI and the CRISP-DM methodology.
Results
244 pupils were permanently excluded and 2136 had fixed term exclusions. In the non-excluded group, 50.5% were male, median age is 10 years, 17.2% are known to social care, 17.2% benefit from free school meals (FSM), 12.3% have a special educational need/disability (SEND). In the excluded group, 76.9% are boys, median age is 14 years, 44.5% are known to social care, 39% benefit from FSM, 35% have a SEND need.
Conclusions
Data linkage and mining has enabled identification of significant differences in demographic, socioeconomic and educational indicators in children excluded from school. Work is ongoing to develop a robust predictive model to minimise exclusions in Walsall. External funding details
    This eLearning portal is powered by:
    This eLearning portal is powered by MULTIEPORTAL
Anonymous User Privacy Preferences

Strictly Necessary Cookies (Always Active)

MULTILEARNING platforms and tools hereinafter referred as “MLG SOFTWARE” are provided to you as pure educational platforms/services requiring cookies to operate. In the case of the MLG SOFTWARE, cookies are essential for the Platform to function properly for the provision of education. If these cookies are disabled, a large subset of the functionality provided by the Platform will either be unavailable or cease to work as expected. The MLG SOFTWARE do not capture non-essential activities such as menu items and listings you click on or pages viewed.


Performance Cookies

Performance cookies are used to analyse how visitors use a website in order to provide a better user experience.


Save Settings