Unveiling the Impact of Socioeconomic and Demographic Factors on Graduate Salaries: A Machine Learning Explanatory Analytical Approach Using Higher Education Statistical Agency Data DOI Creative Commons

Bassey Henshaw,

Bhupesh Kumar Mishra, Will Sayers

et al.

Analytics, Journal Year: 2025, Volume and Issue: 4(1), P. 10 - 10

Published: March 11, 2025

Graduate salaries are a significant concern for graduates, employers, and policymakers, as various factors influence them. This study investigates determinants of graduate in the UK, utilising survey data from HESA (Higher Education Statistical Agency) integrating advanced machine learning (ML) explanatory techniques with statistical analytical methodologies. By employing multi-stage analyses alongside models such decision trees, random forests explainability SHAP stands (Shapley Additive exPanations), this 21 socioeconomic demographic variables on salary outcomes. Key variables, including institutional reputation, age at graduation, classification, job qualification requirements, domicile, emerged critical determinants, reputation proving most significant. Among ML methods, tree achieved standout highest accuracy through rigorous optimisation techniques, oversampling undersampling. highlighted top 12 influential providing actionable insights into interplay between individual systemic factors. Furthermore, analysis using ANOVA (Analysis Variance) validated significance these revealing intricate interactions that shape dynamics. Additionally, domain experts’ opinions also analysed to authenticate findings. research makes unique contribution by combining qualitative contextual quantitative methodologies, views addressing gaps existing identification predicting components. findings inform policy educational interventions reduce wage inequalities promote equitable career opportunities. Despite limitations, UK-specific dataset focus lays robust foundation future predictive modelling

Language: Английский

Unveiling the Impact of Socioeconomic and Demographic Factors on Graduate Salaries: A Machine Learning Explanatory Analytical Approach Using Higher Education Statistical Agency Data DOI Creative Commons

Bassey Henshaw,

Bhupesh Kumar Mishra, Will Sayers

et al.

Analytics, Journal Year: 2025, Volume and Issue: 4(1), P. 10 - 10

Published: March 11, 2025

Graduate salaries are a significant concern for graduates, employers, and policymakers, as various factors influence them. This study investigates determinants of graduate in the UK, utilising survey data from HESA (Higher Education Statistical Agency) integrating advanced machine learning (ML) explanatory techniques with statistical analytical methodologies. By employing multi-stage analyses alongside models such decision trees, random forests explainability SHAP stands (Shapley Additive exPanations), this 21 socioeconomic demographic variables on salary outcomes. Key variables, including institutional reputation, age at graduation, classification, job qualification requirements, domicile, emerged critical determinants, reputation proving most significant. Among ML methods, tree achieved standout highest accuracy through rigorous optimisation techniques, oversampling undersampling. highlighted top 12 influential providing actionable insights into interplay between individual systemic factors. Furthermore, analysis using ANOVA (Analysis Variance) validated significance these revealing intricate interactions that shape dynamics. Additionally, domain experts’ opinions also analysed to authenticate findings. research makes unique contribution by combining qualitative contextual quantitative methodologies, views addressing gaps existing identification predicting components. findings inform policy educational interventions reduce wage inequalities promote equitable career opportunities. Despite limitations, UK-specific dataset focus lays robust foundation future predictive modelling

Language: Английский

Citations

0