NORMA eResearch @NCI Library

Forecasting Ukrainian refugee employment in Ireland's Accommodation& Food Service sector Using Random Forest, Gradient Boosting, and Neural Network models

Bhosale, Dikshant Manohar (2024) Forecasting Ukrainian refugee employment in Ireland's Accommodation& Food Service sector Using Random Forest, Gradient Boosting, and Neural Network models. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
Preview
PDF (Master of Science)
Download (1MB) | Preview
[thumbnail of Configuration Manual]
Preview
PDF (Configuration Manual)
Download (897kB) | Preview

Abstract

When conflicts escalate into wars, a large scale of displacement occurs. Urging other nations to extend support to refugees. Then critical question arises like How can refugees successfully integrate into their host countries? This study delves into the employment prospects for Ukrainian refugees in Ireland, using machine learning techniques like Random Forest, Gradient Boosting and Neural Network to understand and predict employment levels among Ukrainian refugees in Ireland’s Accommodation and Food Service sector during 2022 to 2024. Comparing Random Forest, Gradient Boosting, and Neural Network models, the research evaluates their predictive accuracy for refugee employment levels. Gradient Boosting emerged as the optimal model, slightly outperforming Random Forest with an R-squared of 0.9867 (98.67% accuracy) and RMSE of 393.2624, while significantly outperforming Neural Network (R-squared: 0.6673). Despite Random Forest showing better MAE (283.0300 compared to Gradient Boosting's 332.7844), Gradient Boosting's superior learning curve convergence and generalization capabilities established it as marginally more reliable. Through Gradient Boosting's feature importance analysis, the study identified Manufacturing (Importance Score=0.204069), Information and Communication (Importance Score=0.186781), and Education (Importance Score=0.123934) as the most influential sectors affecting refugee employment in the Accommodation and Food Service sector. These quantified sector influences provide specific insights for aligning refugee employment support with sectors showing strong predictive relationships to the Accommodation and Food Service sector.

Item Type: Thesis (Masters)
Supervisors:
Name
Email
Qayum, Abdul
UNSPECIFIED
Uncontrolled Keywords: R-Squared; Mean Absolute Error (MAE); Root Mean Squared Error (RMSE); Random Forest; Gradient Boosting; Neural Network
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
H Social Sciences > HD Industries. Land use. Labor > Specific Industries > Hospitality Industry > Food service
Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
H Social Sciences > HV Social pathology. Social and public welfare > Asylum Seekers and Refugees
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Ciara O'Brien
Date Deposited: 31 Jul 2025 13:52
Last Modified: 31 Jul 2025 13:52
URI: https://norma.ncirl.ie/id/eprint/8389

Actions (login required)

View Item View Item