A multivariate analysis using machine learning of the impact of education-based factors on employment income for youth
Bibliographic record
Abstract
The transition from education to employment is a critical stage for all youth. However, youth employment outcomes vary widely due to complex and interconnected socioeconomic factors, prompting efforts to optimize these outcomes. Although prior studies have examined factors’ individual influences, few have addressed their combined effects. Therefore, this study investigated how educational attainment and work experience during education collectively influence post-education median employment income for Canadian youth aged 15–24, using median income as a measure of equality in youth employment outcomes. Using datasets from Statistics Canada, a neural network model was applied to explore the independent and combined impacts of these factors on median income. By analyzing historical data from the past 20 years, the study aimed to identify trends and simulate potential policy outcomes to guide targeted interventions that could improve youth employment outcomes. The relationships between education, work experience, and median income were found to vary across different provinces and time periods. Using machine learning techniques, the research highlighted the potential of AI-driven approaches to predict and simulate policy effects, offering a valuable tool for economic and educational development. This study also evaluated the model to identify limitations that may have impacted the model’s accuracy, including noise, gaps in provincial data, and challenges in applying machine learning to economic data. We explored potential improvements to these limitations and identified areas for further investigation, such as analysis of localized trends and regional disparities. The study’s findings provide insights for policymakers seeking to optimize socioeconomic outcomes for young Canadians.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.005 | 0.014 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.003 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.004 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".