Enhancing interpretability in random forest: Leveraging inTrees for association rule extraction insights
Bibliographic record
Abstract
The random forest model is a powerful supervised learner, recognized for its ability to learn the pattern within data with superior predictive accuracy. However, it is a black box model because it lacks interpretability. This study addressed the interpretable challenge by employing the inTree framework. The rules were extracted from each decision tree in a random forest model, and the association rules were determined through measured matrix support and confidence to reveal the frequent variable interactions for predicting unemployment. This approach provided insight into the relationships between specific variables and unemployment outcomes. The developed method used data set from the integrated labor force survey (ILFS) 2020/2021 in Zanzibar. Zanzibar’s unemployment rate consistently increased across surveys conducted in 2006, 2014, and 2020/2021. Results have shown that the rules that most predict unemployment for individuals are female and lack of health insurance and secondary education level, female and youth age group and lack of health insurance and secondary education level with a high confidence level. This study provides practical insights for Zanzibar’s government to develop effective interventions, programs, and policies. Improving the interpretability of the random forest model enhances decision-making to address unemployment challenges.
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 | 0.011 | 0.040 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.005 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.004 | 0.004 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".