Prediction of Violence Against Women Using Ensemble Learning Models: A Comparative Study of LightGBM, XGBoost, and Others
Bibliographic record
Abstract
Violence against women and the possibility of its occurrence among children is a very serious issue that negatively impacts the physical, psychological, and emotional aspects of the victims and those around them.Various efforts have been made to reduce violence against women and children; however, in reality, such violence still occurs significantly in many countries due to emotions and turmoil within human relationships.It is necessary to propose prediction methods so that violence can be reduced through early observation and intervention against violence experienced by women.machine learning, as one of the Artificial Intelligence algorithms, offers a solution to identify and predict the risk of violence.This study aims to explore the use of several Ensemble Learning models, such as LightGBM, XGBoost, CatBoost, and AutoEnsemble, which are expected to improve prediction accuracy and stability.This study uses a dataset consisting of 348 samples with 5 selected features that represent indicators relevant to the risk of violence against women.The test results show that XGBoost and CatBoost achieved the highest accuracy, approximately 73%, with a precision of 76%, recall of 65%, and F1-Score of 70%.TabNet demonstrated similar performance with an accuracy of 73%, but with a higher recall of 70%.Meanwhile, LightGBM showed slightly lower performance with 68% accuracy and an F1-Score of 64%.AutoEnsemble produced stable results with 73% accuracy, 76% precision, 65% recall, and 70% F1-Score.However, the practical limitation of this study lies in the relatively small dataset size, which may affect the model's generalization ability when applied to larger or more diverse features.The findings of this study indicate that Ensemble Learning models can provide accurate and effective results in predicting violence against women.It is hoped that this research can contribute to more proactive and accurate efforts to prevent violence against women in the future.
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 | 0.003 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".