Outil de diagnostic et de prévention de l'insatisfaction des employés
Bibliographic record
Abstract
Employee retention is a burning problem in home care industry.Several studies have already been looking for solutions.They identified factors that can be grouped into five categories :-employee characteristics -scheduling -job related factors -social interactions with other employees and patients -structure related factors These studies aim for a measure of satisfaction using polls and surveys.The answers are then analyzed to highlight the causes of employee churn.Our project proposes a new way of studying employee satisfaction by looking directly at employees visit schedule.A partnership with AlayaCare allowed us to have access to such data.This company from Montreal offers a platform to home care agencies to ease coordinators' workload.The main user is generally a manager or a coordinator.Through the software, one can assign employees to visits and have a better overview of the staff workload.Various information can be found in the database : the length of visits, the location, or the type of service given.The objective is to extract as many features as possible to identify important ones among them.We decided to model this problem as a classification problem.One of the biggest challenge is that no obvious measure is available to assess the satisfaction of the employees through time.The proposed solution is to try to distinguish periods before an employee left from previous ones.Therefore, we should be able to identify the variables that evolved through time and may explain why an employee left.Preprocessing and shaping the data are necessary steps before creating training sets for classification models.Different time divisions has been tried to determine which one fits best the way we modelled this problem.Several classification algorithms have been implemented :-logistic regression -tree-based models (random forests and XGBoost) -neural networks Model selection run on different hyper-parameters in order to reach optimal performances.This method is applied on 10 health care clients : 6 located in Canada, 2 in the United Stated, and 2 in Australia.Comparing the results across these companies may help to generalize the ix
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 | 0.021 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.005 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.002 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.003 | 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".