PENERAPAN DATA MINING PENGELOMPOKAN JAMINAN HARI TUA (JHT) BERDASARKAN WILAYAH DALAM MASA PANDEMI (STUDI KASUS : BPJS KETENAGAKERJAAN CABANG LANGKAT)
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
During the COVID-19 pandemic, many companies experienced a decline or went bankrupt, so they had to reduce the number of workers and even close the company. BPJS Ketenagakerjaan is a public legal entity that is responsible to the president and functions to administer four programs, namely Work Accident Insurance (JKK), Death Insurance (JKM), Old Age Security (JHT), with the addition of the Pension Guarantee program (JP). One of them is the submission of claims from too many participants of the Old Age Security program from various regions, especially the Langkat sub-district, so that it becomes a big problem to provide good service or information for the participants. For this reason, the author tries to create a system to support a computerized grouping process that can help automatically classify JHT claims by region, so there is an opportunity to design a grouping data mining system in it. Data mining is a process of mining data in very large amounts of data using statistical, mathematical methods, to utilizing the latest artificial intelligence technology. Clustering is a method that is applied in creating a grouping data mining system to make it easier for employees to group JHT by region. Based on the analysis that has been done in the grouping of old-age insurance data using the clustering method, it is necessary to do the cluster process several times to get the same results according to the process that was first carried out, namely in cluster 1 : 2 3 2 cluster 2 : 2 8 2, cluster 3 : 2 13 2 with 545 data in cluster 1, 308 data in cluster 2 and 421 data in cluster 3.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.002 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.005 | 0.006 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 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 it