Clustering of PLN ULP Binjai Timur Customer Complaints using the K-Means Method
Bibliographic record
Abstract
The large number of customer complaints received daily by PLN ULP Binjai Timur presents a challenge in providing responsive and accurate service. Irregularities in recording and grouping complaints mean that the available information is less than optimal for supporting decision-making. This study aims to group customer complaints based on similar characteristics for easier analysis. The method used is the K-Means algorithm, a clustering technique in data mining that divides data into several groups based on their proximity to the cluster center (centroid). The analysis was conducted through the Knowledge Discovery in Database (KDD) stages, which include data selection, transformation, and algorithm implementation using MATLAB software. The three main variables used in the grouping process were complaint type, complaint submission medium, and customer address. The implementation results in three main complaint clusters with distinct patterns, providing PLN with insight into the most frequently encountered problems, areas with high complaint rates, and the most frequently used reporting medium. These findings provide an important foundation for PLN in setting treatment priorities, improving service quality, and strengthening customer relationships. The application of the K-Means algorithm has proven effective as a systematic and practical solution for managing complex and large amounts of complaint data.
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 | 0.001 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.005 | 0.006 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| 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".