DATA-DRIVEN PREDICTION OF CELLULAR NETWORKS COVERAGE: AN INTERPRETABLE MACHINE-LEARNING MODEL
Bibliographic record
Abstract
Understanding the extent and quality of wireless coverage provided by cellular networks is a key challenge for service providers as well as spectrum regulators. Conventionally, service providers build coverage maps by running expensive drive-test campaigns in a controlled fashion and then spatially interpolating the measurements. With the advent of crowd-sourcing applications providing performance data of mobile users however, there is potential to directly characterize the coverage using large amounts of user-reported data. In this paper, we fuse crowd-sourced measurements from users of Long-Term Evolution (LTE) cellular systems with other information about user's context and radio access network (RAN) configuration to build a predictive model of wireless coverage. We compare the proposed model's predictions against a conventional empirical model as well as values obtained by spatial interpolation of drive-test measurements; indicating the superior accuracy of our data-driven model. We further interpret the model's predictions using the recently-introduced Shapley Additive Explanations (SHAP) framework, allowing us to quantify each feature's contribution to model output.
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 | 0.002 | 0.008 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 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".