RESEARCH BY INDUSTRY
Find published research and synthetic demonstrations, with planned and developing topics clearly separated.
9 published public-data studies4 synthetic demonstrations51 planned or developing topics
1 published study · 2 planned or developing topics
S47 / Telecommunications
A telecom service leader wants to understand whether call failures, complaints and usage patterns identify customers at risk before departure. Test stable, interpretable signals and the limits of translating them into an intervention plan.
Evaluated public-data study
Read the finding and evidence ↗Additive models; calibration; causal diagrams; feature stability
These topics are separate from completed findings. Each status reflects the work actually performed.
S46 / Telecommunications
A telecom commercial team must allocate limited contact capacity across churn risk, product appetite and upsell likelihood. Test whether a shared predictive representation improves the three outcomes and clarifies tradeoffs between objectives.
Planned topic
Multi-task learning; calibrated probabilities; constrained allocation
Use the documented Orange KDD Cup targets and a manageable feature subset before scaling. Compare three independent regularized/boosted models with a shared multi-task representation. Audit missingness and anonymized features; calibrate each target separately and retain the official held-out protocol where labels are available.
Evaluation: Use nested development splits and an untouched customer test; do not invent timestamps. Report target-specific PR metrics, calibration, multi-task gains/losses and capacity-specific outcome capture. Test sensitivity to missing features and assumed value weights.
Boundary: Anonymous benchmark features limit business explanation. These labels do not identify causal offer response, actual revenue or a production-ready next-best-action policy; synthetic value assumptions must be clearly labeled.
S48 / Telecommunications
A network planning team wants to locate predictable activity peaks and unusual surges. Test whether spatial models improve short-horizon cell-grid activity forecasts and identify where a hypothetical capacity budget would be most exposed.
Planned topic
Spatiotemporal models; graph regularization; residual anomalies
Build time-aligned Milan grid series for the released activity measures. Compare seasonal baselines, spatially pooled models and a graph-temporal challenger. Define adjacency from the documented grid and preserve separate activity types; treat normalization and missing intervals explicitly.
Evaluation: Use blocked future-day/week holdouts and selected spatial blocks. Report scaled error, peak-period quantile loss and false alerts under a defined threshold. Test the short observation period's sensitivity to unusual days and compare any allocation policies only under common simulated assumptions.
Boundary: Normalized grid activity is not subscriber count, bytes, tower load or dropped-call experience. The short historical period cannot validate a physical network expansion plan or annual seasonality.
The 60-topic program spans 20 industries, with 9 studies published. Synthetic demonstrations are counted separately. Unpublished topics have no public case-study route.
