Understanding the influence basic service and value-added service usage has on customer churn in Pay-TV subscription services
Bibliographic record
Abstract
Similarly to other North-American markets, new digital services and alternatives to the traditional pay-TV service are proliferating while the Canadian pay-TV industry is witnessing persistent subscriber losses. In an attempt to support changing viewing behaviors, generate more value and protect the subscriber base, pay-TV operators are extending their core TV service using value-added services (VAS). However, whether or not VAS successfully contributes to reducing subscriber attrition is unknown for academics and operators alike. Using survival analysis, the research examines VAS usage and churn behaviors for 11 647 pay-TV customers over a 12-month period. The results show that VAS users are not systematically less likely to churn and their churn behavior largely depends on usage frequency and usage patterns. Customers with constant or increasing usage frequency are less likely to churn than non VAS users and heaviest users appear to exhibit the greatest level of risk. Results also show that beneficial effects of VAS are generated by free services while payable VAS actually increases customers’ risk. These findings show that churn prediction models need to look beyond the core service and examine actual behavioral usage statistics for both the core service and value-added services. From a managerial perspective, the results confirm that service extensions do indeed generate value and operators can further reduce customer attrition by maximizing VAS adoption. However, the results also show operators need to maintain and stimulate usage to preserve the beneficial effect of VAS and better understand the drivers that increase service switching behaviors.
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 | 0.010 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| 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".