PREDICTING CHURN IN TELECOM SECTOR USING A POPULATION-BASED INCREMENTAL ANN LEARNING ALGORITHM
Bibliographic record
Abstract
Abstract With global advancement, Information Technology has led to the growth of numerous Service Providers, which, in turn, has resulted in fierce competition between themselves. For Service Providers, the most prevalent obstacle is the handling of customer churn, retention, and satisfaction of customers for successful market sustenance. Customer Relationship Management (CRM) concentrates on boosting, sustaining, and building long term customer associations. CRM relies on the collection of information prior to making decisions. When a customer halts the existing service provider relationship and shifts to another, this is referred to as churn. The overall business profit and image are perturbed by this never-ending motion of churning. Therefore, it is more preferable to stop customers from churning and going for forecasting. In this work, churn prediction in telecom sector is investigated. Artificial Neural Network are used for prediction. To enhance the performance of the ANN, it is required to optimize its structure. From a given solution set, the global optimum can be detected utilizing the probabilistic method of Simulated Annealing (SA). Various optimization problems related to engineering and other areas have been resolved favourably with Population-Based Incremental Learning (PBIL) utilization. For predicting customer churn, this work has proposed a structure optimized Hybrid Simulated Annealing – Population-Based Incremental Learning ANN. Further deep learning techniques were used to improve the Churn prediction.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".