Churn Prediction Model Improvement Using Automated Machine Learning with Social Network Parameters
Bibliographic record
Abstract
Due to strong competition in the telecom market, telecom companies are facing customer churn problems. For telecom, it is very important to predict the churn of a user to be able to prevent it. Marketing campaigns can be used to prevent churn and thus prevent a decrease in revenue. Usually, the churn prediction is based on behavioural user data, which describes user activity and general user data. In our prediction model, we added social network attributes that describe the social influence of other users on the user's decision to make a churn. Besides standard centrality measures, we developed two new social attributes, which measure the social influence of already churned users. To determine if social network attributes aid in churn prediction precision we created and compared the models based only on the behavioural data and the models with the social attributes and behavioural data. In our work, we propose upgrading the standard Automated Machine Learning (AutoML) model with the part of the model related to Social Network Analysis (SNA), and we use the proposed model in our research. We show that the AutoML can be used to successfully predict telecom churn based on the real data from telecom operators from Bosnia and Herzegovina.
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 | 0.006 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".