Customer Churn Prediction with Machine Learning Methods In Telecommunication Industry
Bibliographic record
Abstract
Abstract With the emergence of new competitors in today's globalizing world and the increase in investments in telecommunication services in an environment where change continues, the importance of marketing strategies and the conscious behavior of customers have become an important demand for companies. New regulations and technologies increase competition among mobile operators. Because acquiring a new customer is more expensive than acquiring active customers, companies seek solutions to reduce the churn rate. Therefore, telecommunications companies want to analyze the concept of the customer's desire to change the service provider and take the necessary measures to protect their existing customers. In this study, usage information, usage trends, subscription commitment, subscription age, ARPU (average revenue per user) and billing information, competitor familiarity, outgoing call information, number porting experience, etc. Loss estimation modeling was made taking into account the The data set includes 593 columns and 1826588 lines. Corporate mobile customers were analyzed by dividing into three subgroups as Single Line Mobile Customers, 2-5 Line Mobile Customers, and 6-15 Line Mobile Customers. In order to estimate customer loss, various data mining analyzes were made with machine learning techniques in the SAS application. Four different machine learning methods were used while creating loss prediction models. The machine learning methods used are random forest, logistic regression, decision tree, gradient boosting. The model was developed by modeling with 600 different variables and loss estimation was made. ROC curves and lift chart results for different corporate mobile customer groups were compared and the most suitable models were selected for each group. In this project, it is aimed to prevent loss of revenue for different corporate mobile segment groups by estimating potential customer losses.
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 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.000 | 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 | 0.000 |
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".