MétaCan
Menu
Back to cohort
Record W4286518196 · doi:10.18280/ria.360304

Churn Prediction Model Improvement Using Automated Machine Learning with Social Network Parameters

2022· article· en· W4286518196 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

venuePublished in a venue whose home country is Canada.
no affNo Canadian affiliation: this work is invisible to an affiliation-only frame.
No Canadian affiliation. An affiliation-only frame, the usual design, would never have seen this work. It is one of the works that make the case for inverting the frame.

Bibliographic record

VenueRevue d intelligence artificielle · 2022
Typearticle
Languageen
FieldBusiness, Management and Accounting
TopicCustomer churn and segmentation
Canadian institutionsnot available
Fundersnot available
KeywordsCentralityComputer scienceSocial network (sociolinguistics)RevenueCompetition (biology)Data scienceMachine learningArtificial intelligenceSocial network analysisRevenue modelSocial mediaWorld Wide WebBusiness

Abstract

fetched live from OpenAlex

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.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.115
Threshold uncertainty score0.953

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0010.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

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.

Opus teacher head0.041
GPT teacher head0.251
Teacher spread0.210 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it