Advanced International Journal for Research

E-ISSN: 3048-7641   •   Impact Factor: 9.11

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Call for Paper Volume 7, Issue 4 (July-August 2026) Submit your research before last 3 days of August to publish your research paper in the issue of July-August.
Submit Research Paper Join as a Reviewer

Plagiarism is checked by the leading plagiarism checker TurnItIn

Call for Paper

Volume 7 Issue 4
July-August 2026

Submit your research paper

Indexing Partners
Academia Advanced Sciences Index Bielefeld Academic Search Engine CiteSeer DRJI Google Scholar Independent Search Engine & Directory Network ISI (International Scientific Indexing) Issuu Mendeley Research Networks
RefSeek ResearcherId - Thomson Reuters ResearchGate Scirus Scribd Semantic Scholar Wiki for Call for Papers WorldCat Zenodo

Reproducibility Audit of a Five-Hidden-Layer Feedforward Network for Customer Churn Classification

Author(s) Ms. Shabista Khan, Ms. Dipti Sharma
Country India
Abstract Abstract. This paper presents a reproducibility audit of a customer-churn experiment using a supplied 64,374- record CSV, a MATLAB source listing, and stored result figures. The active program excludes CustomerID, uses ten behavioral and service-related predictors, trains on records 1-10,000, and evaluates records 10,001-13,001 as a 3,001-record external holdout. It constructs a feedforward fitting network with five hidden layers of ten neurons each. Dense connectivity implies 561 trainable weights and biases. Stored MATLAB artefacts report LevenbergMarquardt training, termination at epoch 24, best validation mean-squared error of 0.032864 at epoch 18, final training performance of 0.00902, and an all-development regression coefficient of 0.93989. A stored external figure reports 95.77% accuracy. The source variable calls the associated 4.23% quantity MAPE, although the implemented expression contains no percentage-error denominator; it is an absolute-label error and equals misclassification rate only when every rounded output is binary. No active particle-swarm-optimization routine exists in the executable code. The contribution is therefore an implementation-aligned audit rather than a new experiment: it corrects the model description and parameter count, documents the actual row partitions, separates internal validation from the external holdout, and marks unavailable evidence explicitly. Because the exact MATfile, trained object, random seed, scores, and predictions are absent, the paper does not claim an independent rerun or invent confusion-matrix, AUC, calibration, or uncertainty results.
Keywords Keywords. Customer Churn; Reproducibility Audit; Feedforward Neural Network; LevenbergMarquardt; Source-Code Verification; External Holdout; Research Integrity
Field Engineering
Published In Volume 7, Issue 4, July-August 2026
Published On 2026-08-25
View / Download PDF File

Share this



E-ISSN 3048-7641
CrossRef

CrossRef DOI is assigned to each research paper published in our journal.

AIJFR DOI prefix is
10.63363/aijfr

Downloads
Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 7 Isu 4Cover Page Vol 7 Isu 3Cover Page Vol 7 Isu 2

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA Open Access

About AIJFR
Fees & Payment
Current Issue
Publication Archive 		Submit Research Paper
Track Submission Status
Publication Guidelines
Publication Ethics
Peer Review & Plagiarism 		Join as a Reviewer
Editors & Reviewers
Reviewer Referral Program
Get Reviewer Membership Certi. 		Website/Journal Policies
Usage Policy
Content Policies
Privacy Policy
Contact Us +91-9898-79-39-59 editor@aijfr.com