International Journal of Leading Research Publication

E-ISSN: 2582-8010   •   Impact Factor: 9.56

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Monthly Scholarly International Journal

Call for Paper Volume 7 Issue 6 June 2026 Submit your research before last 3 days of to publish your research paper in the issue of June.
Submit Research Paper Join as a Reviewer

Plagiarism is checked by the leading plagiarism checker TurnItIn

Call for Paper

Volume 7 Issue 6
June 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 UTeM - Universiti Teknikal Malaysia Melaka Wiki for Call for Papers WorldCat Zenodo

FedCRM: Privacy-Preserving Federated Learning for Enterprise Salesforce CRM Analytics with Heterogeneous Schema Support and Differential Privacy

Author(s) Lalith Chandra Bandaru
Country United States
Abstract Enterprise Salesforce CRM implementations across business units, subsidiaries, and partner organisations contain customer relationship data whose analytical value substantially exceeds what any individual CRM yields from isolated local analysis. However, data governance regulations, contractual obligations, and internal data policies frequently prohibit centralising this data for joint model training. FedCRM is a federated learning framework for Salesforce CRM analytics that enables multiple organisations to collaboratively train predictive models — customer churn classifiers, lead conversion estimators, opportunity win probability models — without sharing raw CRM data. FedCRM contributes four innovations to federated CRM analytics: a heterogeneity-aware aggregation algorithm that weights participant contributions by both data volume and quality metrics; a per-participant configurable differential privacy budget management system; a Salesforce schema normalisation pipeline that maps heterogeneous custom field schemas to a common feature vocabulary; and a secure gradient aggregation protocol using threshold homomorphic encryption. Evaluated across nine Salesforce organisations over fourteen months, FedCRM achieves model performance within 3.1 percentage points of a centralised baseline while providing formal differential privacy guarantees. Federated models outperform locally trained models by an average of 7.4 percentage points on held-out test sets, confirming that federation provides genuine analytical value.
Keywords federated learning, differential privacy, Salesforce CRM, schema heterogeneity, privacy-preserving analytics, churn prediction, lead scoring, secure aggregation, FedAvg.
Field Computer > Artificial Intelligence / Simulation / Virtual Reality
Published In Volume 5, Issue 7, July 2024
Published On 2024-07-12
DOI https://doi.org/10.70528/IJLRP.v5.i7.2218
Short DOI https://doi.org/hb5p9s
View / Download PDF File

Share this



CrossRef

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

IJLRP DOI prefix is
10.70528/IJLRP

Downloads
Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 7 Isu 6 Cover Page Vol 7 Isu 5 Cover Page Vol 7 Isu 4

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 IJLRP
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 +91-9687-828-838 editor@ijlrp.com