Advanced Predictive Approaches to Talent Management Employee Retention Productivity and Career Growth

Today’s workforce calls for a pro-active approach towards talent management beyond the existing reactive approach. This paper develops an integrated predictive model based on deep learning and graphical architectures that will model employee retention probability, productivity dynamics, and career trajectory in parallel. In contrast to the current practice of dealing with each of these aspects separately, the methodology introduced in the paper is based on sequential HRIS data and relational networks to derive insights for talent management. The model utilizes the LSTM-Attention mechanism to predict retention probability and GNN for personalized career planning, making it possible to predict retention, optimize productivity, and plan career development in parallel. Comparative analysis of the models’ performance shows that an integrated architecture outperforms separate machine learning models in terms of modeling interactions between retention, productivity, and growth outcomes.

Authors

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-15
DOI
https://doi.org/10.5281/zenodo.24246133
Primary Topic
AI and HR Technologies
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Advanced Predictive Approaches to Talent Management Employee Retention Productivity and Career Growth

Dr. Vijaya Rani N, Dr.R Dhanasekaran, Dr.Kavitha P
Zenodo (CERN European Organization for Nuclear Research)
AI and HR Technologies
article

Advanced Predictive Approaches to Talent Management Employee Retention Productivity and Career Growth

Dr. Vijaya Rani N, Dr.R Dhanasekaran, Dr.Kavitha P
article en

Abstract

Today’s workforce calls for a pro-active approach towards talent management beyond the existing reactive approach. This paper develops an integrated predictive model based on deep learning and graphical architectures that will model employee retention probability, productivity dynamics, and career trajectory in parallel. In contrast to the current practice of dealing with each of these aspects separately, the methodology introduced in the paper is based on sequential HRIS data and relational networks to derive insights for talent management. The model utilizes the LSTM-Attention mechanism to predict retention probability and GNN for personalized career planning, making it possible to predict retention, optimize productivity, and plan career development in parallel. Comparative analysis of the models’ performance shows that an integrated architecture outperforms separate machine learning models in terms of modeling interactions between retention, productivity, and growth outcomes.

Zenodo (CERN European Organization for Nuclear Research)
AI and HR Technologies
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon