Your new experience awaits. Try the new design now and help us make it even better

ORIGINAL RESEARCH article

Front. Big Data

Sec. Recommender Systems

Volume 8 - 2025 | doi: 10.3389/fdata.2025.1564521

This article is part of the Research TopicRecommender Systems for Human ResourcesView all articles

Towards more realistic Career Path Prediction: Evaluation and Methods

Provisionally accepted
Elena  SengerElena Senger1,2*Yuri  CampbellYuri Campbell2*Rob  Van Der GootRob Van Der Goot3Barbara  PlankBarbara Plank1
  • 1Ludwig Maximilian University of Munich, Munich, Germany
  • 2Fraunhofer Institute for Systems and Innovation Research ISI, Karlsruhe, Baden-Württemberg, Germany
  • 3IT University of Copenhagen, Copenhagen, Denmark

The final, formatted version of the article will be published soon.

Predicting career trajectories is a complex yet impactful task, offering significant benefits for personalized career counseling, recruitment optimization, and workforce planning. However, effective career path prediction (CPP) modeling faces challenges including highly variable career trajectories, free-text resume data, and limited publicly available benchmark datasets. In this study, we present a comprehensive comparative evaluation of CPP models-linear projection, multilayer perceptron (MLP), LSTM, and large language models (LLMs)-across multiple input settings and two recently introduced public datasets. Our contributions are threefold: (1) we propose novel model variants, including an MLP extension and a standardized LLM approach, (2) we systematically evaluate model performance across input types (titles only vs. title+description, standardized vs. free-text), and (3) we investigate the role of synthetic data and fine-tuning strategies in addressing data scarcity and improving model generalization. Additionally, we provide a detailed qualitative analysis of prediction behaviors across industries, career lengths, and transitions. Our findings establish new baselines, reveal the trade-offs of different modeling strategies, and offer practical insights for deploying CPP systems in real-world settings.

Keywords: Career Path Prediction, Recommendation, synthetic data, LLM, Labour market

Received: 21 Jan 2025; Accepted: 31 Jul 2025.

Copyright: © 2025 Senger, Campbell, Van Der Goot and Plank. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

* Correspondence:
Elena Senger, Ludwig Maximilian University of Munich, Munich, Germany
Yuri Campbell, Fraunhofer Institute for Systems and Innovation Research ISI, Karlsruhe, Baden-Württemberg, Germany

Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.