[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-86583-en":3,"doc-seo-86583-105":29,"detail-sidebar-cat-0-en-105":95},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},86583,7971461741311,"Ophelia","https://ap-avatar.wpscdn.com/avatar/74000253aff267980c6?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779345379180704826",8,"Research & Report","STEP: Career-Path Recommendation via Temporal and Educational Trajectory Modeling","Career paths reflect long-term skill acquisition, role transitions, and educational investment, yet resume data remains difficult to analyze at scale due to its unstructured, heterogeneous, and multilingual nature. STEP (Sequential Trajectory of Employment Prediction) is introduced as a career-path recommendation system that predicts the next job by modeling temporal dynamics and educational signals from resumes. The approach combines a time-decay GRU, FiLM conditioned on educational attainment, attention-based sequence pooling, and a ROUTE procedure using contrastive learning to improve occupation representations. Experiments on four career-trajectory datasets show strong performance over state-of-the-art baselines, with public release of dataset and code.","arXiv :2607 . 1 1722v 1 [ cs .CL] 13 Jul 2026  \nSTEP: Career-Path Recommendation via Temporal and Educational Trajectory Modeling  \nIMAN JOHARY, AIDA-IDLab, Ghent University, Belgium GUILLAUME BIED, AIDA-IDLab, Ghent University, Belgium ALEXANDRU C. MARA, AIDA-IDLab, Ghent University, Belgium TIJL DE BIE, AIDA-IDLab, Ghent University, Belgium  \nCareer paths encode decades of skill acquisition, role transitions, and educational investment, and understanding them at scale underpins workforce planning, labor market policy, and job recommendation. Resumes are a rich source of information about career paths: they contain detailed descriptions of work experience, education, and skills. Yet their unstructured, heterogeneous, and multilingual nature has long prevented large-scale systematic analysis. With the advent of large language models (LLMs), it is now possible to source rich career trajectory data containing temporal and educational signals from unstructured resumes, enabling new opportunities for career-path recommendation.  \nExploiting this opportunity, we present STEP (Sequential Trajectory of Employment Prediction), a novel career-path recommendation system that leverages temporal and educational signals to predict the next job ina career trajectory. STEP integrates a time-decay Gated Recurrent Unit (GRU) cell to model temporal dynamics, Feature-wise Linear Modulation (FiLM) conditioned on educational attainment, and attention-based sequence pooling to select relevant features for next job prediction. To improve internal occupation representation for STEP, we introduce ROUTE, a two-stage contrastive procedure that first adapts a multilingual encoder to the career domain via unsupervised denoising autoencoding, then performs supervised contrastive fine-tuning with guided negative selection.  \nWe evaluate STEP on four datasets of career trajectories, including an improved version of our publicly available JobHop dataset, and show that it outperforms state-of-the-art baselines in next job prediction. The dataset and code are publicly released to support reproducible career-trajectory research.  \nCCS Concepts: • Information systems → Recommender systems; Probabilistic retrieval models; • Computing methodologies → Information extraction; Learning latent representations.  \nAdditional Key Words and Phrases: labour market analysis, large language models, ESCO classification, career trajectory, dataset, representation learning, sequential prediction  \nACM Reference Format:  \nIman Johary, Guillaume Bied, Alexandru C. Mara, and Tijl De Bie. 2026. STEP: Career-Path Recommendation via Temporal and Educational Trajectory Modeling. ACM Trans. Inf. Syst. 1, 1, Article 1 (January 2026), 39 pages. [https://doi.org/XXXXXXX.XXXXXXX](https://doi.org/XXXXXXX.XXXXXXX)  \nAuthors’ addresses: Iman Johary, Guillaume Bied, Alexandru C. Mara, and Tijl De Bie, AIDA-IDLab, Department of Electronics and Information Systems, Ghent University, Ghent, Belgium. {iman.johary, guillaume.bied, alexandru.mara, [tijl.debie}@ugent.be](tijl.debie}@ugent.be).  \nPermission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires [prior specific permission and/or a fee. Request permissions from permissions@acm.org](prior specific permission and/or a fee. Request permissions from permissions@acm.org).  \n© 2026 Copyright held by the owner/author(s) . Publication rights licensed to ACM.  \nACM 1558-2868/2026/1-ART1  \n[https://doi.org/XXXXXXX.XXXXXXX](https://doi.org/XXXXXXX.XXXXXXX)  \nACM Trans. Inf. Syst., Vol. 1, No. 1, Article 1 . Publication dat","cbCaikc2DYzzkp2Y","https://ap.wps.com/l/cbCaikc2DYzzkp2Y","pdf",1113304,1,39,"English","en",105,"# Overview\n## Motivation and data challenges\n## STEP model and key components\n## ROUTE representation learning\n## Experimental evaluation and results\n## Public dataset and code","[{\"question\":\"What problem does STEP address?\",\"answer\":\"STEP targets next job prediction from a person’s career trajectory, using information extracted from resumes to recommend reachable career paths more precisely than methods based on aggregate transition matrices.\"},{\"question\":\"How does STEP incorporate time and education signals?\",\"answer\":\"STEP uses a time-decay GRU to model temporal dynamics and applies FiLM conditioned on educational attainment, then uses attention-based sequence pooling to focus on relevant features for predicting the next job.\"},{\"question\":\"What is ROUTE and why is it used?\",\"answer\":\"ROUTE is a two-stage contrastive procedure that first adapts a multilingual encoder to the career domain via unsupervised denoising autoencoding, then performs supervised contrastive fine-tuning with guided negative selection to strengthen occupation representations.\"},{\"question\":\"How is STEP evaluated and what are the outcomes?\",\"answer\":\"STEP is evaluated on four career-trajectory datasets, including an improved version of JobHop, and is shown to outperform state-of-the-art baselines in next job prediction, with dataset and code publicly released for reproducibility.\"}]",1784212770,98,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":90,"head_meta":92,"extra_data":94,"updated_unix":27},"step-career-path-recommendation-via-temporal-and-educational-trajectory-modeling","",{"@graph":35,"@context":89},[36,53,68],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/step-career-path-recommendation-via-temporal-and-educational-trajectory-modeling/86583/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-24","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81,85],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does STEP address?","Question",{"text":75,"@type":76},"STEP targets next job prediction from a person’s career trajectory, using information extracted from resumes to recommend reachable career paths more precisely than methods based on aggregate transition matrices.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does STEP incorporate time and education signals?",{"text":80,"@type":76},"STEP uses a time-decay GRU to model temporal dynamics and applies FiLM conditioned on educational attainment, then uses attention-based sequence pooling to focus on relevant features for predicting the next job.",{"name":82,"@type":73,"acceptedAnswer":83},"What is ROUTE and why is it used?",{"text":84,"@type":76},"ROUTE is a two-stage contrastive procedure that first adapts a multilingual encoder to the career domain via unsupervised denoising autoencoding, then performs supervised contrastive fine-tuning with guided negative selection to strengthen occupation representations.",{"name":86,"@type":73,"acceptedAnswer":87},"How is STEP evaluated and what are the outcomes?",{"text":88,"@type":76},"STEP is evaluated on four career-trajectory datasets, including an improved version of JobHop, and is shown to outperform state-of-the-art baselines in next job prediction, with dataset and code publicly released for reproducibility.","https://schema.org",{"og:url":51,"og:type":91,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":93,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":96},[97,101,105,109,114,119,124,127,132,135,139],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":102,"show_sort_weight":103,"slug":104},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},"Exam",70,"exam",{"id":110,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},5,"Comic",60,"comic",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},6,"Technology",50,"technology",{"id":120,"doc_module":4,"doc_module_name":45,"category_name":121,"show_sort_weight":122,"slug":123},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":125,"slug":126},30,"research-report",{"id":128,"doc_module":4,"doc_module_name":45,"category_name":129,"show_sort_weight":130,"slug":131},9,"Religion & Spirituality",20,"religion-spirituality",{"id":130,"doc_module":4,"doc_module_name":45,"category_name":133,"show_sort_weight":130,"slug":134},"World Cup","world-cup",{"id":136,"doc_module":4,"doc_module_name":45,"category_name":137,"show_sort_weight":136,"slug":138},10,"Lifestyle","lifestyle",{"id":140,"doc_module":4,"doc_module_name":45,"category_name":141,"show_sort_weight":110,"slug":142},19,"General","general"]