Beyond Accuracy Optimization: On the Value of Item Embeddings for Student Job Recommendations

Emanuel Lacic, Dominik Kowald, Markus Reiter-Haas, Valentin Slawicek, Elisabeth Lex

Research output: Contribution to journalArticleResearchpeer-review

Abstract

In this work, we address the problem of recommending jobs to university students. For this, we explore the utilization of neural item embeddings for the task of content-based recommendation, and we propose to integrate the factors of frequency and recency of interactions with job postings to combine these item embeddings. We evaluate our job recommendation system on a dataset of the Austrian student job portal Studo using prediction accuracy, diversity and an adapted novelty metric. This paper demonstrates that utilizing frequency and recency of interactions with job postings for combining item embeddings results in a robust model with respect to accuracy and diversity, which also provides the best adapted novelty results.
Original languageEnglish
JournalarXiv.org e-Print archive
Publication statusPublished - 21 Nov 2017

Fingerprint

Students
Recommender systems

Keywords

  • cs.IR

Cite this

Beyond Accuracy Optimization : On the Value of Item Embeddings for Student Job Recommendations. / Lacic, Emanuel; Kowald, Dominik; Reiter-Haas, Markus; Slawicek, Valentin; Lex, Elisabeth.

In: arXiv.org e-Print archive, 21.11.2017.

Research output: Contribution to journalArticleResearchpeer-review

@article{e6cfb19e44c243ea90d14fff6a43bdce,
title = "Beyond Accuracy Optimization: On the Value of Item Embeddings for Student Job Recommendations",
abstract = "In this work, we address the problem of recommending jobs to university students. For this, we explore the utilization of neural item embeddings for the task of content-based recommendation, and we propose to integrate the factors of frequency and recency of interactions with job postings to combine these item embeddings. We evaluate our job recommendation system on a dataset of the Austrian student job portal Studo using prediction accuracy, diversity and an adapted novelty metric. This paper demonstrates that utilizing frequency and recency of interactions with job postings for combining item embeddings results in a robust model with respect to accuracy and diversity, which also provides the best adapted novelty results.",
keywords = "cs.IR",
author = "Emanuel Lacic and Dominik Kowald and Markus Reiter-Haas and Valentin Slawicek and Elisabeth Lex",
note = "4 pages, 2 figures, 1 table",
year = "2017",
month = "11",
day = "21",
language = "English",
journal = "arXiv.org e-Print archive",
publisher = "Cornell University Library",

}

TY - JOUR

T1 - Beyond Accuracy Optimization

T2 - On the Value of Item Embeddings for Student Job Recommendations

AU - Lacic, Emanuel

AU - Kowald, Dominik

AU - Reiter-Haas, Markus

AU - Slawicek, Valentin

AU - Lex, Elisabeth

N1 - 4 pages, 2 figures, 1 table

PY - 2017/11/21

Y1 - 2017/11/21

N2 - In this work, we address the problem of recommending jobs to university students. For this, we explore the utilization of neural item embeddings for the task of content-based recommendation, and we propose to integrate the factors of frequency and recency of interactions with job postings to combine these item embeddings. We evaluate our job recommendation system on a dataset of the Austrian student job portal Studo using prediction accuracy, diversity and an adapted novelty metric. This paper demonstrates that utilizing frequency and recency of interactions with job postings for combining item embeddings results in a robust model with respect to accuracy and diversity, which also provides the best adapted novelty results.

AB - In this work, we address the problem of recommending jobs to university students. For this, we explore the utilization of neural item embeddings for the task of content-based recommendation, and we propose to integrate the factors of frequency and recency of interactions with job postings to combine these item embeddings. We evaluate our job recommendation system on a dataset of the Austrian student job portal Studo using prediction accuracy, diversity and an adapted novelty metric. This paper demonstrates that utilizing frequency and recency of interactions with job postings for combining item embeddings results in a robust model with respect to accuracy and diversity, which also provides the best adapted novelty results.

KW - cs.IR

M3 - Article

JO - arXiv.org e-Print archive

JF - arXiv.org e-Print archive

ER -