OPENSKIMR A JOB- AND LEARNINGPLATFORM

David C. Wyld et al. (Eds) : CSITA, ISPR, ARIN, DMAP, CCSIT, AISC, SIPP, PDCTA, SOEN - 2017
pp. 95– 106, 2017. © CS & IT-CSCP 2017 DOI : 10.5121/csit.2017.70110
OPENSKIMR A JOB- AND LEARNING-
PLATFORM
Andreas Kofler1
and Marianne Prast2
1,2
Management Center Innsbruck (MCI), Innsbruck, Austria
andreas.kofler@mci.edu, marianne.prast@mci.edu
ABSTRACT
This paper is concerned with the mathematical aspects of the development of the job- and
learningplatform OPENSKIMR. The platform should enable users to be matched with jobs
based on their individual skill profile and the job skill requirements. Further, once users have
chosen jobs they like, possible learnings in order to better fit the job’s requirements are
recommended. We give a short introduction to the data model we use and show the
mathematical framework we act within. Further, we present our Route Planner Algorithm and
discuss its functionality.
KEYWORDS
OpenSkiMr, knowledge engineering, data mining, digitalization, e-learning, learning roadmap,
matching, recommender systems
1. INTRODUCTION
OPENSKIMR (Open European Skill Match Maker) is a project funded by the European Union.
The goal is to develop a matching system between users, jobs and education. In doing so, the
platform should help stabilize the European labor market (especially for young people), foster
lifelong learning and vocational education and enhance geographic mobility within Europe. The
philosophy standing behind OPENSKIMR is the picture of a route. Users should be able to find
new ways, new goals as well as get information on how to reach them.
The platform should perform the following tasks:
• Submitting skills or dream job: OPENSKIMR offers two different ways to submit
personal information that builds the basis for the subsequent matching. The user can
either sketch a personal skill profile or submit a dream job.
• Matching the users according to their skill profile with occupations and jobs: Skill
mismatch is a complex problem which does affect not only those who are looking for a
job but most of the workforce. The phenomenon of skill mismatch involves underskilling
as well as overskilling. Both can undermine the long-term potential of the workforce [1].
• Suggesting an education route: The user receives recommendations for learnings which it
might be interested in in order to better fit a job’s requirements

96 Computer Science & Information Technology (CS & IT)
2. DATA MODEL
The functionality of OPENSKIMR is based on ESCO (European Skills, Competences and
Occupations) catalogue. The outcome is a standardized data set with a common understanding of
occupations and their related skills and knowledge, as well as the relationships between these
concepts. It is part of the Europe 2020 strategy [2].
2.1. NOTATION

Computer Science & Information Technology (CS & IT) 97
3. SKILLS AND TOOLS ASSESSMENT
Since we base the matching of users and job profiles on the skills and tools required, the first
problem we are faced with is to offer the user an accessible way to build its profile by rating some
skills and tools.
On the one hand, a user may have a quite clear idea of the area it wants to work in and therefore
might rate skills which are related to certain occupations. On the other hand, a user may not have
a specific choice on the area but would rather like to get an overview of jobs it would fit to. In
this case the user might be interested in rating its skills by choosing them from some skills
clusters. When a user rates its skills by browsing occupations, it finds tools when they are related
to skills. For example, when a user states that it has knowledges about programming, the user has
the possibility to rate the programmning languages C++ or Java. Recruiters are treated the same
as users when they create a job advertisement.
3.2. CLUSTERING OF SKILLS AND OCCUPATIONS

4. FUNCTIONALITY OF OPENSKIMR
4. 1 MATCHING FUNCTION

4.2. MATCHING USERS WITH JOBS AND OCCUPATIONS

4.3. ROUTE PLANNER ALGORITHM
4.3.1. DEFINITION OF A LEARNING

4.3.2. CONSTRUCTION OF A LEARNING ROUTE

5. TESTING

6. CONCLUSIONS AND FUTURE WORK

FUNDING
This work has been supported by the European Union with Agreement Number ECOKT 2014-4-
30-CE-0741117/00-28.
ACKNOWLEDGEMENTS
The authors would like to thank the whole OPENSKIMR project team for the pleasant ambience
and the numerous discussions which led to this work
REFERENCES
[1] CEDEFOP (2015). Matching Skills and Jobs in Europe. European Centre for the Development of
Vocational Training, Europe 123, 570 01 Thessaloniki (Pylea), Greece, 2nd edition.
[2] European Commission (2013). European Classification of Skills/Competences, Qualifications and
Occupations. European Commission, Publications Office of the European Union: Luxembourg, 1st
edition.
[3] Ricci, F., Rokach, L., and Shapira, B. (2015). Recommender Systems Handbook -Springer, Berlin,
Heidelberg, 2nd edition.
[4] Liu, B. (2011). Web Data Mining - Exploring Hyperlinks, Contents, and Usage Data.Springer Science
and Business Media, Berlin Heidelberg.
[5] Aric A. Hagberg, Daniel A. Schult, P. J. S. (2008). Exploring network structure, dynamics, and
function using NetworkX. In Proceedings of the 7th Python in Science Conference (SciPy2008),
pages 1115, Pasadena, CA USA.
[6] Gan, G., Ma, C., and Wu, J. (2007). Data Clustering - Theory, Algorithms, and Applications.SIAM,
Philadelphia.

OPENSKIMR A JOB- AND LEARNINGPLATFORM

More Related Content

What's hot (18)

Viewers also liked (18)

Similar to OPENSKIMR A JOB- AND LEARNINGPLATFORM (20)

Recently uploaded (20)

OPENSKIMR A JOB- AND LEARNINGPLATFORM