Balázs Hidasi

Data Mining Researcher

CV

Last update: 18.07.2016.
Download as PDF

Work experience

Head of Data Mining and Research (January 2015 - Present)
at Gravity Research and Development Inc.

As the leader of the data science team, I am responsible for research and data mining activities in Gravity. I coordinate the team's and also conduct my own research in the field of machine learning and data mining. The research revolves around (1) developing advanced recommender algorithms to make Gravity's recommender engine even better; and (2) exploring new fields and application areas for recommender systems. I also coordinate and consult data mining projects (e.g. data analysis, POCs) within the company.

Research Intern (June 2015 - September 2015)
at Telefónica I+D

As part of a research collaboration between Telefónica I+D and Gravity R&D in the CrowdRec project, I spent three months at TID in Barcelona. During this time, we laid the foundations for a longer research project that aims at developing the next generation of recommender algorithms using advanced machine learning techniques.

Data Mining Researcher (January 2010 - January 2015)
at Gravity Research and Development Inc.

I joined the Gravity R&D team in January 2010 as a datamining researcher. My main responsibilities are research and data analysis. The research revolves around developing new, intelligent machine learning algorithms that can give more relevant/efficient recommendations. Experimentation with recommendation algorithms also includes determining the circumstances in which a given algorithm can be used efficiently. Customer data analysis reveals the behavior of the users of the customer and makes us able to select the most efficient algorithms and parameterizations for the given recommendation problem. An other part of this task is monitoring the efficiency of the live recommendation system and modifying the algorithms based on the feedback, if necessary. I am also responsible for implementing the well-tried algorithms from my research into the recommendation engine of Gravity.

R&D projects

CrowdRec (November 2013 - Present)
at Gravity Research and Development Inc.

CrowdRec is an EU FP7 funded research project that aims to create the new generation of recommender systems. In order to enhance current systems, the project focuses on context-awareness, interactivity, scalability, stream recommendations and on creating symbiosis between users and the system so the users will provide relevant information to the system and will get better service as a result. The consortium partners are: Technical University of Delft, Technical University of Berlin, Gravity Research & Development Zrt, Moviri, Telefónica I+D, Tuenti, Xing. The project is coordinated by JCP-Connect.

ShiftTree research (January 2008 - September 2011)
at DmLab (BME-VIK, TMIT)

Individual research project in which I created and examined a novel, model-based time-series classifier algorithm, coined ShiftTree. During the research I was affiliated with DmLab (led by Csaba Gáspár) at the Department of Telecommunications and Mediainformatics (TMIT) at the Budapest University of Technology and Economics (BME).

Education

Ph.D. candidate (September 2014 - June 2016)

Budapest University of Technology and Economics,
Department of Telecommunications and Mediainformatics,
Data Science and Content Technologies Laboratory (DCLab)

Summa cum laude Ph.D. (30.06.2016)

Ph.D. studies (September 2011 - September 2014)

Budapest University of Technology and Economics,
Computer Sciences Doctorate School,
Intelligent Systems Group

M.Sc. studies in Computer Science and Engineering (2009 - 2011)

Budapest University of Technology and Economics,
Faculty of Electrical Engineering and Informatics,
Major in Computer science and engineering (M.Sc.)

Graduated with Highest Honors (21.07.2011)

B.Sc. studies in Computer Science and Engineering (2005 - 2009)

Budapest University of Technology and Economics,
Faculty of Electrical Engineering and Informatics,
Major in Computer science and engineering (B.Sc.)

Graduated with Highest Honors (08.01.2009)

Highschool studies

Eötvös József Gimnázium,
Scientific faculty

Excellent graduation with distinction (25.06.2005)

Teaching experience

Lectures on recommender systems (2011 - 2014, every semester)
at Budapest University of Technology and Economics

As part of various bachelor and master courses at BME-VIK TMIT, mainly in "Tartalomelemzés" (Content analysis) and "Media and Text Mining" courses.

Databases (2011 - 2014, fall semesters)
at Budapest University of Technology and Economics

Giving classes, scoring students, creating practice exercises.

Software laboratory 5. (Database laboratory) (2009 - 2014, spring semesters)
at Budapest University of Technology and Economics

Giving lab classes on the practical side of databases, scoring students, creating practice exercises.

Invited talks

24. July 2014
at University of Szeged

I presented a lecture on the context-aware recommendation problem and context-aware algorithms as a part of a summer course at the University of Szeged.

11. April 2014
at Technical University of Delft

I gave an hour long talk on my research to fellow researchers at the Technical University of Delft.

14. March & 25. April 2013
at Óbuda University

Two lectures on implicit feedback and context-awareness as part of the recommender systems course at the Óbuda University.

Awards & honors

2009

2nd place award
at the Thesis Competition organized by the Scientific Association for Infocommunications Hungary

Scholarship of the (Hungarian) Republic for 2009/2010

Best presentation award
at the Graduates' Conference organized by the Scientific Association for Infocommunications Hungary

3rd place award
at the National Scientific Students' Association Conference with the dissertation titled "Solving the problem of time series classification with a novel, decision tree based data mining algorithm" ("Az idősor osztályozás problémájának megoldása új, döntési fa alapú adatbányászati algoritmussal")

2008

1st place award
at the Scientific Students' Association Conference with the dissertation titled "Solving the problem of time series classification with a novel, decision tree based data mining algorithm" ("Az idősor osztályozás problémájának megoldása új, döntési fa alapú adatbányászati algoritmussal")

2004

Natiobal 31th place
from mathematics at the National academic competition for high school students (OKTV)

Languages

Hungarian – Native proficiency
English – Professional working proficiency
German – Elementary proficiency

Professional interest

Machine learning, artificial intelligence
Data mining research and analysis
Recommender systems