Research Seminar 9/5: “A combinatorial approach to entity matching for products”

School of Science and Technology
International Hellenic University

Thursday 9 May 2019

International Hellenic University, Lecture Room B1

Seminar Title

A combinatorial approach to entity matching for products”

Dr Leonidas Akritidis

Speaker information:
Leonidas Akritidis is a post-doctoral researcher at the Data Structuring and Engineering (DaSE) Lab of the Department of Electrical & Computer Engineering, University of Thessaly, Greece. He is also an MSc studies instructor in the same Department, teaching Data Structures, Algorithms and World Wide Web technologies. He obtained his PhD degree in 2013, and his BSc from the Department of Electrical & Computer Engineering of the Aristotle University of Thessaloniki, Greece, in 2003. His research interests include Data Mining, Machine Learning, Large-scale Data Processing, Big Data Engineering, and Information Retrieval.

Presentation at a glance:
The continuous growth of the e-commerce industry has rendered the problem of product retrieval particularly important. As more enterprises move their activities on the Web, the volume and the diversity of the product-related information increase quickly. These factors make it difficult for the users to identify and compare the features of their desired products. Recent studies proved that the standard similarity metrics cannot effectively identify identical products, since similar titles often refer to different products and vice-versa. Other studies employed external data sources (search engines) to enrich the titles; these solutions are rather impractical since the process of fetching external data is inefficient. In this presentation we will review the state-of-the-art approaches to entity matching and we will introduce UPM, an unsupervised algorithm for matching products by their titles. UPM is independent of any external sources and consists of three stages: during the first stage, the algorithm analyzes the titles and extracts combinations of words out of them. These combinations are evaluated in stage 2 according to several criteria, and the most appropriate of them are selected to form the initial clusters. The third phase is a post-processing verification stage which performs a refinement of the initial clusters by correcting the erroneous matches. This stage is designed to operate in combination with all clustering approaches, especially when the data possess properties which prevent the co-existence of two data points within the same cluster. We shall also present experimental results which demonstrate the superiority of the algorithm against multiple string similarity metrics and clustering methods.’s-studies.html

**IHU Students' Success Stories**

Congratulations to Ioannis Schoinas, IHU MSc in Mobile and Web Computing student, for his paper: Ι. Schoinas, C. Tjortjis, “MuSIF: A Product Recommendation System Based on Multi-source Implicit Feedback”, accepted by the 15th Int’l Conf. on Artificial Intelligence Applications and Innovations to be published by the Springer IFIP AICT (LNCS) Series.

The paper reports on MuSIF, a recommendation system equipped with a new method to increase the accuracy of matrix factorization algorithms via initialization of factor vectors, which is tested for the first time in an implicit model-based Collaborative Filtering approach. Moreover, it includes methods for addressing data sparsity. Evaluation shows that MuSIF can benefit customers and e-shop owners with personalization in real world scenarios.

You can find more ‘IHU Students’ Stories’ here .

The School of Science and Technology at the International Hellenic University hosted on 20-21/9, our partners: University of Mons (Belgium), Heriot Watt University (UK) and the University of the Basque Country (Spain), as well as the local associated partners: Hellenic Petroleum SA, CERTH, Association of Information Technology Companies of Northern Greece (SEPVE), Alexander Innovation Zone SA and the Municipality of Thermi, for the launch of our joint Erasmus Mundus Master in Smart Cities and Communities (SMACCs). Our School’s involvement is coordinated by Asst. Prof. Christos Tjortjis.

Applications will open shortly for the 2019 intake.

Scholarships of up to 47.000 euros per student will be available. Deadline 1/2/2019.

More information will be available soon at




Meeting’s agenda:
Thursday 20/9
9.30 Session 1
9.30-10.30: MSc Marketing steps
10.30-12.00: Final Common EMJMD (SMACCs) Presentation
12.00-12.30 coffee break
12.30 Session 2
Launching SMACCs (with invited guests)
12.30 Welcome / IHU presentation by IHU/SST Dean Prof. Evangelidis
12.45 UMONS presentation (Dr. Christos Ioakeimidis)
12.55 HWU presentation (Prof. Gudrun Kocher-Oberlehner)
1.05 UPV presentation (Prof. Luis A. Del Portillo Valdés)
1.15 SMACCS presentation (lead by UMONS but complemented by the other 3 partners)
1.30 Associated partners presentations

  • George Koulaouzides, General Secretary, Municipality of Thermi

          A brief description and some more information related to “Smart Cities”

  • Georgios Katsanos, Coordinator - Co-funded Projects, Association of Information Technology Companies of Northern Greece (SEPVE)

          SEPVE: mission and objectives

  • Georgios Dimitriou, Advisor to the President, Alexander Innovation Zone SA

          Thessaloniki: Innovation friendly destination

  • Spyros Kiartzis, Manager New Technologies and Alternative Energy Sources, Hellenic Petroleum SA

          Investing in New Technologies

  • Panagiotis Iordanopoulos, Research Associate, Hellenic Institute of Transport (HIT) – CERTH

          The Hellenic Institute of Transport: Presentation of activities and expertise

2.20 conclusion
2.30-3.30 working lunch break
3.30 Session 3
3.30-3.50: MSc Brochure (specifications)
3.50-5.00: Final Web Site Corrections and Completion
5.00 coffee break
5.20 Session 4
5.20-6.30: Application form (in agreement with all Universities)
9.00 Dinner downtown
Friday 21/9
9.30 Session 5
9.30-11.30: Students selection-evaluation (administration procedure)
11.30 coffee break
12.00 Session 6
12.00-2.00: AOB

Page 2 of 7