Research projects in DABILab

SCVis Logo
European Fashion Retail Supply Chain Visibility Training Resource

Funded by Erasmus+ Key Action 2.

Coordinator: University of Gloucester, UK

Duration: 1/11/2017 to 30/10/2019.
Budget: 250.000€

Scientific coordinator for IHU: Dr George Stalidis, Professor

The aim of the project is to create a web-based tool and the related learning material, capable of detecting knowledge gaps and providing easily accessible resources to trainees who are oriented towards the strengthening of their careers.

More information and related publications in the SCVis project webpage
Data Analysis and Knowledge Management Technologies for Planning Tourism Products

Funded by the program Archimides III

Implementation: Lab of Data Analysis and Multimedia Applications, Department of Marketing, ATEITh

Research field: Intelligent Systems
Duration: 1/4/2012 to 31/3/2015
Budget: 75.000€

Scientific coordinator:
Dr George Stalidis (from 9/2014 to end)
Prof Dimitrios Karapistolis (from start to 31/8/2014 )

In DANKMAN, advanced Data Analysis and Knowledge Modeling methods are applied to support the management of touristic destinations. The development and implementation of the methods is based on edge information technologies, more specifically on the combination of multidimensional factor analysis software, neural networks and knowledge management systems, as well as modern web application tools.

More information and related publications in the DANKMAN project webpage

Participation in Research projects through collaboration with other labs



Funded by the Greek National Programme «ΕΡΕΥΝΩ-ΔΗΜΙΟΥΡΓΩ-ΚΑΙΝΟΤΟΜΩ»

Implementing organisation: ArxNet

Scientific coordination: Ιntelligent Systems Laboratory, Department of Information and Electronic Engineering

Scientific Coordinator: Prof Konstantinos Diamantaras

Participating member of DABILab: Dr George Stalidis

Budget: 130.000 €
Duration: 7/2018 – 7/2021

Recommender Systems are a rapidly evolving field in the area of information extraction from data, offering solutions to important marketing and advertising problems e.g. finding new products that a customer will like, based on the preferences of other customers with similar characteristics, friends or members of a common group.

The project aims are in two categories, research and commercial. The research aims include industrial research in parallel and distributed implementation of a parametrizable recommender system which will cover the needs of enterprises with Big Data. Commercial aims include the development of a novel software package which will apply the results of industrial research, as well as the application, testing and promotion of the product

Contribution of DABILab (Researcher: G. Stalidis)

  • Application of Multidimensional Factor Analysis methods in the explorative analysis of purchase history and the prediction of future buys of super market customers, in order to send them smart personalised offers through mobile apps  
  • Contribution in the development of business scenaria for the exploitation of personalised recommendation systems.

Related publications

Stalidis, G., Siomos T., Kaplanoglou, P., Katsalis, A., Karaveli, I., Delianidi, M. and Diamantaras K. (2020). Multidimensional Factor and Cluster analysis vs embedding-based learning for personalized supermarket offer recommendations. In “Studies in Classification, Data Analysis, and Knowledge Organization” Eds T. Chadjipadelis, B. Lausen, A. Markos, T. R. Lee, A. Montanari and R. Nugent, pp 273-281. Springer, Cham. .

Stalidis G., Delianidi M., Christantonis K., Kaplanoglou P. I., Karaveli I., Katsalis A., Siomos T., Salampasis M. and Diamantaras K. (2020), “Personalised offer recommendations in retail combining factor and cluster analysis, neural networks and graph databases”, 8th International Conference on Contemporary Marketing Issues, Virtual, 11-13 September,  Proc pp 269-271

Stalidis G., Kaplanoglou P., Diamantaras K. (2019), “Multidimensional data analysis of shopping records towards knowledge-based recommendation techniques”, 16th Conf of the International Federation of Classification Societies, 26-29 Aug 2019, Thessaloniki.

Stalidis G., Diamantaras K. (2019), “Offers just for you: intelligent recommendation of personalised offers employing multidimensional statistical models”, 7th International Conference on Contemporary Marketing Issues, 10-12 July, Heraklion, Proc pp 328-330.


Intelligent platform for digital multichannel marketing with dynamic path learning and knowledge engineering  (TREELYTICS)

Funded by the Greek national programme “ΕΡΕΥΝΩ – ΔΗΜΙΟΥΡΓΩ – ΚΑΙΝΟΤΟΜΩ (ΕΣΠΑ)”

Implementing Organisation: MyCompany Projects

Scientific coordination: Systems, Networks and Security Research Laboratory, IHU.

Scientific coordinator: Prof Periklis Chatzimisios 

Vice scientific coordinator: Dr. George Stalidis

Duration: 2/2020 – 8/2022

This project aims to develop a sophisticated artificial intelligence unit that can be integrated into existing digital marketing, eCommerce, and customer relationship management (CRM) platforms, providing enhanced customer behavior forecasting capabilities and creation of personalized recommendations. Treelytics focuses on (a) learning the potential dynamic behavior of potential customers to achieve time-series predictions, enhancing forecasting accuracy and increasing performance in event marketing and next best action applications. (b) the integration of methods of machine learning and modeling of knowledge, so that it is possible to adapt to business policies and to integrate specialized research knowledge. The unit will be based on both reinforcing deep learning technologies, using predictive model analytics in real-time by using continuous machine learning methods, as well as on a complex knowledge model and a computerized inference engine and knowledge base using Linked Data technologies.

Contribution of DABILab  

Contribution in modeling and management of knowledge and in the development of the Knowledge Base