Emanuel Lacic

TagRec: towards a standardized tag recommender benchmarking framework

In this paper, we introduce TagRec, a standardized tag recommender benchmarking framework implemented in Java. The purpose of TagRec is to provide researchers with a framework that supports all steps of the development process of a new tag recommendation algorithm in a reproducible way, including methods for data pre-processing, data modeling, data analysis and recommender evaluation against state-of-the-art baseline approaches. We show the performance of the algorithms implemented in TagRec in terms of prediction quality and runtime using an evaluation of a real-world folksonomy dataset. Furthermore, TagRec contains two novel tag recommendation approaches based on models derived from human cognition and human memory theories.

Utilizing Online Social Network and Location-Based Data to Recommend Products and Categories in Online Marketplaces

Recent research has unveiled the importance of online social networks for improving the quality of recommender systems and encouraged the research community to investigate better ways of exploiting the social information for recommendations. To contribute to this sparse field of research, in this paper we exploit users’ interactions along three data sources (marketplace, social network and location-based) to assess their performance in a barely studied domain: recommending products and domains of interests (i.e., product categories) to people in an online marketplace environment. To that end we defined sets of content- and network-based user similarity features for each data source and studied them isolated using an user-based Collaborative Filtering (CF) approach and in combination via a hybrid recommender algorithm, to assess which one provides the best recommendation performance. Interestingly, in our experiments conducted on a rich dataset collected from SecondLife, a popular online virtual world, we found that recommenders relying on user similarity features obtained from the social network data clearly yielded the best results in terms of accuracy in case of predicting products, whereas the features obtained from the marketplace and location-based data sources also obtained very good results in case of predicting categories. This finding indicates that all three types of data sources are important and should be taken into account depending on the level of specialization of the recommendation task.

TagRec: towards a toolkit for reproducible evaluation and development of tag-based recommender algorithms

This article presents TagRec, a framework to foster reproducible evaluation and development of recommender algorithms based on folksonomy data. The purpose of TagRec is to provide the research community with a standardised framework that supports all steps of the development process and the evaluation of tag-based recommendation algorithms in a reproducible way, including methods for data pre-processing, data modeling and recommender evaluation. TagRec currently contains 32 state-of-the-art algorithms for tag and item prediction, including a set of novel and very efficient algorithms based on the human cognition theories ACT-R and MINERVA2. The framework should be relevant for researchers, teachers, students and developers working on recommender systems and predictive modeling in general and those interested in tag-based recommender algorithms in particular.

Towards a scalable social recommender engine for online marketplaces: the case of apache solr

Recent research has unveiled the importance of online social networks for improving the quality of recommenders in several domains, what has encouraged the research community to investigate ways to better exploit the social information for recommendations. However, there is a lack of work that offers details of frameworks that allow an easy integration of social data with traditional recommendation algorithms in order to yield a straight-forward and scalable implementation of new and existing systems. Furthermore, it is rare to find details of performance evaluations of recommender systems such as hardware and software specifications or benchmarking results of server loading tests. In this paper we intend to bridge this gap by presenting the details of a social recommender engine for online marketplaces built upon the well-known search engine Apache Solr. We describe our architecture and also share implementation details to facilitate the re-use of our approach by people implementing recommender systems. In addition, we evaluate our framework from two perspectives: (a) recommendation algorithms and data sources, and (b) system performance under server stress tests. Using a dataset from the SecondLife virtual world that has both trading and social interactions, we contribute to research in social recommenders by showing how certain social features allow to improve recommendations in online marketplaces. On the platform implementation side, our evaluation results can serve as a baseline to people searching for performance references in terms of scalability, model training and testing trade-offs, real-time server performance and the impact of model updates in a production system.

SocRecM: a scalable social recommender engine for online marketplaces

This paper presents work-in-progress on SocRecM, a novel social recommendation framework for online marketplaces. We demonstrate that SocRecM is easy to integrate with existing Web technologies through a RESTful, scalable and easy-to-extend service-based architecture. Moreover, we reveal the extent to which various social features and recommendation approaches are useful in an online social marketplace environment.

The social semantic server: a flexible framework to support informal learning at the workplace

Informal learning at the workplace includes a multitude of processes. Respective activities can be categorized into multiple perspectives on informal learning, such as reflection, sensemaking, help seeking and maturing of collective knowledge. Each perspective raises requirements with respect to the technical support, this is why an integrated solution relying on social, adaptive and semantic technologies is needed. In this paper, we present the Social Semantic Server, an extensible, open-source application server that equips client-side tools with services to support and scale informal learning at the workplace. More specifically, the Social Semantic Server semantically enriches social data that is created at the workplace in the context of user-to-user or user-artifact interactions. This enriched data can then in turn be exploited in informal learning scenarios to, e.g., foster help seeking by recommending collaborators, resources, or experts. Following the design-based research paradigm, the Social Semantic Server has been implemented based on design principles, which were derived from theories such as Distributed Cognition and Meaning Making. We illustrate the applicability and efficacy of the Social Semantic Server in the light of three real-world applications that have been developed using its social semantic services. Furthermore, we report preliminary results of two user studies that have been carried out recently.

Smart booking without looking: providing hotel recommendations in the TripRebel portal

In this paper, we present a scalable hotel recommender system for TripRebel, a new online booking portal. On the basis of the open-source enterprise search platform Apache Solr, we developed a system architecture with Web-based services to interact with indexed data at large scale as well as to provide hotel recommendations using various state-of-the-art recommender algorithms. We demonstrate the efficiency of our system directly using the live TripRebel portal where, in its current state, hotel alternatives for a given hotel are calculated based on data gathered from the Expedia Affiliate Network (EAN).

Trust-based collaborative filtering: tackling the cold start problem using regular equivalence.

User-based Collaborative Filtering (CF) is one of the most popular approaches to create recommender systems. This approach is based on finding the most relevant k users from whose rating history we can extract items to recommend. CF, however, suffers from data sparsity and the cold-start problem since users often rate only a small fraction of available items. One solution is to incorporate additional information into the recommendation process such as explicit trust scores that are assigned by users to others or implicit trust relationships that result from social connections between users. Such relationships typically form a very sparse trust network, which can be utilized to generate recommendations for users based on people they trust. In our work, we explore the use of regular equivalence applied to a trust network to generate a similarity matrix that is used to select the k-nearest neighbors for recommending items. We evaluate our approach on Epinions and we find that we can outperform related methods for tackling cold-start users in terms of recommendation accuracy.

Gone in 30 days! Predictions for car import planning

Abstract A challenge for importers in the automobile industry is adjusting to rapidly changing market demands. In this work, we describe a practical study of car import planning based on the monthly car registrations in Austria. We model the task as a data driven forecasting problem and we implement four different prediction approaches. One utilizes a seasonal ARIMA model, while the other is based on LSTM-RNN and both compared to a linear and seasonal baselines. In our experiments, we evaluate the 33 different brands by predicting the number of registrations for the next month and for the year to come.

Real-time recommendations in a multi-domain environment by Emanuel Lacic with Prateek Jain as coordinator

Emanuel Lacić is a Software Engineer and Scientific Researcher in the Social Computing division at the Know-Center. Additionally, he is a PhD student at the Interactive Systems & Data Science Institute of Graz University of Technology. He has a M.Sc. and B.Sc. in Software Engineering and Information Systems from the Faculty of Electrical Engineering and Computing at the University of Zagreb. His PhD focus is on real-time recommender systems in large-scale settings. Apart from that, his research is utilized in several industry and European-funded projects such as Learning Layers, AFEL or MoreGrasp. His main research interests are in the fields of Recommender Systems, Deep Learning, Information Retrieval, Big Data, as well as Social and Complex Network Analysis. For more information please see https://lacic.github.io/