Final Year Data Science Projects 2025/26
This academic year, I am offering a range of final-year projects for MSc Data Science students at King’s College London. The topics are motivated by current research in urban computing and data governance.
Recent Posts
Automating Data Governance with Generative AI
Organizations now manage complex data systems, and meeting privacy laws such as the GDPR has become both vital and expensive. We examined how large language models (LLMs) can support data governance by generating warnings about data access decisions in decentralized data systems.
The Experience of Running: Recommending Routes Using Sensory Mapping in Urban Environments
Most apps that have a running route recommendation feature suggest routes based on distance, surface, elevation, and popularity, disregarding other factors that influence the psychological experience of running
Understanding the Influence of Data Characteristics on the Performance of Point-of-Interest Recommendation Algorithms
Point-of-interest (POI) recommendations are essential for travelers and the e-tourism business. They assist in decision-making regarding what venues to visit and where to dine and stay. While it is known that traditional recommendation algorithms’ performance depends on data characteristics like sparsity, popularity bias, and preference distributions, the impact of these data characteristics has not been systematically studied in the POI recommendation domain. To fill this gap, we extend a pr...
First Workshop on Urban Recommender Systems
As we witness an ongoing centralization of the population towards urban landscapes, recommendation technology has an increasing role in people’s perception and decision-making in cities. People use recommender systems for choosing places to stay, which attractions and restaurants to visit, and route recommender systems for navigation. This workshop aims to bring together practitioners and academics working on improving recommendations in the urban space with an emphasis on both individual nee...
Data-driven Destination Recommender Systems
This thesis explores various aspects of the destination recommendation domain, namely mobility analyses about which types of travelers can be observed in location-based social media data, how these groups perform in point-of-interest recommendation, how long travelers should stay at a destination, and which data sources are suitable to characterize destinations. Finally, we propose a city recommender system that supports users making the trade-offs involved in their travel choices.
Travelers vs. Locals: The Effect of Cluster Analysis in Point-of-Interest Recommendation
The involvement of geographic information differentiates point-of-interest recommendation from traditional product recommendation. This geographic influence is usually manifested in the effect of users tending toward visiting nearby locations, but further mobility patterns can be used to model different groups of users.
A Comparative Study of Data-Driven Models for Travel Destination Characterization
To evaluate which data sources are most suitable to characterize destinations, we investigate 18 characterization methods that fall into the following categories: venue data, textual data, and factual data.
Navigation by Revealing Trade-offs for Content-based Recommendations
Tourism is a complex domain for recommender systems because of the high cost of recommending an unsuitable item and the absence of ratings to learn user preferences.
Mining Trips from Location-based Social Networks for Clustering Travelers and Destinations
This is the first major publication of my dissertation project, which extends and combines previous work on the analysis of traveler mobility.
Designing a Conversational Travel Recommender System Based on Data-driven Destination Characterization
Recommending complex, intangible items in a domain with high consequences, such as destinations for traveling, requires additional care when deriving and confronting the users with recommendations.
How Long to Stay Where? On the Amount of Item Consumption in Travel Recommendation
Recommender systems could benefit from not only recommending the most fitting items but also in what quantity the user should consume them.
Survey on Feature Usage in JabRef
If you are using JabRef as your bibliography manager, please consider participating in a user survey about yur usage of JabRef’s features.
Seminar on Current Topics in Recommender Systems
Together with Wolfgang Wörndl and Daniel Herzog I will be teaching a seminar on ‘Current Topics in Recommender Systems’ next semester.
Java by Comparison
I am very happy to announce the release of ‘Java by Comparison’ by Simon Harrer, Jörg Lenhard and myself published at the Pragmatic Bookshelf.
Hello world, reloaded!
After a technical downtime of shutting down my old server last December, I have finally set up a new homepage again.