Researchers Rank Recommendation Algorithms Using Sports Tournament Model
Researchers from the AI and Digital Science Institute at the HSE Faculty of Computer Science have developed an approach for selecting recommendation algorithms more effectively. Their approach uses pairwise comparisons of algorithms to create a tournament table, with the overall ranking based on their performance across all datasets in the tournament. This can reduce the number of algorithms that need to be tested when developing new services, saving both time and money. The study was presented at the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2026).
Recommendation systems determine which products, films, songs, or publications to show users. To do this, they analyse users’ past behaviour and predict what they might be interested in next. For example, recommendation systems identify users with similar interests and take into account the sequence of their views or purchases.
However, there is no universal recommendation algorithm. A method that works well for an online store may not be suitable for an online cinema. Therefore, algorithms are usually pre-tested on existing datasets, and their performance is averaged across them. This approach, however, has its limitations: the resulting ranking does not account for the specifics of individual datasets and may be unstable, while testing all algorithms online with real users is costly and risky.
Researchers at HSE University have developed a methodology for comparing recommendation algorithms based on the Bradley–Terry model, which is used to rank competitors based on the outcomes of pairwise ‘matches.’ In this study, the recommendation algorithms were the ‘players,’ while the ‘matches’ were tests of the algorithms on different datasets. Two algorithms were compared using a selected metric, such as recommendation accuracy, and the one with the higher score was declared the winner. Based on the results of all pairwise comparisons, the model estimated the relative strength of each algorithm. The researchers trained and tested 14 algorithms on 89 datasets from different fields.
The results showed that the same algorithms could occupy different positions in the ranking depending on the type of data used in the ‘matches.’ For example, on sequential datasets, where the order of user actions is important, SASRec and GASATF ranked as the top performers. However, when a dataset did not contain an explicit sequence, these algorithms dropped to tenth and eleventh place, respectively, while LightGCN and ALS topped the ranking.
Additionally, the researchers tested the robustness of the rankings to incomplete data. The ranking produced by the Bradley–Terry model remained stable even when some comparisons were missing, meaning that not every algorithm was compared with every other algorithm. The authors also tested an extended version of the model on additional datasets, taking the context into account. In this case, the model had to predict the winners without directly comparing the recommendation algorithms.
'The idea of using a sports model came to us thanks to the work of our senior colleague Vladimir Spokoiny. To draw an analogy with a sports tournament, the outcome of a match is influenced not only by the players themselves but also by conditions such as the city or the weather. In our study, the characteristics of the dataset served as this context, including the number of users and items, the average length of users’ histories, and other parameters. If we train the model to take this context into account alongside the results of previous comparisons, it can use the characteristics of a new dataset to predict in advance which algorithms are likely to perform best,' says co-author Anton Lysenko, Expert at the International Laboratory of Stochastic Algorithms and High-Dimensional Inference.
In 78% of cases, the algorithm ranked first by the model was indeed among the top three. With the conventional approach of averaging performance metrics, this was the case in only 16% of cases. The authors attribute this difference to the fact that, unlike heuristic comparison methods, their model has a sound theoretical foundation, making the resulting rankings more reliable.
'Our approach helps identify which algorithms are best suited to a particular dataset before they are tested online. For example, if a bank needs to recommend loyalty programmes, it can feed the characteristics of a new dataset into the model to identify the most promising algorithms. Only these algorithms would then need to be tested on real users, rather than all available options. This saves both time and resources,' says co-author Sergey Samsonov, Head of the International Laboratory of Stochastic Algorithms and High-Dimensional Inference.
The study was carried out as part of a programme implemented by the HSE AI Research Centre and supported by a grant from the Ministry of Economic Development of the Russian Federation.
See also:
HSE University to Launch 11 Projects with Research Centres from Five Countries
HSE University has announced the results of its International Academic Cooperation (IAC) competition for joint fundamental research projects. Five projects have received full funding, while six more have been awarded partial funding. The research teams include scholars from Brazil, South Africa, China, India, and Oman. Alexander Balyshev, HSE University Vice President, shared details of the 2026 IAC competition winners.
Window into the Body: Scientists Develop Neural Network to Detect Risk of 15 Diseases from Retinal Images
Russian universities, with the participation of HSE University, Sber, and Z-union, have developed a neural network that can simultaneously assess the risk of 15 types of pathology from retinal photographs, including not only eye diseases but also cardiovascular conditions. The AI system can help clinicians detect potentially concerning changes at an early stage, identify signs reflecting the condition of retinal blood vessels, and determine whether a patient may need further examination. The paper has been published in Frontiers in Medicine.
HSE Researchers Show How Congenital Motor Disorders Affect Brain Development
Researchers from HSE University’s Institute for Cognitive Neuroscience have synthesised the findings of their previous studies on brain development in children with obstetric brachial plexus palsy and arthrogryposis. Their analysis shows that impaired motor function in early childhood not only limits children’s motor experience but also affects memory, categorical thinking, and information processing. The study has been published in Frontiers in Psychology.
AI Users Earn Up to 41.8% More Than Non-Users
Research conducted by economists at HSE University has revealed a significant correlation between the regular use of GenAI in the workplace and higher pay among Russian employees. The study found that individuals who frequently use GenAI in their professional activities earn notably more than those who reject these new tools or resort to them occasionally. The salary premium for highly qualified specialists reaches 41.8%. The article was published in the Voprosy Ekonomiki journal.
AI Robot for Environmental Recognition Tested at HSE University
Engineers and researchers at the HSE Institute for Robotics Systems have successfully run the first tests of an AI-powered environmental recognition model deployed on a robot dog. The robot navigated around the HSE Pokrovka building and Pokrovsky Bulvar, analysing the surrounding environment to identify its location.
Personal Interest in Doctoral Thesis Topic Most Important for Confidence in Successful Defence
A researcher at HSE University analysed data on 1,539 doctoral students from 161 Russian universities to identify which features of a thesis topic are associated with academic success and engagement. The most important factor was found to be personal interest in the research topic, which was associated with almost all key aspects of doctoral programme experience—from engaging with the academic supervisor to research activity and confidence about successfully defending the thesis. The findings have been published in Higher Education.
Algebra, Geometry, and AI: Russian and Vietnamese Mathematicians Discuss Current Research
A delegation of scientists from Hanoi visited the HSE Faculty of Computer Science and then took part in a Russian-Vietnamese conference in St Petersburg. The events were part of the three-year project ‘Flexibility and Computational Methods.’ Over the course of the project, the researchers have prepared joint publications and obtained new mathematical results.
Researchers Develop Methodology to Assess the Quality of Legal Representation in Criminal Proceedings
Having a good defence attorney in criminal proceedings can largely determine whether a defendant retains their freedom, health and good name. Researchers at HSE University propose a method for predicting an attorney’s performance based on the outcomes of their previous cases. The methodology takes into account the severity of the charges, the complexity of the cases, and the most likely outcome, drawing on judicial statistics.
When Pictures Hinder Understanding: Illustrations May Impede Learning of Abstract Ideas
Illustrations can help remember specific actions but do not always make abstract ideas easier to learn. Researchers from HSE University and Humboldt University compared how people learn from texts with different levels of abstractness. They found that participants remembered illustrations better and performed better on related tasks after reading a multimedia text about yoga asanas than after reading an abstract text about the Nash equilibrium. The findings could help improve the selection of illustrations for educational and informational materials. The study has been published in Learning and Instruction.
HSE Researchers Present Study on Neural Network Robustness in Video Analysis at ChinaMM 2026
Researchers from HSE University presented a study at the international ChinaMM 2026 conference on how video transmission distortions affect the performance of neural networks. The authors proposed a new approach to testing the robustness of such models under conditions that closely resemble the real-world use of video services.