Scientists Develop Algorithm for Accurate Financial Time Series Forecasting
Researchers at the HSE Faculty of Computer Science benchmarked more than 200,000 model configurations for predicting financial asset prices and realised volatility, showing that performance can be improved by filtering out noise at specific frequencies in advance. This technique increased accuracy in 65% of cases. The authors also developed their own algorithm, which achieves accuracy comparable to that of the best models while requiring less computational power. The study has been published in Applied Soft Computing.
Financial time series are sequences of values that change over time, such as stock prices or their volatility (which reflects how much these prices fluctuate). Such data is difficult to predict, being influenced by many factors, such as news, investor behaviour, technological changes, and random events. These influences often overlap, making patterns in the data unstable. As a result, forecasting models either require extensive customisation for specific cases or produce results that are not applicable in practice.
Researchers at the HSE FCS Laboratory for Models and Methods of Computational Pragmatics propose using wavelet transformations to improve the accuracy of financial time series forecasting. Wavelet transformations represent a time series as a sum of components at different levels of detail, allowing noise at various scales to be filtered out.
To validate their approach, the researchers used real-world data on 89 financial assets, including company stocks and cryptocurrencies. The dataset comprised time series of average daily prices and realised volatility calculated from five-minute interval data. The assets were then grouped into clusters, after which the leading assets in each cluster were selected. The authors used this data to compare different forecasting approaches, including classical econometric models, machine learning methods, neural networks, and their own algorithm, the Triple Correction Method. In total, they tested 200,000 model configurations.
The authors’ novel algorithm showed strong performance. Unlike classical models, it does not rely on predefined parameters; instead, it updates them at each forecasting step while simultaneously accounting for multiple types of fluctuations in the data. As a result, the method adapts more effectively to market changes. It ranked second in performance for average daily prices, slightly trailing the naïve forecast under the overall Copeland ranked-choice method, while outperforming other methods in terms of absolute values. For the volatility series, the results were less clear-cut; however, when combined with wavelet transformations, the method often produced forecasts that were the best or close to the best. At the same time, it remained computationally simpler than many alternatives and did not require complex parameter tuning.
Vyacheslav Manevich
'Although the Triple Correction Method does not always produce the best result for each individual series, it consistently delivers strong forecasts in most cases—something that is often lacking in practice. Highly specialised models may perform better, but they tend to lose their effectiveness quickly when conditions change,' comments co-author of the study Vyacheslav Manevich, Research Fellow at the HSE Laboratory for Models and Methods of Computational Pragmatics.
Experiments show that wavelet transformations improve predictions in more than 65% of cases. Unlike, for example, the Fourier transform, they allow both the time and frequency of a signal to be considered simultaneously. As a result, the model is provided with more refined data and can capture patterns more accurately. At the same time, the effect depends on the type of data: for stock prices, the transformations help identify trends against the background of market noise, while for volatility they better capture sharp, irregular changes, which tend to make forecasting particularly challenging.
The authors emphasise that even small improvements in accuracy achieved with such methods can lead to significant increases in profit, especially in high-turnover settings. In the future, the researchers plan to investigate how to automatically select optimal wavelet transformations and how to extend the method to multi-step forecasting, for example in business, energy, or medical applications, where it is important to predict not only the next step but also longer-term changes.
The study was conducted with support from HSE University's Basic Research Programme.
See also:
Neural Network Maps as a Method for Constructing Mathematical Models
Scientists from HSE University–Nizhny Novgorod and the Institute of Physics Belgrade, Serbia, are jointly exploring the application of machine learning techniques and neural networks to the study of nonlinear dynamics. Natalya Stankevich, Leading Research Fellow at the Laboratory of Topological Methods in Dynamics of the Faculty of Informatics, Mathematics, and Computer Science at HSE University–Nizhny Novgorod, spoke to the HSE News Service about this international project.
HSE Scientists Develop Method to Compress Large Language Models Without Losing Quality
Researchers from the AI and Digital Science Institute at the HSE Faculty of Computer Science have developed a new compression method for large language models such as GPT and LLaMA that reduces their size by 25–36% without additional training or significant loss of accuracy. This is the first approach to use mathematical transformations—specifically, rotations of model weights—to make models more amenable to compression with structured matrices. The study results have been published in ACL Findings 2025. The code is available on GitHub.
Machine Learning Models Can Help Reduce Volatility and Boost Stock Market Returns
The use of machine learning models makes it possible to achieve greater accuracy in predicting risks in the Russian stock market compared to classical econometric approaches. The predictive power of these models increases by 23%, while the average investor’s return can reach up to 13% per annum. These conclusions were drawn by Nikita Lysenok from the Department of Financial Market Infrastructure at the HSE Faculty of Economic Sciences. The paper has been published in Fundamental and Applied Mathematics.
Pocket Money, Personal Interest, and Family Practices: What Shapes Students’ Economic Literacy?
University students' economic literacy depends not only on their field of study but also on their interest in economics, the learning environment, and family financial practices. For example, students who received pocket money irregularly tend to perform better on economic literacy tests than their peers who received financial support on a regular basis. These findings come from a study conducted by HSE University involving more than 1,100 students from five Russian universities. The findings have been published in Cakrawala Pendidikan.
HSE Study Reveals Imbalance in the Generative AI Market
Researchers at HSE University analysed how effectively the global generative artificial intelligence market converts investment into real revenue, concluding that AI is currently developing faster than it is paying off. The results have been published in the journal Foresight and STI Governance.
HSE Scientists Train Neural Network to 'Hear' Faults in Electric Motors
Researchers at the AI and Digital Science Institute of the HSE Faculty of Computer Science have developed a new method—the Signature-Guided Data Augmentation (SGDA) framework—that achieves 99% accuracy in motor fault detection and 86% accuracy in fault classification. The application of this approach can reduce industrial equipment repair costs, minimise downtime, and improve production safety. The study results have been published in Engineering Applications of Artificial Intelligence.
The 'Second Shift' Is Not Why Women Avoid News
Women are more likely than men to avoid political and economic news, but the reasons for this behaviour are linked less to structural inequality or family-related stress than to personal attitudes and the emotional perception of news content. This conclusion was reached by HSE researchers after analysing data from a large-scale survey of more than 10,000 residents across 61 regions of Russia. The study findings have been published in Woman in Russian Society.
Resource Race and Green Transition: Three Unexpected Conclusions from Foresight Centre’s Research on Climate and Poverty
Beneath the surface of green energy—which most people associate with solar panels, electric vehicles, and reduced CO2 emissions—lies a complex web of geopolitical interests, international inequality, and resource constraints. Researchers from the Laboratory for Science and Technology Studies (LST) at the HSE ISSEK Foresight Centre have published a series of articles in leading international journals on hidden and overt conflicts surrounding critically important metals and minerals, as well as related processes in the energy sector.
Immersion in Second Language Environment Influences Bilinguals’ Perception of Emotions
Researchers at the Cognitive Health and Intelligence Centre at the HSE Institute for Cognitive Neuroscience have discovered how bilingual individuals process emotional words in their native (first) and non-native (second) languages. It was found that the link between word meaning and bodily sensations is weaker in a second language than in a first language. However, the more a person is immersed in a language environment, the smaller this difference becomes. The article has been published in Language, Cognition and Neuroscience.
Researchers Find More Effective Approach to Revealing Majorana Zero Modes in Superconductors
An international team of researchers, including physicists from HSE MIEM, has demonstrated that nonmagnetic impurities can help more accurately reveal Majorana zero modes—quantum states considered promising building blocks for quantum computing. The researchers found that these impurities shift the energy levels that typically obscure the Majorana signal, while leaving the mode itself largely unaffected, thereby making its spectral peak more distinct. The study has been published in Research.