HSE Researchers Demonstrate Effectiveness of Machine Learning in Forecasting Inflation
Inflation is a key indicator of economic stability, and being able to accurately forecast its levels across regions is crucial for governments, businesses, and households. Tatiana Bukina and Dmitry Kashin at HSE Campus in Perm have found that machine learning techniques outperform traditional econometric models in long-term inflation forecasting. The results of the study focused on several regions in the Privolzhskiy Federal District have been published in HSE Economic Journal.
Inflation forecasting is crucial for the economy, particularly since Russia's transition to an inflation targeting regime in 2014. This means that the Bank of Russia sets specific inflation targets and employs a range of tools to meet them.
Various data is used to predict inflation, including the consumer price index, the unemployment rate, exchange rates, and the Central Bank rate. To systematise this information for forecasting, economists at the HSE Campus in Perm used data from the Unified Interdepartmental Statistical Information System.
The researchers' main objective was to determine which model predicts regional inflation more accurately: traditional econometric time series models or more recent machine learning methods. The study analysed data from 14 regions in the Privolzhskiy Federal District from January 2010 to December 2022. R Studio and Python were used for the analysis: time series forecasting was performed in R Studio, while machine learning models, including support vector machines, gradient boosting, and random forests, were implemented in Python. The forecasts were conducted on test samples, which helped prevent model overfitting and provided more accurate estimates.
The authors employed a cross-validation method using test samples of equal size. This approach allows models to be trained on data from one period and tested on data from another, ensuring stability and accuracy of the forecasts.
'To ensure accurate performance of machine learning methods, it is essential to select the optimal hyperparameters for the models. Hyperparameters differ from other model parameters in that they are set before training begins and define the model's specifications. Cross-validation is employed to select the optimal hyperparameters. When cross-validating time series, the training data precedes the test data without overlap, unlike in standard data validation,' according to Tatiana Bukina, Associate Professor, Faculty of Computer Science, Economics, and Social Sciences, HSE Campus in Perm.
The study found the gradient boosting model to be the most accurate of all machine learning models considered for predicting regional inflation. It delivers more accurate forecasts than autoregressive models over more time horizons. Thus, at forecasting horizons of 3, 6, 21, and 24 months, the gradient boosting model outperforms the basic AR(1) model by 20.3%, 16.2%, 72.5%, and 77.7%, respectively. The AR(1) model, a statistical tool for analysing and predicting time series, assumes that the current value of a series depends on its previous value plus a random error.
The random forest model and the support vector machine also demonstrated accurate forecasts over the long horizons of 21 and 24 months, outperforming the AR(1) model by 72.5% and 77.7%, respectively. A random forest combines multiple decision trees to enhance the accuracy and stability of forecasts, and then uses regression to average the predictions or select the most frequent value. The support vector machine identifies the optimal line that separates the data while minimising classification errors.
![](/mirror/pubs/share/direct/947095882.jpg)
According to the authors, their results confirm that machine learning methods can be effective for forecasting inflation across various time horizons.
Tatiana Bukina notes, 'Our research has demonstrated that machine learning provides more reliable tools for long-term forecasts. However, traditional econometric models continue to play a crucial role in short-term forecasts and should not be entirely excluded from analysts' toolkits. Combining econometric modelling with machine learning methods can significantly improve the accuracy of regional inflation forecasts. This is particularly important in an environment characterised by high uncertainty and rapid changes in economic conditions.'
The study also highlighted the specific characteristics of inflation forecasting for different regions. For example, in machine learning models, inflation seasonality was observed only in the Perm, Nizhny Novgorod, Penza, and Saratov regions. In the Republic of Tatarstan, the specific month for which the forecast was calculated proved to be a significant factor.
In the random forest model, the average inflation value for the previous three months emerged as a significant factor for the Republic of Mordovia, Nizhny Novgorod and Ulyanovsk regions, and the Chuvash Republic.
Each region has unique characteristics related to its economic structure, natural resources, and geographical location. These factors account for the variations in inflation dynamics and key macroeconomic indicators.
See also:
Scientists Identify Fifteen Key Motives Driving Human Behaviour
Researchers at HSE University and the London School of Hygiene and Tropical Medicine have identified 15 key motives that drive human behaviour. By analysing people's views, preferences, and actions through an evolutionary lens, they demonstrated how these motives intertwine to shape habits and interpersonal relationships. The findings have been published in Personality and Individual Differences.
HSE Neurolinguists Create Russian Adaptation of Classic Verbal Memory Test
Researchers at the HSE Centre for Language and Brain and Psychiatric Hospital No. 1 Named after N.A. Alexeev have developed a Russian-language adaptation of the Rey Auditory Verbal Learning Test. This classic neuropsychological test evaluates various aspects of auditory verbal memory in adults and is widely used in both clinical diagnostics and research. The study findings have been published in The Clinical Neuropsychologist.
Tickling the Nerves: Why Crime Content is Popular
Consumers of content about serial killers watch and read it to experience intense emotions that are often lacking in everyday life and to understand the reasons that drive people to commit crimes. However, such content does not contribute to increased aggression. These conclusions were drawn by sociologists from HSE University. The results of their study have been published in Crime, Media, Culture: An International Journal.
HSE Researchers Prove the Existence of Nash Equilibrium for a New Class of Problems in Game Theory
Researchers at HSE University's St Petersburg School of Economics and Management have been exploring methods for the efficient allocation of resources in systems involving multiple players. The scientists have proven the existence of strategies for optimal decision-making in competition for limited, discrete resources in four different cases. The developed mathematical model can be applied in various fields, ranging from education and medicine to managing networks and computing power. The paper has been published in Games and Economic Behaviour.
Researchers at HSE Centre for Language and Brain Reveal Key Factors Determining Language Recovery in Patients After Brain Tumour Resection
Alina Minnigulova and Maria Khudyakova at the HSE Centre for Language and Brain have presented the latest research findings on the linguistic and neural mechanisms of language impairments and their progression in patients following neurosurgery. The scientists shared insights gained from over five years of research on the dynamics of language impairment and recovery.
Neuroscientists Reveal Anna Karenina Principle in Brain's Response to Persuasion
A team of researchers at HSE University investigated the neural mechanisms involved in how the brain processes persuasive messages. Using functional MRI, the researchers recorded how the participants' brains reacted to expert arguments about the harmful health effects of sugar consumption. The findings revealed that all unpersuaded individuals' brains responded to the messages in a similar manner, whereas each persuaded individual produced a unique neural response. This suggests that successful persuasive messages influence opinions in a highly individual manner, appearing to find a unique key to each person's brain. The study findings have been published in PNAS.
Russian Scientists Improve Water Purification Membranes Using Metal Ions
Researchers have proposed using polymer membranes modified with copper, zinc, and chromium metal ions for water purification. These polymers were used for the first time in water purification via electrodialysis. Copper-based membranes demonstrated record selectivity for monovalent ions, opening new possibilities for sustainable water recycling. The study has been published in the Journal of Membrane Science.
Independent Experts More Effective Than Collective Expertise in Decision-Making Under Uncertainty
A collaborative study by Sergey Stepanov, Associate Professor at the HSE Faculty of Economic Sciences, and experts from INSEAD Business School and NYU Shanghai, indicates that in making decisions under high uncertainty, where it is unclear which choice is superior, advice from independent experts may be more beneficial than a collective opinion from a group of experts. The study has been published in Games and Economic Behavior.
HSE Researchers Uncover Causes of Gender Pay Gap among Recent University Graduates in Russia
A study conducted at HSE University shows that despite having the same education and similar starting conditions, the pay gap between male and female recent graduates can be as high as 22%. This is partly because female students often choose less lucrative fields and also because they tend to seek jobs in sectors that offer lower pay but are perceived to have more stable and safer working conditions.
Scientists at HSE University Devise More Accurate Method for Predicting the Electrical Conductivity of Electrolyte Solutions
Researchers at HSE MIEM have developed a model for calculating the electrical conductivity of aqueous electrolyte solutions; for the first time, it considers the spatial distribution of ion charges instead of assuming their localisation at a single point. The model remains effective even at high electrolyte concentrations and across a wide temperature range. This breakthrough will contribute to the development of more efficient batteries and enable the calculation of electrical conductivity without the need for experimental testing. The study has been published in the Journal of Chemical Physics.