Yerassyl Iskakov

Mr. Yerassyl Iskakov

Department of Information Systems, L.N. Gumilyov Eurasian National University, Nur-Sultan, Astana, Kazakhstan
orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
17 October 2024 in Econometrics
Verified
Journal Article
Open access
PDF file
ATAzat Tleubayev
Azat Tleubayev
Seyit KerimkhulleSeyit Kerimkhulle
Seyit Kerimkhulle
MTManatzhan Tleuzhanova
Manatzhan Tleuzhanova
AUAigul Uchkampirova
Aigul Uchkampirova
ZBZhanat Mukhanbetzhankyzy Bulakbay
Zhanat Mukhanbetzhankyzy Bulakbay
DTDaniyar Toleubay
Daniyar Toleubay
Based on the systematization of relevant problems in the agricultural sector of Kazakhstan and other countries, the purpose of the research is to aid in the development and implementation of a methodology for the econometric analysis of sustainability, the classification of economic growth, and an alternative strategy for gross value added depending on time phases with time lags of 0, 1, and 2 years, and on the gross fixed capital formation in the agricultural sector of Kazakhstan. The research has used a variety of quantitative techniques, including the logistic growth difference equation, applied statistics, econometric models, operations research, nonlinear mathematical programming models, economic modeling simulations, and sustainability analysis. In the work on three criteria: equilibrium, balanced and optimal growth, we have defined the main trends of growth of Gross added value of agriculture, hunting and forestry. The first, depending on the time phases, the second, depending on the Gross fixed capital formation transactions for equilibrium growth, for the growth of an alternative strategy, for the endogenous growth rate and the growth of exogenous flows. And we also received a classification of the trend of Productive, Moderate and Critical growth for the agricultural industry depending on the correlated linkaged industry of the national economy of Kazakhstan. The results of this work can be used in data analytics and artificial intelligence, digital transformation and technology in agriculture, as well as in the areas of sustainability and environmental impact.

30 August 2025
Verified
Book Chapter
Closed access
PDF file
Seyit KerimkhulleSeyit Kerimkhulle
Seyit Kerimkhulle
SKShakharzat Kuttykozhayeva
Shakharzat Kuttykozhayeva
GTGulnara Turtkarayeva
Gulnara Turtkarayeva
TSToty Seitova
Toty Seitova
NONazgul Ospanova
Nazgul Ospanova
YIYerassyl Iskakov
Yerassyl Iskakov

11 August 2026 in Engineering, Technology & Applied Science Research
Verified
Journal Article
Open access
PDF file
YIYerassyl Iskakov
Yerassyl Iskakov
ASAinur Shekerbek
Ainur Shekerbek
ANAizhan Nazyrova
Aizhan Nazyrova
Zhanar LamashevaZhanar Lamasheva
Zhanar Lamasheva
RDRayimbek Durbenov
Rayimbek Durbenov
This paper presents a two-stage Machine Learning (ML) framework for signal-based portfolio optimization in the National Stock Exchange (NSE) of India. Using a dataset of 20 major equities from 2020 to 2025, the study evaluates eleven predictive models, including regularized linear regressions, tree-based methods, and hybrid Deep Learning (DL) architectures such as Convolutional Neural Network–Long Short-Term Memory (CNN-LSTM) and Long Short-Term Memory–Multilayer Perceptron (LSTM-MLP). In the first stage, a 60-day sliding window is used to generate one-day-ahead return forecasts, which are then stabilized through a 10-period smoothing mechanism to reduce short-term prediction noise. In the second stage, these forecasts are transformed into cross-sectional investment signals and incorporated into a portfolio optimization framework. The results indicate that hybrid DL models achieve better predictive performance than traditional approaches in capturing non-linear market dynamics. Overall, the proposed framework provides a practical approach for converting model forecasts into portfolio decisions and may contribute to improved risk-adjusted performance.

30 June 2025 in Bulletin of the National Engineering Academy of the Republic of Kazakhstan
Verified
Journal Article
Closed access
LUL.N. Gumilyov Eurasian National University
L.N. Gumilyov Eurasian National University
Zhanar LamashevaZhanar Lamasheva
Zhanar Lamasheva
ASAinur Shekerbek
Ainur Shekerbek
ABA. S. Baegizova
A. S. Baegizova
RDR. M. Durbenov
R. M. Durbenov
YIYerassyl Iskakov
Yerassyl Iskakov
This study examines the dynamics of the major international currencies (USD, EUR, RUB, and CNY) in relation to the Kazakhstani Tenge (KZT) between 2000 and 2024, highlighting the crucial role that exchange rate stability plays in economic performance. Understanding currency fluctuations is crucial because Kazakhstan’s economy is highly reliant on the export of commodities and is susceptible to changes in the global economy. The research aims to analyze historical exchange rate trends and develop predictive models using machine learning technique. The methodology used machine learning algorithm, particularly Linear regression models, correlation studies, and descriptive statistical analysis. Data sourced from the National Bank of Kazakhstan encompassed 9,086 data points, providing insights into currency behaviors. Descriptive analysis revealed significant variations, with USD and EUR showing higher volatility compared to more stable RUB and CNY. The study also highlighted interconnected exchange rate dynamics and the unique position of the Russian Ruble, offering valuable insights for policymakers, investors, and all financial market participants navigating KZT complex behavior.