Artificial intelligence-driven trade forecasting models: enhancing predictive accuracy in international trade flows and market volatility

Kurolov , Maksud

Innovation science and technologiy · 2025-yil

Annotatsiya

This study investigates how the application of artificial intelligence manifests itself in traders’ perceptions of theirdecision-making in the context of international trade flows. The rise of AI-driven forecasting has enabled new forms ofprediction, but the effectiveness of these models, particularly the accuracy in shaping expectations of market volatility,is not well understood. This research aims at examining the task of forecasting trade flows based on data derivingfrom statistical indicators, for instance regression outputs and other correlation measures, with the development of arelevant model for predictive accuracy. We employ the SWOT analysis method to analyze trade strategies conductedwith international datasets, and we identify six key mechanisms of model performance, namely data integration, variableselection, risk assessment, forecasting precision, adaptability, and robustness. Our results illustrate that from anempirical perspective, accuracy in predictive modeling is a key positive element of sustainable trade management. Thestudy furthers understanding of the implications from regression analysis and correlation testing on international tradeforecasting. In this paper, a methodological and instrumental solution to the current problem of creating the most effectivepredictive framework in a volatile global market is proposed

Maqola ma’lumotlari
MualliflarKurolov , Maksud
JurnalInnovation science and technologiy
NashriyotТошкент давлат иқтисодиёт университети
Nashr sanasi2025-08-01
Jild1
Son8
TilIngliz
Ilmiy sohaIqtisodiyot
DOI10.5281/zenodo.17447908
Indeksga qo‘shilgan2026-08-26

DOI: 10.5281/zenodo.17447908 · Maqolaning asl sahifasi

Kalit so‘zlar

Artificial Intelligence, Predictive Accuracy, International Trade Forecasting, Market Volatility, Regression– Correlation Analysis, SWOT–SEM Hybrid Modeling, Sustainable Trade Management

Ilmiy soha

Iqtisodiyot

Iqtibos keltirish

APAKurolov , Maksud (2025). ARTIFICIAL INTELLIGENCE-DRIVEN TRADE FORECASTING MODELS: ENHANCING PREDICTIVE ACCURACY IN INTERNATIONAL TRADE FLOWS AND MARKET VOLATILITY. Innovation science and technologiy, 1(8). https://doi.org/10.5281/zenodo.17447908
GOST (OAK)Kurolov , Maksud ARTIFICIAL INTELLIGENCE-DRIVEN TRADE FORECASTING MODELS: ENHANCING PREDICTIVE ACCURACY IN INTERNATIONAL TRADE FLOWS AND MARKET VOLATILITY // Innovation science and technologiy. – 2025. – T. 1, № 8. – DOI: 10.5281/zenodo.17447908.
MLAKurolov , Maksud. “ARTIFICIAL INTELLIGENCE-DRIVEN TRADE FORECASTING MODELS: ENHANCING PREDICTIVE ACCURACY IN INTERNATIONAL TRADE FLOWS AND MARKET VOLATILITY.” Innovation science and technologiy, 1(8), 2025. https://doi.org/10.5281/zenodo.17447908
ChicagoKurolov , Maksud. “ARTIFICIAL INTELLIGENCE-DRIVEN TRADE FORECASTING MODELS: ENHANCING PREDICTIVE ACCURACY IN INTERNATIONAL TRADE FLOWS AND MARKET VOLATILITY.” Innovation science and technologiy, 1(8) (2025). https://doi.org/10.5281/zenodo.17447908
HarvardKurolov , Maksud (2025) ‘ARTIFICIAL INTELLIGENCE-DRIVEN TRADE FORECASTING MODELS: ENHANCING PREDICTIVE ACCURACY IN INTERNATIONAL TRADE FLOWS AND MARKET VOLATILITY’, Innovation science and technologiy, 1(8). https://doi.org/10.5281/zenodo.17447908
BibTeX
@article{kurolovmaksud2025,
  title = {ARTIFICIAL INTELLIGENCE-DRIVEN TRADE FORECASTING MODELS: ENHANCING PREDICTIVE ACCURACY IN INTERNATIONAL TRADE FLOWS AND MARKET VOLATILITY},
  author = {Kurolov , Maksud},
  journal = {Innovation science and technologiy},
  year = {2025},
  volume = {1},
  number = {8},
  doi = {10.5281/zenodo.17447908},
  url = {https://doi.org/10.5281/zenodo.17447908}
}

Boshqa maqola uchun iqtibos tayyorlash

Innovation science and technologiy jurnalidan boshqa maqolalar

Innovation science and technologiy — barcha maqolalar · 2025-yil arxivi

Kurolov , Maksud — boshqa maqolalari

Iqtisodiyot sohasidagi boshqa maqolalar

Iqtisodiyot sohasidagi OAK jurnallari