INNOVATIVE APPROACHES TO AGRICULTURAL MARKETING: NSGA-II AND K-MEANS FOR STRATEGIES IN THE AGRO-INDUSTRIAL COMPLEX

Zhansaya Abildaeva, Raissa Uskenbayeva, Nurbek Konyrbaev, Gulzhanat Beketova, Valeriy Lakhno, Alona Desiatko

Scientific Journal of Astana IT University, 2025

Full text Open access: Gold Metadata (CSL-JSON)
DOI 10.37943/23orhf6321
Data confidence 70 medium
How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

The relevance of this study is determined by the urgent need to improve marketing strategies in the agro-industrial complex (AIC) of Kazakhstan, where competitiveness and sustainability depend not only on production efficiency but also on effective promotion of agricultural products. Rapid digitalization and regional market heterogeneity create new challenges for enterprises that cannot be solved by traditional heuristic or single-objective approaches. The purpose of the research is the development of a hybrid method for multi-criteria optimization of marketing budget allocation in the AIC of Kazakhstan. The objective of the experiment is to test the hypothesis that such a method provides more balanced solutions in terms of efficiency, coverage, and cost compared to baseline approaches. The methodology is based on combining the evolutionary NSGA-II algorithm with K-means clustering. The first stage identifies Pareto-optimal distributions of marketing resources, while the clustering procedure segments the obtained strategies into groups with distinct efficiency-cost trade-offs. Input data were derived from synthetic simulations reflecting typical market conditions and real indicators of several agricultural enterprises. The results of computational experiments demonstrate that the proposed method outperforms single-objective optimization. In particular, it achieved higher average efficiency (1.56 vs. 1.10), wider coverage (1.39 vs. 0.95), and greater hypervolume (0.67 vs. 0.45). Clusters with combined use of digital and television channels provided the most effective balance of performance indicators, while radio and print media remained relevant for enterprises with moderate budgets. The novelty of the study lies in integrating evolutionary optimization with machine learning for marketing strategy design in the AIC. The obtained data can be applied by managers and policymakers for media planning, budget allocation, and the development of adaptive strategies that strengthen competitiveness and contribute to export growth.