Optimizing agricultural decision-making with integrated MCDM-MCDA methods: A case study on crop economics

Because of the quantitative and qualitative uncertainty and complexity, it is not sufficient to use just Multicriteria Decision Making (MCDM), but also Multi-Criteria Decision Analysis (MCDA). The MCDM relates to the methods by which decisions are taken (i.e., selection of alternatives, ranked or ordered, and for what is analyzed being objective values. While MCDA offers a comprehensive approach for systematic assessment of criteria considering its impact on decision outcomes. Given that both methods have their own strengths, it is necessary to apply both MCDM and MCDA in agricultural economics which has a lot of uncertainty because of market price variability, increasing input costs and changing weather patterns. In this paper, Fuzzy Hypersoft Sets (FHSs), is used to model this problem and a case study is solved with Stable Preference Ordering Towards Ideal Solution (SPOTIS), Random Forest (RF), and Multi-Objective Optimization by Ratio Analysis (MULTIMOORA) to identify the most favorable crop for Jane's farm in terms of weather, costs required during agricultural production process like water or land usage, pesticide resistance against pests as well as market demand. Maize as an alternative ??7 = 0.526 was identified as the best choice by all three methods with Tomatoes and Rice scoring second, based on calculated score values. Thus, it enables us to study both quantitative and qualitative data, making it extremely able for agriculture uncertainties. This unique usage of sophisticated mathematics integrated with machine learning allows the decision-makers to find more accurate results, meaning it can manage economic risks better and allocate resources intelligently in agriculture. The comparative analysis with existing studies highlights the superiority of proposed work. Thus, it is significantly superior in accuracy. Hence farmers can harness farm economics to address these challenges by managing economic risks using mathematical decision-making tool, thereby leading them towards sustainability of livelihoods, food security and a resilient agricultural sector.