This work provides a complete methodology for adopting well-established AI methods (predictive analytics, LLM agents, forecasting) into Microsoft Dynamics 365 Customer Relationship Management (CRM) for agricultural lending. While not claiming that the algorithms are novel, this work contributes a pragmatic approach to implementing these algorithms that specifically address the regulatory, seasonal, and operational characteristics of agricultural finance, as regulated by the Farm Credit System. It focuses on the real-life constraints and constraints within the regulated financial services industry, and measurable impacts that occurred. The paper provides a domain-oriented application of specific existing AI-CRM integration, with credible statistical testing including an external validation on USDA datasets and benchmarking across peer Farm Credit institutions, as well as cross-institutional analysis. By taking a reasonably conservative duration of 18 months, the Farm Credit institutions noted a statistically significant impact (operational efficiencies of the lending institution to assess member interests) where average case resolution time reduced by 28% (67.2h to 48.4h), and lead conversions improved by 35% (25.9% to 35.0%). Each methodology of implementation also included a series of validations in compliance with regulatory oversight in financial institutions that started to build data governance, model performance compliance through a proactive risk definition, and compliance standards suitable for their institution, and within regulatory standards by regulations. Beyond statistical significance (paired tests, $p <0.001$), practical impact was quantified using absolute and relative changes and bootstrap confidence intervals. The article provides the agricultural lending industry an applied methodology to adopt AI for stakeholder innovation while ensuring they are adept in their enterprise risk management requirement, and still target measurable business outcomes. Given a conservative potential implementation timetable (i.e., 18 months) and validation methodology protocols developed to ensure complete data and model validation, this approach is scalable for agricultural lending implementation and would be a useful instrument across all 72 Farm Credit System institutions.

Assessing the performance of decision-making units (DMUs) under intuitionistic fuzzy conditions has emerged as an essential area of investigation in today’s performance evaluation studies. The framework demonstrated in Intuitionistic Fuzzy Data Envelopment Analysis (IFDEA) is a way to assess the relative performance of DMUs when the observed data are notably expressed as ambiguity or uncertainty in the inputs and outputs represented by intuitionistic fuzzy numbers (IFN). When the situations define the conditions to use models with traditional input-output distinctions, traditional models are not less applicable when the parameters are vague, thus prompting the need for a set of more flexible tools. In this work, a ranking procedure is utilized that uses the centroid of triangular intuitionistic fuzzy numbers (TIFNs) to address the IFDEA model that defined input and output variable through TIFNs, it allows to calculate the efficiency status of each unit and to differentiate the DMUs between efficient and inefficient groups. An intuitionistic super-efficiency (IFSE) model is provided to obtain a complete ranking of DMUs that identified as efficient. To help decision makers, a reference-set-oriented benchmarking strategy is created to identify relevant peer units of the DMUs identified as inefficient to assist in improving their performance. To demonstrate the strength and practical applicability of the proposed framework, two examples of application are presented, as well as discussed, the technical differences of comparing the outcomes of analysis with the ranking proposals existing in the literature.

Selecting an optimal logistics service provider is a complex multi-criteria decision-making problem that directly affects a company’s competitiveness. This paper proposes a hybrid MCDM model that integrates the Full Consistency Method (FUCOM) and Measurement Alternatives and Ranking according to Compromise Solution (MARCOS) methods. FUCOM was used to determine the weight coefficients of seven criteria, while MARCOS was applied to rank ten potential logistics providers in the market of Bosnia and Herzegovina. The case study was conducted for the company Hygiene Pro Team from Banja Luka. The results showed that provider P9 represents the most favorable solution, which was confirmed by an extensive sensitivity analysis that verified the stability of the model. The proposed FUCOM–MARCOS model provides a robust framework for strategic decision-making in logistics.

The optimization of project schedules in the presence of uncertainty remains a critical challenge in project management. This study proposes a hybrid methodology that combines Monte Carlo Simulation (MCS) with Integer Linear Programming (ILP) to optimize project crashing strategies under conditions of schedule risk. The approach was applied to a real-world telecommunications infrastructure project, which involved the construction of 50 towers within a stringent contractual deadline. MCS was employed to model the uncertainty in activity durations and assess the likelihood of on-time project completion, while ILP was used to determine the most cost-effective crashing strategy. The findings indicate that, without any mitigation measures, the probability of completing the project within the planned 68-day schedule was a mere 3%. However, upon implementing risk response measures, this probability increased to 21%. A comparative analysis demonstrated that delay penalties increase at a much higher rate than crashing costs, highlighting the significant financial benefits of early intervention. This study illustrates that the integration of probabilistic risk analysis with optimization techniques not only enhances schedule reliability but also minimizes cost overruns, providing a robust decision-making framework for complex projects. By leveraging the combination of MCS and ILP, the proposed methodology supports the development of more resilient and economically efficient project plans, particularly in projects characterized by high uncertainty and time-sensitive constraints.