Computerized adaptive testing (CAT) systems face major challenges at the beginning of test administration, when limited response data produces unstable ability estimates and poor item selection. This cold-start problem reduces measurement precision and testing efficiency, especially for students whose abilities diverge from population norms. This study introduces a hybrid ability-estimation model that dynamically integrates neural network predictions with classical item response theory (IRT) estimation throughout the adaptive testing process. The neural component uses auxiliary student information-including demographics, prior performance, and early response patterns-to generate accurate initial ability estimates, while the IRT component preserves psychometric validity as response data accumulate. A dynamic fusion mechanism gradually shifts estimation weight from the neural model to the IRT model as more items are administered. Experimental validation on 2847 students across four subject domains shows that the hybrid approach reduces RMSE in ability estimation by 34.2% during the first five items compared with traditional CAT methods, while maintaining equivalent precision in later stages. The system also decreases the number of items required to reach target precision (SE < 0.3) by 28.7% on average, with the largest gains observed for students at ability extremes.

This paper presents the design and validation of a modular interface architecture for automated testing of IoT devices. The proposed system integrates asyn

Investment assessment in the agricultural sector remains a complex problem owing to uncertainty, incomplete information, and the heterogeneous nature of economic and environmental data, particularly in developing economies. This study proposes a multi-agent hybrid model to evaluate the investment attractiveness of Kazakhstan’s agro-industrial complex. The methodology integrates fuzzy logic, artificial neural networks, and optimization algorithms into a modular multi-agent architecture. The model is based on international datasets from the OECD and FAO covering the period 2010–2023, including Producer Support Estimate (PSE), Agri-Environmental Indicators (AEI), Agricultural Outlook projections, and foreign direct investment (FDI) inflows. The data were normalized using the min–max method and transformed into fuzzy representations through triangular membership functions to capture uncertainty and expert judgment. Specialized agents perform data acquisition, preprocessing, factor analyses, and prediction tasks. Neural networks optimized using genetic algorithms and particle swarm optimization were trained on fuzzy-transformed indicators to generate an integrated investment attractiveness index ranging from zero to one. The experimental results demonstrate high predictive performance, with MAE = 0.083, ROC-AUC = 0.87, and F1-score = 0.81, confirming the robustness and stability of the proposed approach. The results indicate that combining fuzzy logic for interpretability, neural networks for predictive accuracy, and multiagent systems for scalability significantly improves investment assessment under uncertainty. The proposed framework can be practically applied by policymakers, investors, and agricultural stakeholders to support transparent, adaptive, and evidence-based investment decision-making in Kazakhstan’s agro-industrial sector.