In this research, machine learning algorithms including Logistic Regression, Random Forest, XGBoost, and Artificial Neural Networks were evaluated and compared. Experimental results demonstrated that the integrated model achieved higher accuracy and effectiveness compared to traditional systems based solely on academic assessment. In particular, the inclusion of soft skills parameters significantly improved the prediction accuracy of students’ future educational pathways. The proposed model can be effectively utilized in the development of intelligent educational platforms, educational analytics systems, and AI-based recommendation systems in the future.
| Mualliflar | Mallayev, Oybek, Aliyev, Jaloliddin, Fozilov, Otabek, Gazatov , Jamoliddin |
|---|---|
| Jurnal | Al-Farg'oniy avlodlari |
| Nashr sanasi | 2026-05-30 |
| Son | 2 |
| Betlar | 247-258 |
| Til | Rus |
Machine learning, educational analytics, academic performance, soft skills, data modeling, neural networks, predictive analytics, student profiling, artificial intelligence, educational recommendation systems, long-term educational data, hybrid learning models, машинное обучение, educational analytics, академическая успеваемость, soft skills, моделирование данных, нейронные сети, predictive analytics, профилирование обучающихся, искусственный интеллект, рекомендательные образовательные системы, долгосрочные образовательные данные, гибридные модели обучения, Machine learning, educational analytics, academic performance, soft skills, data modeling, neural networks, predictive analytics, student profiling, artificial intelligence, educational recommendation systems, long-term educational data, hybrid learning models
Ushbu maqolada bir o'lchovli termoelastik jismning matematik modeli va uning sonli simulyatsiyasi muhokama qilinadi. Termoelastik jarayonlarni tavsiflovchi differentsial tenglamalar chekli farq usuli yordamida…
This article discusses the issues of geometric modeling of furniture objects with fractal structures based on the iterative function system (IFS). The study analyzes the specific properties of fractal geometry, in…
The principle of development of a perfect multisensor system integrated with unmanned aerial vehicles for the purpose of accurate and operational monitoring of various objects is considered. The system collects current…
This article discusses theoretical foundations of digital image preprocessing algorithms, their software implementation, and performance evaluation. Image quality degradation caused by noise, low contrast, and blurring…
This article proposes a quantum-resilient adaptive network security model for IoT and edge computing infrastructures. The model integrates firewalls, IDPS, Zero Trust, post-quantum cryptography, and resource-aware…
Recent studies in cognitive neurobiology have shown that biological neurons interact with each other through multiple neurotransmitter channels: a single neuron simultaneously secretes different neurotransmitters, each…
This article analyzes the problem of pixel-level separation of crop plants from weeds in agricultural images. In this study, the semantic segmentation models DeepLabV3+, U-Net, and U-Net++ were evaluated under identical…
Dimensionality reduction is one of the important problems in machine learning and intellectual data analysis, especially when objects are described by mixed-type features measured in different scales. Methodology for…
The article investigates the problem of determining semantic similarity of Uzbek texts using mathematical modeling. The study aims to integrate semantic analysis, vector space representation, similarity calculation, and…
This paper describes a hybrid quantum-classical system for solving the Capacity-Constrained Vehicle Routing Problem (CVRP) using a real-world distribution network in Samarkand, Uzbekistan.The problem is formulated as a…