3 results
Search Results
Now showing 1 - 3 of 3
Item Open Access Statistical inference and machine learning in big data(Faculty of Engineering and Natural Science, 2019) Temirali A.In my practice. I met with different definitions: - Big Data is when data is more than 100GB (500GB. 1TB. who likes it) - Big Data is data that cannot be processed in Excel - Big Data is data that cannot be processed on a single computer. And even such: - Big Data is generally any data. - Big Data does not exist. marketers have invented it. Thus, under Big Data I will understand not some specific amount of data or even the data itself, but their processing methods. which allow distributed information to be processed. These methods cat? be applied both to huge data arrays (such as the content of all pages on the Internet) and to small ones (such as the content of this thesis).Item Open Access REALIZATION OF ALGORITHM OF SELF-GENERATING NEURAL NETWORKS(Faculty of Engineering and Natural Sciences, 2019) Abdikhaliyev Y.The development of various spheres of human activity is associated with the generation and accumulation of a huge amount of data that can contain the most important practical information. However, significant benefit from this information can be extracted only with proper processing and analysis of this data. Recently, there has been an increased interest in the field of artificial intelligence, and methods of automating the extraction of knowledge based on data mining are actively developing. Self-generating neural networks are built on the principle of biological, of course, with a number of assumptions, they have a huge number of simple processes with many connections. Like the human brain, these networks | are capable of learning. Self-generating neural networks find their application in areas such as computer vision, speech recognition, processing of natural language, etc. The thesis provides an‘analysis of the development of the theory of neural networks, their classification and mathematical formulation of the task of recognizing pattern recognition.Item Open Access Student Performance Prediction Using Machine Learning(SDU University, 2026) Syzdykov D.The early identification of academically at-risk students remains one of the most pressing problems in contemporary higher education. As universities accumulate large amounts of administrative, demographic and behavioural data through their Virtual Learning Environments, machine learning has emerged as a powerful instrument for transforming raw educational data into actionable early-warning signals. This dissertation develops, evaluates and explains a comprehensive machine learning pipeline for predicting student academic performance on the Open University Learning Analytics Dataset (OULAD), a publicly available benchmark containing detailed records for 32,593 learners across 22 module-presentations. The work is framed around four research questions concerning the most predictive student features, the most suitable learning algorithm for the task, the relative contribution of individual pipeline components and the practical interpretability of the resulting models. To answer these questions, the dissertation proposes an end-to-end methodology that combines multi-source data integration, domain-driven feature engineering, hybrid feature selection, synthetic minority over-sampling, Bayesian hyperparameter optimisation using Optuna and post-hoc model interpretation through SHapley Additive exPlanations (SHAP). Four representative classifiers are compared on the same task: a regularised Logistic Regression baseline, Random Forest, XGBoost and LightGBм. Experimental results demonstrate that gradient-boosted tree ensembles, and in particular an Optuna-tuned XGBoost model, consistently outperform the alternative baselines on the held-out test set, reaching a test area under the receiver operating characteristic curve of 0.97 and a test F1 score of 0.90 with a moderate overfitting gap. Engagement-related features-including the number of active days on the Virtual Learning Environment, total clicks and an engineered score_consistency indicator-are identified as the most influential predictors by both global feature-importance methods and SHAP analysis. An ablation study reveals that feature engineering, class-imbalance handling and hyperparameter tuning each contribute incrementally to the final performance and that their combination yields the best balance of accuracy, generalisation and computational efficiency. The dissertation also discusses educational, ethical and deployment-related implications of the proposed pipeline. SHAP-based explanations are shown to produce individualised, actionable insights that can be conveyed to educators and policymakers without requiring a deep understanding of the underlying algorithms. Limitations associated with the use of a single benchmark dataset, with binary outcome modelling and with the absence of causal claims are explicitly acknowledged, and directions for future research are outlined, including temporal modelling, fairness-aware learning and integration with existing learning analytics dashboards. Overall, the dissertation contributes a reproducible methodological template that bridges predictive accuracy and humaninterpretable insight in the context of student performance prediction.