XGBoost To Enhance Learner Performance Prediction

Computers and Education Artificial Intelligence, Journal Year: 2024, Volume and Issue: 7, P. 100254 - 100254

Published: June 13, 2024

The huge amount of data generated by an Intelligent Tutoring System becomes useful when analyzed in appropriate way to provide significant insights about learners, especially his or her performance. Performance retrieved from historical interactions is the main engine for learner performance prediction, where likelihood answering correctly future questions calculated. Modeling can into individual students promote successful learning and maximize educational achievement. This study aims enhance prediction some logistic regression-based models, namely Item Response Theory, Factor Analysis, DAS3H using XGBoost, including empirical comparison eight real-world datasets, containing log collected different online intelligent tutoring systems, involving first time a new dataset Moodle Morocco. results have demonstrated that XGBoost has enhanced PFA predictive on seven datasets with AUC up 0.88 improved ASSISTment17 while conserving almost same Theory datasets.

Language: Английский

---

A Novel Fuzzy Feature Generation Approach for Happiness Prediction

IEEE Transactions on Emerging Topics in Computational Intelligence, Journal Year: 2024, Volume and Issue: 8(2), P. 1595 - 1608

Published: Jan. 24, 2024

Happiness refers to an emotional state of well-being and contentment. Accurate prediction happiness is important for people in promoting a healthy lifestyle, helping reduce stress, enhancing humans' immune system. In this paper, we propose novel fuzzy feature generation approach prediction. We design weighted operation based on the IF-THEN rules generate feature. This generated (new information) added model training achieve more accurate model. addition, considering high interpretability rules, it can improve process generation. Experimental results show that with use proposed approach, performance used machine learning models be improved prediction, outperforming state-of-the-art models. Among all models, FF-CatBoost has best terms accuracy (62.75%) F1-score (66.63%). Results other data sets also confirm effectiveness our approach. The statistical from Wilcoxon rank-sum test further significantly accuracy. With its excellent useful tool help know about their status live happier life.

Language: Английский

---

A Feature Importance-Based Multi-Layer CatBoost for Student Performance Prediction

IEEE Transactions on Knowledge and Data Engineering, Journal Year: 2024, Volume and Issue: 36(11), P. 5495 - 5507

Published: May 3, 2024

Student performance prediction is vital for identifying at-risk students and providing support to help them succeed academically. In this paper, we propose a feature importance-based multi-layer CatBoost approach predict the students' grade in period exam. The idea construct structure with increasingly important features layer by layer. Specifically, importance are first calculated sorted ascending order. each layer, least accumulated until reaching given threshold. Then, these selected used training CatBoost. Next, trained utilized generate that adds set their within After that, all train next This process repeated used. results show proposed model has best performance. Moreover, statistical test conducted based on 20-runs of experiments validates significant superiority our over compared models demonstrates efficacy enhancing model. indicates can decision makers educational quality.

Language: Английский

---

Predictive Modeling of Student Behavior for Early Dropout Detection in Universities using Machine Learning Techniques

2019 IEEE 6th International Conference on Engineering Technologies and Applied Sciences (ICETAS), Journal Year: 2023, Volume and Issue: unknown, P. 1 - 5

Published: Oct. 25, 2023

In universities, student dropout is a significant concern as it adversely affects both the students and educational institutions. Identifying who are at risk of dropping out early allows for timely interventions support systems to be implemented, thereby enhancing retention rates. This study focuses on applying machine learning techniques analyze behavior predict in university settings. The objective this research develop learning-based predictive model that utilizes behavioral data identify potential indicators dropout. Various aspects behavior, including academic performance, engagement, course participation, campus involvement, considered input features model. By analyzing these patterns, aims accurately which higher stages their journey. A comprehensive dataset collected, encompassing demographic information, records, extracurricular activities, other relevant variables. To extract useful from dataset, feature engineering approaches employed, then used inputs algorithms. algorithms, such vector machines, feed forward neural networks, random forest, logistic regression, gradient boosting, KNN ensemble methods implemented evaluated determine most effective approach prediction. findings have substantial implications education since they provide new understanding relationships between out. suggested provides institutions with tool proactively may danger dropout, enabling implementation tailored programs aimed improving overall accomplishment.

Language: Английский

---

An Unbiased Fuzzy Weighted Relative Error Support Vector Machine for Reverse Prediction of Concrete Components

IEEE Transactions on Artificial Intelligence, Journal Year: 2024, Volume and Issue: 5(9), P. 4574 - 4584

Published: April 5, 2024

Concrete is a vital component in modern construction, prized for its strength, durability, and versatility. Accurately determining the quantities of concrete components crucial civil engineering applications to optimize resources (e.g., manpower financial resources). In this article, we propose an unbiased Fuzzy-Weighted Relative Error Support Vector Machine (UFW-RE-SVM) reverse prediction components. First, add term target function UFW-RE-SVM obtaining model. Second, design fuzzy-weighted operation indicate sample importance by incorporating fuzzy membership values into UFW-RE- SVM. The nth root introduced address exponential explosion issue operation. Finally, considering sensitive hyper-parameters multi-output prediction, Whale Optimization Algorithm (WOA) utilized hyper-parameter optimization effectiveness tasks. We fitness based on results from multiple balance performance predictions. Experimental show that our proposed model outperforms existing works predicting terms mean absolute relative error, standard deviation, square error. Further, statistical test shows WOA two other metaheuristics can significantly improve performance. This indicates term, operation, are effective improving With these promising results, could provide decision-makers with valuable tool desired qualities.

Language: Английский

---

Superficial implementation of religious moderation in Islamic educational management

Cogent Education, Journal Year: 2024, Volume and Issue: 12(1)

Published: Dec. 20, 2024

This study examines of religious moderation in Indonesia educational institutions, focusing on its cognitive dimension. focus frequently results a superficial understanding moderation, depicting it more as theoretical concept than transformative force shaping one's character. The serves complementary investigation to previous inquiries by addressing the often-neglected contradictory aspects. Employing qualitative research methodologies, gathered data from diverse online news outlets, digital journals, and interviews with educators. findings within institutions shed light top-down execution policies, coupled an implementation that predominantly remains confined textual realm. Three primary factors elucidate nature moderation. Firstly, material's superficiality, presented learning format, is direct consequence policies. Religious education conforms predetermined programs constrained timeframe Islamic Education classes, lacking practical application beyond classroom. Secondly, material concerning lacks integration prevailing school culture. Thirdly, repercussions become apparent cultivation values lack contextualization social realities, resulting heightened intolerance, instances violence sector, increased susceptibility among students adopt fanatical attitudes.

Language: Английский

---

A whale optimization algorithm-based ensemble model for power consumption prediction

Electrical Engineering, Journal Year: 2024, Volume and Issue: unknown

Published: July 18, 2024

Language: Английский

---

Exploring Machine Learning’s Role in Education: A Comprehensive Review and Academic Implications

Communications in computer and information science, Journal Year: 2024, Volume and Issue: unknown, P. 228 - 241

Published: Jan. 1, 2024

Language: Английский

---

SoK: The Impact of Educational Data Mining on Organisational Administration

Information, Journal Year: 2024, Volume and Issue: 15(11), P. 738 - 738

Published: Nov. 19, 2024

Educational Data Mining (EDM) applies advanced data mining techniques to analyse from educational settings, traditionally aimed at improving student performance. However, EDM’s potential extends enhancing administrative functions in organisations. This systematisation of knowledge (SoK) explores the use EDM organisational administration, examining peer-reviewed and non-peer-reviewed studies provide a comprehensive understanding its impact. review highlights how can revolutionise decision-making processes, supporting data-driven strategies that enhance efficiency. It outlines key used tasks like resource allocation, staff evaluation, institutional planning. Challenges related implementation, such as privacy, system integration, need for specialised skills, are also discussed. While offers benefits increased efficiency informed decision-making, this notes risks, including over-reliance on misinterpretation. The role developing robust frameworks align with goals is explored. study provides critical overview existing literature identifies areas future research, offering insights optimise administration through effective highlighting growing significance shaping

Language: Английский

---

Complementary CatBoost based on residual error for student performance prediction

Pattern Recognition, Journal Year: 2024, Volume and Issue: unknown, P. 111265 - 111265

Published: Dec. 1, 2024

Language: Английский

---