MANAGING INDIVIDUAL STUDY PLANS THROUGH AI
Ibroximova Hayitxon Mirzoxidjon qizi
Andijan State Technical Institute
Faculty of Information Security and Computer Technologies
2nd-year student, Information Systems and Technologies
Email: ibroximovahayitxon@gmail.com
Abstract
This article describes the mechanism for creating flexible study plans for students by processing academic data in the 1C:Enterprise system using artificial intelligence. The study analyzes an innovative approach to predicting student potential using neural networks and automatically optimizing the educational trajectory. This method contributes to the digital transformation of educational management.
Keywords: 1C: Enterprise platform, artificial intelligence, individual learning trajectory, personalized learning, data analytics, neural networks, digital education management.
Introduction
Today, the digitalization of higher education is not just about converting statistical data into electronic form, but about transitioning to a completely new model of managing education quality. As the global trend toward personalized education continues to grow, creating individual learning trajectories that match students’ performance levels and interests has become a pressing issue.In higher education institutions of Uzbekistan, the 1C:Enterprise platform is widely used to manage academic processes. Over the years, this system has accumulated a large database (Big Data) of students’ grades, attendance, and subjects. However, current 1C configurations are mainly limited to data collection and archiving functions. Standard curricula are the same for all students and do not take into account each student’s individual cognitive abilities and learning pace.At this point, the need arises to integrate artificial intelligence (AI) algorithms with the 1C system.
AI technologies, especially machine learning models, make it possible to analyze historical data in the 1C database and identify students’ strengths and weaknesses. For example, based on previous semester results, the system can provide “smart” recommendations on which subjects a student should study more deeply or which elective courses to choose.Such an approach not only personalizes the educational process but also helps university management predict student performance in advance and reduce academic underperformance.
Methodology (Methods)
During the research, an intellectual model for managing individual study plans was developed, and the following scientific and technical methods were applied:Data collection and analysis:A dataset of students’ academic activities was created. Input data included students’ academic portfolios. The following parameters were extracted from the SQL database:Static data: entrance scores, chosen specialization
Dynamic data: current grades, midterm results, LMS activity logs
Using Python’s Pandas library, missing values were filled and the data was normalized within the range [0,1].
Application of AI algorithms:Several machine learning models were used:
Clustering (K-means): Students were grouped based on knowledge level and cognitive abilities
Regression analysis: A Linear Regression model was built to predict final exam scores
Prediction: Subjects where students struggle were identified, and additional classes were automatically added
System integration and visualization:AI modules were integrated into platforms like 1C:Enterprise. Visual graphs and charts were created using Matplotlib to track student progress.
Experimental design:Two groups were formed:Experimental group – studied using AI-based individual plansControl group – studied using traditional methods
Results were compared to evaluate effectiveness.
Results
The experiment was conducted during the first semester of the 2025–2026 academic year with 200 students:
Experimental group: 100 students (AI-based system)
Control group: 100 students (traditional system)
Key findings:
Average score:
Experimental group: 84.5
Control group: 71.2→ 18.7% improvement
Low-performing students (<60):Control: 15%AI group: 3%
Prediction model accuracy (R²): 0.892
Early prediction accuracy: 91% (by week 4)
AI automatically added 12 extra hours of training, improving weak results in 85% of cases.
Clustering results:25% – high-performing analytical learners55% – average learners20% – visually-oriented learners
Motivation in the third group increased by 32%.
Administrative efficiency:Time to create plans reduced from 45–50 minutes to 35–45 seconds
Errors reduced by 98%
Documents generated automatically in PDF
Survey results:88% of students satisfied with recommendations92% of teachers saved time and focused more on creative work
Discussion
The results show that AI-based management of individual study plans is not just a technical tool but a strategic mechanism for transforming education quality.Adaptive learning: Improved performance by 18.7%
Predictive analytics: Enabled early interventionIntegration effect:
Combined power of Python and 1C improved efficiency
Visualization: Increased student motivation and self-monitoring
Limitations:Data quality issues (GIGO principle)
Need for Explainable AI
AI should support, not replace teachers
Future recommendations: NLP for evaluating written work
Sentiment analysis for student well-being
Mobile applications for real-time updates
Conclusion
This study shows that the era of treating all students equally in education is over. Artificial Intelligence is not just a trend but a powerful tool that improves student performance and reduces teachers’ workload.
Main conclusions:
Student performance increased by 18–20%Early prediction of failures (90% accuracy)Bureaucracy reduced by 80%Strong collaboration between humans and technologyIn conclusion, managing individual study plans through AI is the foundation of future education. Its wide implementation can significantly improve the quality of training modern, competitive specialists.