Description:FIELD OF THE INVENTION
This invention relates to System and Method for Predicting Student Performance in Online Courses Using Machine Learning Algorithms
BACKGROUND OF THE INVENTION
Maintaining and assessing pupil participation has grown more challenging as a result of the swift adjustment to online learning. In order to identify distracted or at-risk students with capture current educational actions, standard techniques depend on human monitoring and static assessments, that are inadequate. These methods frequently don't take advantage of the enormous quantity of interaction data that is accessible in Virtual Learning Environments (VLEs), and they aren't scalable or personalized. An automated, data-driven system that uses machine learning to predict engagement among learners correctly and support timely interventions to improve learning outcomes is desperately needed.
Several existing patents and applications address aspects of student performance measurement in online education:
1. US20140205990A1 Machine Learning for Student Engagement: This patent application offers methods for using machine learning algorithms to detect patterns in how students interact with educational systems. The method aims to predict students' academic progress and gauge their level of interest in the material.
2. US10909867B2 Student Engagement and Analytics Systems and Methods with Machine Learning Student Behaviors Based on Objective Measures of Student Engagement: The systems and techniques covered by this patent leverage machine learning to evaluate objective indicators of student engagement. The system's goal is to forecast student behavior and give teachers analytics so they may implement interventions that will enhance student performance.
3. US20220198949A1 System and Method for Determining RealTime Engagement Scores in Interactive Online Learning Sessions: This application explains a system that creates student engagement scores in real time during live online sessions using artificial intelligence models. In order to give composite and individual engagement scores, the system gathers data from insession, postsession, and class sessions. This helps teachers quickly identify and resolve student involvement levels.
4. US20200134759A1 Machine Learning for Optimal Student Guidance: This application describes a machine learning based system that gives pupils the best possible guidance. The system provides tailored suggestions to improve learning outcomes by examining a variety of data points pertaining to student behavior and performance.
While these patents and applications offer various solutions, they often focus on engagement monitoring rather than a comprehensive student performance measurement system that integrates realtime learning behaviors, personalized interventions, and predictive analytics.
SUMMARY OF THE INVENTION
This summary is provided to introduce a selection of concepts, in a simplified format, that are further described in the detailed description of the invention.
This summary is neither intended to identify key or essential inventive concepts of the invention and nor is it intended for determining the scope of the invention.
To further clarify advantages and features of the present invention, a more particular description of the invention will be rendered by reference to specific embodiments thereof, which is illustrated in the appended drawings. It is appreciated that these drawings depict only typical embodiments of the invention and are therefore not to be considered limiting of its scope. The invention will be described and explained with additional specificity and detail with the accompanying drawings.
The invention offers an intelligent system that uses machine learning algorithms to estimate the degree of student involvement in virtual learning environments (VLEs). The system generates statistical models that identify patterns that indicate whether a student is actively engaged or at risk of disengagement by gathering and analyzing data from various sources, including student assessments, personal information, VLE interactions, and instructional materials.
BRIEF DESCRIPTION OF THE DRAWINGS
The illustrated embodiments of the subject matter will be understood by reference to the drawings, wherein like parts are designated by like numerals throughout. The following description is intended only by way of example, and simply illustrates certain selected embodiments of devices, systems, and methods that are consistent with the subject matter as claimed herein, wherein:
FIGURE 1: SYSTEM ARCHITECTURE
The figures depict embodiments of the present subject matter for the purposes of illustration only. A person skilled in the art will easily recognize from the following description that alternative embodiments of the structures and methods illustrated herein may be employed without departing from the principles of the disclosure described herein.
DETAILED DESCRIPTION OF THE INVENTION
The detailed description of various exemplary embodiments of the disclosure is described herein with reference to the accompanying drawings. It should be noted that the embodiments are described herein in such details as to clearly communicate the disclosure. However, the amount of details provided herein is not intended to limit the anticipated variations of embodiments; on the contrary, the intention is to cover all modifications, equivalents, and alternatives falling within the scope of the present disclosure as defined by the appended claims.
It is also to be understood that various arrangements may be devised that, although not explicitly described or shown herein, embody the principles of the present disclosure. Moreover, all statements herein reciting principles, aspects, and embodiments of the present disclosure, as well as specific examples, are intended to encompass equivalents thereof.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments. As used herein, the singular forms “a",” “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms “comprises,” “comprising,” “includes” and/or “including,” when used herein, specify the presence of stated features, integers, steps, operations, elements and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and/or groups thereof.
It should also be noted that in some alternative implementations, the functions/acts noted may occur out of the order noted in the figures. For example, two figures shown in succession may, in fact, be executed concurrently or may sometimes be executed in the reverse order, depending upon the functionality/acts involved.
In addition, the descriptions of "first", "second", “third”, and the like in the present invention are used for the purpose of description only, and are not to be construed as indicating or implying their relative importance or implicitly indicating the number of technical features indicated. Thus, features defining "first" and "second" may include at least one of the features, either explicitly or implicitly.
Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which example embodiments belong. It will be further understood that terms, e.g., those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
The invention offers an intelligent system that uses machine learning algorithms to estimate the degree of student involvement in virtual learning environments (VLEs). The system generates statistical models that identify patterns that indicate whether a student is actively engaged or at risk of disengagement by gathering and analyzing data from various sources, including student assessments, personal information, VLE interactions, and instructional materials.
The invention specifically does:
1. Collects Multisource Educational Data:
Data about student behavior is collected in real time, including the amount of time spent on learning modules, the quantity of forum posts, quiz attempts, assignment submissions, and the frequency of logins.
2. Preprocesses and Transforms the Data:
In addition to resolving missing values, normalizing input, and creating valuable features for model training, the system cleans, filters, and converts raw data to a format that can be used.
3. Trains Predictive Machine Learning Models:
Several techniques, like as neural networks, decision trees, and support vector machines, are used to train on past student data in order to determine the relationship between various behaviors and engagement results.
4. Evaluates Model Performance:
The invention evaluates and compares models based on performance criteria to identify the most suitable model for deployment.
5. Predicts Engagement Levels in Real Time:
Following training, the algorithm continuously analyzes incoming student interaction data to forecast engagement levels, enabling real-time monitoring.
6. Supports Early Intervention and Personalization:
Through the identification of pupils exhibiting early indicators of disengagement, the system assists teachers in taking prompt, tailored measures, such as sending notifications, suggesting more resources, or setting up one-on-one support sessions.
Detailed Description of the Invention:
1. Data Collection Module: Compiles student academic records, grades from prior semesters, attendance, discussion participation, and course material engagement.
2. Feature Engineering Module: Converts unstructured data into useful features, such as assignment completion time, quiz attempts, and interaction frequency
3. Machine Learning Model:
o Uses a range of machine learning methods, including:
 Random Forest (RF): An ensemble learning technique based on decision trees that increases prediction accuracy.
 MultiLayer Perceptron (MLP): A neural network model designed to learn complex student performance patterns.
 kNearest Neighbors (KNN): A classification method that groups students based on similar performance trends.
4. Predictive Analytics Module:
o Generates performance predictions based on student behavior patterns.
o Identifies atrisk students early to enable timely interventions.
5. Feedback and Recommendation Engine:
o Provides insights to students and educators regarding performance trends.
o Makes recommendations for corrective therapies, extra study resources, or customized education techniques.
6. Dashboard and Reporting System:
o Uses an intuitive UI to present predictive performance information.
o Enables administrators and teachers to monitor student development and put support systems in place.
The system has been evaluated with a dataset of educational information, including grades, participation measurements, and how they studied. Following training, the machine learning methods' accuracy in predicting was evaluated.
The results showed that Random Forest (RF) outperformed the other models in regards to accuracy and recall, resulting in an ideal approach to forecasting student achievement.
Model Accuracy (%) Precision (%) Recall (%)
Random Forest (RF) 93.5 92.8 93.1
MultiLayer Perceptron (MLP) 89.5 89.7 89.1
kNearest Neighbors (KNN) 85.6 84.2 85.0
Discussion:
1. Model Comparison: RF demonstrated the highest accuracy due to the could manage the complicated patterns in student data. Even though MLP required more processing power, it did a great job. KNN was effective, but it struggled with large datasets.
2. Impact of Personalized Recommendations: Based on the forecasted outcomes, the system provided personalized study plans that increased student participation and continuation levels.
3. Scalability and Adaptability: By effectively adjusting to various educational instances, the framework showed robustness in a variety of online learning scenarios.
In addition to providing real-time, customized support, the proposed innovation significantly increases the accuracy of student achievement predictions. Since integration into LMS systems ensures its smooth adoption, it is a helpful tool for improving the results of online education.
NOVELTY:
The suggested idea differs from current solutions in a number of innovative ways, including:
1. Hybrid Machine Learning Approach: Unlike prior patents which concentrated on a single model, this innovation maximizes predicted accuracy and reliability by combining many complex algorithms (RF, MLP, and KNN).
2. Comprehensive Data Utilization: This approach incorporates a variety of student data, such as prior academic performance, study habits, and interactions, whereas earlier studies just examined involvement metrics.
3. Real Time Intervention and Personalization: A dynamic suggestion engine provided by the invention allows for real-time modifications to assignments, activities, and instructional materials in response to trends in student performance.
4. Scalable and Adaptive Learning Models: By training from latest information, the framework constantly updates its predictive models, guaranteeing current and precise insights into student performance.
5. Integration with Learning Management Systems (LMS): The innovation provides educational facilities with a ready to use a substitute through easy interaction with present LMS sites.
6. Explainable AI (XAI) Capabilities: The proposed approach, in contrast to blackbox AI models, provides brief justifications for predicts and suggestions, enabling teachers and students to comprehend the logic behind results.
7. EarlyStage Risk Identification: The machine learning predictive analytics modules provide timely academic interventions by detecting learning gaps earlier than with conventional evaluation methods..
The image displays a structured pipeline that forecasts student engagement in a virtual learning environment (VLE) using machine learning techniques. The workflow consists of several sequential stages:
1. Input Data Collection:
o The system gathers studentrelated data from multiple sources, including:
 Student assessment and student information: Academic performance data, demographic information, and past learning behaviors.
 VLE interactions: Logs of student activities within the online learning platform.
 Courserelated data: Information about course structure, materials accessed, and participation frequency.
2. Preprocessing:
o The collected data undergoes cleaning and transformation to handle missing values, remove irrelevant attributes, and normalize numerical features.
o Data is structured into a suitable format for training machine learning models.
3. Training Data Preparation:
o The processed data is divided into training and validation sets.
o Feature engineering techniques are applied to extract relevant attributes for engagement prediction.
4. Building Predictive Models:
o Various machine learning models (e.g., decision trees, support vector machines, neural networks) are trained on the prepared dataset.
o The models learn patterns and relationships between input features and student engagement levels.
5. Testing:
o The trained models are evaluated on unseen test data to measure their generalization ability.
o Performance metrics such as accuracy, precision, recall, and F1score are calculated.
6. Model Evaluation:
o The bestperforming model is selected based on evaluation results.
o If necessary, hyperparameter tuning and model optimization are performed.
7. Prediction of Student Engagement:
o The finalized model is deployed to predict student engagement levels in the VLE.
o The system provides insights into student participation trends and identifies atrisk students.
In order to improve individualized learning experiences in online education, this image clearly illustrates the entire process of applying machine learning for realtime student engagement prediction.
ADVANTAGES OF THE INVENTION
1. Comprehensive Performance Analysis: The suggested invention incorporates a wide range of student performance indicators, such as quiz outcomes, study habits, discussion forum involvement, and resource usage, in contrast to previous systems that only concentrate on engagement metrics.
2. Advanced Machine Learning Models: Compared to current methods that rely on simpler algorithms, it guarantees higher prediction precision by combining RF, MLP, and KNN models.
3. RealTime Adaptive Feedback: Provides teachers and students with ongoing monitoring and timely recommendations to address instructional weaknesses as they arise.
4. Early Risk Detection and Intervention: Prevents performance declines by early detection of at-risk kids and the implementation of preventative measures.
5. Personalized Learning Recommendations: Uses predictive analytics to give each learner unique study plans, tailored evaluations, and learning strategies.
6. MultiSource Data Integration: By collecting and evaluating a range of data sources, multisource data integration improves forecast accuracy and reduces the likelihood of inaccurate assessments.
7. EducatorFriendly Dashboard: Gives teachers the ability to efficiently track student progress, generate reports, and employ customized teaching methods using an intuitive visualization interface.
8. Continuous Model Improvement: The system continuously enhances its estimates by learning from new student data, ensuring precision and adaptability.
9. Integration with Learning Management Systems (LMS): This feature is easy for educational institutions to set up because it communicates easily with existing LMS systems.
10. Explainable AI (XAI) Capabilities: Helps educators and learners make informed decisions by providing forecast transparency by explaining the rationale behind each recommendation.
 
, Claims:1. A computer-implemented system for predicting student performance in online courses, comprising:
a data collection module configured to gather academic records, grades, attendance, participation, and virtual learning environment (VLE) activity data;
a preprocessing unit for cleaning and preparing the collected data for model training;
a feature engineering module for converting raw and unstructured data into features such as assignment completion time, quiz attempts, and interaction frequency.
2. A method for predicting student engagement and academic performance in online courses, as claimed in claim 1, wherein the method comprising the steps of:
(a) preprocessing educational datasets including student VLE interaction, assessments, and course information;
(b) training one or more machine learning models on the processed data;
(c) testing the trained models to determine accuracy, precision, and recall; and
(d) evaluating the best performing model for predicting student outcomes.
3. The method as claimed in claim 1, wherein the machine learning model is selected from a group consisting of Random Forest (RF), MultiLayer Perceptron (MLP), and kNearest Neighbors (KNN), wherein the Random Forest model provides superior prediction accuracy and recall for student performance forecasting.
4. The method as claimed in claim 1, wherein further comprising generating predictive analytics using the trained model to identify at-risk students and provide timely alerts and interventions.

5. The method as claimed in claim 1, wherein further comprising a feedback and recommendation engine configured to deliver personalized insights, learning resource suggestions, and performance feedback through a dashboard and reporting interface for use by educators and administrators.