.jpeg)
ABOUT
The IBL AI Platform includes the four needed stages of analytics:
- Descriptive — What happened?
- Diagnostic — Why did it happen?
- Predictive — What will happen?
- Prescriptive — What should I do?
IBL’s AI works through exclusive algorithms and data models by measuring and scoring learners’ engagement, performance, including scenarios of student success and at risk.
Moreover, IBL AI Analytics examines footprints left by students and teachers across multiple learning platforms and environments.
It allows educators to gain invaluable insights, enable research, and discover answers to complex questions about the way instruction has been delivered. It also enables to predict upcoming scenarios and prescribe efficient learning pathways.
The AI/ML–based language models technology — which is behind the Internet phenomenon Chat GPT — is used to make data predictions about future learning patterns.
The language models are provided with historical data to identify patterns and trends. They are able to understand and make use of the context and relationships within large sets of data, texts, and images.
For example, student demographics, past test scores, student attendance, transcripts, grades, disciplinary records, and other relevant information. Afterward, the models are able to predict how well a student is likely to perform in the future.
Along with student performance, the IBL AI Analytics Platform predicts student success.
It also identifies students who may be at risk of falling behind or dropping out of school. The system provides them with a clear solution, including personalized content recommendations, resources and instructional support to help them succeed.
In all examples, the language models are fine-tuned for specific tasks, such as predicting student success in a specific course, program or major, or even a student’s likelihood of graduating in a specific school.
Built on a language model-agnostic layer (not only OpenAI's but Google's open source e.g. Bloom and others like GPT-J), IBL's language models are used for many more applications seeking to empower instructors and students:
Moreover, IBL AI Analytics examines footprints left by students and teachers across multiple learning platforms and environments.
It allows educators to gain invaluable insights, enable research, and discover answers to complex questions about the way instruction has been delivered. It also enables to predict upcoming scenarios and prescribe efficient learning pathways.
The AI/ML–based language models technology — which is behind the Internet phenomenon Chat GPT — is used to make data predictions about future learning patterns.
The language models are provided with historical data to identify patterns and trends. They are able to understand and make use of the context and relationships within large sets of data, texts, and images.
For example, student demographics, past test scores, student attendance, transcripts, grades, disciplinary records, and other relevant information. Afterward, the models are able to predict how well a student is likely to perform in the future.
Along with student performance, the IBL AI Analytics Platform predicts student success.
It also identifies students who may be at risk of falling behind or dropping out of school. The system provides them with a clear solution, including personalized content recommendations, resources and instructional support to help them succeed.
In all examples, the language models are fine-tuned for specific tasks, such as predicting student success in a specific course, program or major, or even a student’s likelihood of graduating in a specific school.
Built on a language model-agnostic layer (not only OpenAI's but Google's open source e.g. Bloom and others like GPT-J), IBL's language models are used for many more applications seeking to empower instructors and students:
- Chatbot-based instructors (trained on specific courses so they only answer based on certain transcripts, not across the board)
- Generation of lessons and learning components
- Learning path and content recommendations
- Predictive and prescriptive learning analytics
- Grading of text-based submissions from students
- Automatic transcripts and language translations
Please contact IBL’s Engineering Department to incorporate and customize these solutions, following your analytics, AI/ML and business needs. Visit our Help Website to learn more or engage with our AI Agent ‘Anne’ now.
