With the help of historical school-related data, an AI solution can provide forecasts for future high school eligibility. The method can also identify relationships and effects between results and various factors. How can we use the kind of insights to adapt the support our students need to reach high school eligibility?
The school is a data-intensive business. With the help of data analysis, we can create better conditions for measuring the quality and improving the learning of our children and students.
Data analysis gives us a more nuanced picture of the results in relation to various factors. Politicians, administration, principals and educators can work more effectively with interpreting and transforming the results into measures while receiving feedback on the efforts that have already been made.
With the help of data-driven school development, we can:
- Increase the opportunity for more children and students to reach their maximum potential
- Increase goal fulfillment in school
- Increase eligibility for and throughput in high school
- Get a school that rests on a scientific foundation and proven experience
We use machine learning models to analyze different types of data from different perspectives; principal, unit and student level. The technology helps us to automate and visualize analysis results and we use support from research to interpret and implement the results.
Some examples of data used and analyzed:
- Grading results for all subjects
- Pupil and teacher survey linked to chapter 2 in the curriculum (School Temp)
- Results of digital mathematics tests in years 2, 4, 5, 7 and 8
- Staff turnover
- Sick leave
- Employee survey (HME)
- Building materials
- Proportion of students with a foreign background
- Proportion of students with parents with a university degree