Wainu : Automated Data Analysis and Reporting System for Enhancing Educational Funding
Kivelä, Manu (2024)
2024
All rights reserved. This publication is copyrighted. You may download, display and print it for Your own personal use. Commercial use is prohibited.
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi:amk-2024122438118
https://urn.fi/URN:NBN:fi:amk-2024122438118
Tiivistelmä
In 2023, WinNova, one of Finland's largest vocational education providers with approximately 5,000 students and 600 staff members, faced a significant shortfall in effectiveness-based funding. Despite its size, WinNova received only €11,164, compared to €200,000 received by a smaller institution. Investigations revealed that incomplete and incorrect apprenticeship and training contracts within Studenta, the student management system, hindered the generation of essential workplace feedback links required for funding.
This thesis presents the development and implementation of Wainu, an automated data analysis and reporting system designed to enhance data accuracy in Studenta by validating contracts. Wainu integrates with Studenta's PostgreSQL database, applies rule-based validation to identify errors, and notifies responsible teachers with detailed instructions for corrections. Key technologies used include Python, FastAPI, Pydantic, Azure services, and a custom WinNova-Python library.
Post-deployment, Wainu reduced faulty contracts by approximately 69%, decreasing the error rate from 27.97% to 8.74% within two months. Consequently, WinNova's effectiveness-based funding increased dramatically from €11,164 to €618,435—a 4,397% improvement—with projections exceeding €1 million for 2025. The system streamlined processes, improved user engagement, and underscored the critical role of data accuracy in funding outcomes. Challenges encountered included optimizing performance for large datasets, integrating with existing systems, and addressing user adoption resistance.
The success of Wainu demonstrates the potential of automated data analysis in educational management, emphasizing the importance of technology-driven solutions in optimizing funding and operational efficiency. Future enhancements aim to expand its functionalities, including advanced analytics and broader system integrations, to further support WinNova's strategic objectives.
This thesis presents the development and implementation of Wainu, an automated data analysis and reporting system designed to enhance data accuracy in Studenta by validating contracts. Wainu integrates with Studenta's PostgreSQL database, applies rule-based validation to identify errors, and notifies responsible teachers with detailed instructions for corrections. Key technologies used include Python, FastAPI, Pydantic, Azure services, and a custom WinNova-Python library.
Post-deployment, Wainu reduced faulty contracts by approximately 69%, decreasing the error rate from 27.97% to 8.74% within two months. Consequently, WinNova's effectiveness-based funding increased dramatically from €11,164 to €618,435—a 4,397% improvement—with projections exceeding €1 million for 2025. The system streamlined processes, improved user engagement, and underscored the critical role of data accuracy in funding outcomes. Challenges encountered included optimizing performance for large datasets, integrating with existing systems, and addressing user adoption resistance.
The success of Wainu demonstrates the potential of automated data analysis in educational management, emphasizing the importance of technology-driven solutions in optimizing funding and operational efficiency. Future enhancements aim to expand its functionalities, including advanced analytics and broader system integrations, to further support WinNova's strategic objectives.