Asgn.
Streamlining assignment management for a better learning experience
Created on 25th February 2023
•
Asgn.
Streamlining assignment management for a better learning experience
The problem Asgn. solves
The Assignment Dispersal System is a software application designed to address the problem of assigning and tracking assignments in educational institutions. This system provides a centralized platform for teachers and administrators to manage assignments efficiently. The system aims to simplify the assignment process by automating certain tasks, reducing paperwork and manual work, and improving the communication between teachers and students.
One of the key components of the system is the machine learning model that predicts the ideal due date for each assignment based on the assigned workload and task difficulty. By taking these factors into account, the model can accurately predict a due date that is feasible and reasonable, reducing the likelihood of conflicts arising due to unrealistic deadlines.
Another significant problem that the Assignment Dispersal System addresses is the lack of transparency in the assignment process. Students often struggle to keep track of their assignments and due dates, which can lead to missed deadlines and poor performance. The system provides students with a centralized platform to access all their assignments and related information, including due dates, progress reports, and feedback from teachers. This helps students stay organized, plan their workload effectively, and improve their academic performance.
The Assignment Dispersal System offers a comprehensive solution to the assignment management problem in educational institutions. By providing an efficient and transparent platform for teachers and students, the system aims to improve the quality of education and reduce the administrative burden on teachers.
Challenges we ran into
Data quality: The accuracy of the data entered into the system is critical to its functioning. If the data is incorrect, the ML model will provide inaccurate predictions, which can cause problems in assignment management. Most of our time went to configuring, cleaning and finding patterns in the data.
Model accuracy: While machine learning can be incredibly accurate, the model must be trained correctly and provided with sufficient data to make accurate predictions. If the model is not accurate enough, the system will not be reliable. We tried various models and the highest we achieved in this short amount of time is 76%.
Tracks Applied (2)