EffortEstiMate

Inspiration

The main inspiration behind building this tool comes from personal experiences with the challenges of academic workload. Students often juggle multiple assignments at once, struggling with time management and frequently racing against deadlines. Many end up submitting work at the last minute—or even after the deadline—despite their efforts. This tool aims to address that need, helping students boost productivity and manage their time more effectively with minimal effort.

What it does

This tool allows students to upload their assignment PDF, which is then analyzed based on a set of predefined metrics designed to assess factors like complexity, reports submisison,task requirements. Using these insights, our AI model predicts the estimated hours needed to complete the assignment. By providing a personalized time estimate, this tool helps students better manage their workload, prioritize tasks, and make more informed study plans. The goal is to minimize time management guesswork, allowing students to approach each assignment with confidence and focus.

How we built it

We built this tool using Flask for the user interface, providing a seamless and interactive experience for students. On the backend, Python powers the modeling processes and handles text extraction from assignment PDFs. Additionally, we integrated the Gemini API to generate relevant metrics for analyzing assignment complexity, structure, and other key factors. This combination of technologies allows us to provide accurate, data-driven time estimates for completing assignments, making it a valuable productivity tool for students.

Challenges we ran into

We faced three major challenges in building this tool: defining the metrics to accurately predict hours, sourcing data to train our model, and integrating the UI with the backend. Defining Predictive Metrics: Identifying the right metrics to estimate completion time was crucial. To solve this, we established a set of core metrics for assessing each assignment, such as complexity, length, and topic familiarity. Data for Model Training: Training the model required a realistic dataset, which was initially a challenge. We addressed this by generating synthetic data ourselves and leveraging Mockaroo to create a diverse dataset that represented different assignment types and difficulties. UI and Backend Integration: Merging our Flask-based UI with the Python backend for a cohesive user experience was our final challenge. We focused on ensuring smooth, responsive interactions, allowing users to upload PDFs, analyze assignments, and receive time estimates seamlessly. By overcoming these challenges, we developed a robust tool to help students better manage their workload and boost productivity.

What we learned

Throughout the project, we gained valuable technical and non-technical skills. On the technical side, we honed our ability to train a model using demo data, iteratively refining it to improve prediction accuracy. We also developed expertise in using Flask to build an intuitive and responsive user interface, ensuring a seamless user experience.

On the non-technical side, we learned how to work effectively under pressure and meet tight deadlines, sharpening our time management and problem-solving abilities. Additionally, we gained valuable teamwork experience, collaborating closely to overcome challenges and integrate our different skill sets into a cohesive solution.

What's next for EffortEstiMate

The future scope of EffortEstiMate lies in expanding its capabilities to support students and professionals in managing multiple parallel assignments. Building on the current model, we aim to integrate features that allow users to create a personalized, dynamic schedule based on their availability, preferred time slots, and assignment deadlines. The tool will not only predict the effort required for each task but also prioritize assignments and suggest the most efficient study plans. With these enhancements, EffortEstiMate will evolve into a comprehensive time management assistant, helping users optimize their productivity and balance their workload with greater ease and precision.