(2nd video) Android APK Demonstration: https://youtu.be/7O6C0F0uVYg
Some of us took part in volunteer teaching, and there was one key issue we realised that prevented volunteer teaching services from scaling up and impacting more students:
Tutors and tutees aren’t matched effectively.
This could be due to:
- Differences in skill level
- Differences in interests or personalities
- Small user-base
We believe that if we match students to tutors based on other factors like interests or personality, we can make the experience of teaching/learning better for both tutors and students! This in turn would:
- Incentivise tutors to keep teaching and tutees to keep learning
- Attract more tutees and tutors
- Benefit more students by providing accessible volunteer teaching services!
What it does
Tutoree makes use of machine learning matching algorithms to make optimal matches between private tutors and tutees, ensuring maximum customer satisfaction at a minimal cost.
How we built it
- We built the backend database to store all user data on SQLite and Java. To integrate it into Android, we used the open source library SQLDroid (to enable DriverManager and JDBC to work).
- We built the backend machine learning model (to match tutors and tutees together based on computed compatibility) using TensorFlow and Keras. To integrate it into Android, TensorFlow Lite was used.
- We designed the user interface on Figma, which is also used for the video demonstration.
- We built the frontend in Android Studio, referencing from Figma and integrating the backend SQLite database with the machine learning model. It is not complete yet however.
Challenges we ran into
- Had to learn a new language while working on the code
- SQLite: The schema was not planned out in full, so the fields and attributes kept changing; Integration of the SQLite into Android also posed a problem and we took a while to find the SQLDroid solution
- Android Studio: Implementing UI elements from Figma fast was a real challenge. Many animations that we wanted on Figma was not trivial to do in Android Studio.
Accomplishments that we're proud of
- We worked on this whilst balancing the daily workload of lectures and assignment submissions
- First hackathon for half the group!
What we learned
- Programming in Kotlin and working with Mobile App development
- Integrating databases with other code
- Process of software development, from deciding on problem statements to making use cases to narrowing down on the important features
- How to import UIs from figma into Kotlin
- Learnt what a hackathon is about and how to collaborate with a team on a project on a tight deadline
What's next for Tutoree - Private tuition platform with no middleman charges
- Include a larger number of factors to increase the accuracy of our data
- Make our User Interface
- (RippleMatch) Best Hack for College Students Looking for Jobs or Internships Private tuition is one of the most accessible ways college students can put their very recent skills sets to use, through Tutoree, college students can earn good pocket money while the tutees can get the most up-to-date information.
- (Facebook) Building Community and Bringing the World Closer Together in a COVID-19 World Our app aims to bring tuition matching online for a closer experience for private tutors and tutees.