Inspiration

Our inspiration for this project was to create a data-driven platform that supports aspiring YouTubers in improving how they present their content. We noticed that many new creators struggle to understand how the YouTube algorithm works, particularly when it comes to optimizing titles, timing, and overall presentation. This motivated us to build a tool that makes these insights more accessible.

What it does

The project is intended to support new and upcoming youtubers by teaching them how to present their youtube videos in a way that takes advantage of its algorithm using the 2026 data analytics. This includes recommendations for improving their title, as well as the day and time the video should be uploaded in order to improve its virality.

How we built it

This project was built starting with cleaning the datasets to be more refined in their nature using RStudio code to filter out unnecessary sections such as the dislike count etc. We then brainstormed what to do with regards to the code logic and used AI such as Claude Opus 4.7 to generate our programming syntax which we further formatted and edited into our final code for the website.

Challenges we ran into

While the group provided excellent ideas, we have little programming experience. Therefore, we planned out our programming logic and used Claude Opus 4.7 to generate our programming syntax which we further formatted and edited into our final code for the website.

Accomplishments that we're proud of

We are proud of collaborating together as a team to turn our concept into a working prototype despite having a limited technical experience. We effectively cleaned and utilised real-world data to build a functional prototype that provides some meaningful insights for aspiring content creators.

What we learned

We learnt the importance of cleaning datasets to refine data to build a meaningful prototype while also improving our teamwork, planning and problem-solving skills.

What's next for HTPML

In the future, we plan to improve the accuracy and depth of our recommendations by incorporating larger and more diverse datasets.

Share this project:

Updates

Submission history