Inspiration
Our inspiration was our love for anime, we also got inspiration from an organizer who said she did a book recommendation project, so we decided to create a program for recommending anime using machine learning and an API.
What it does
Basically, the program takes 5 anime you like and 5 you dislike then 5 you haven't yet watched. Based on the positives and negatives the machine would decide whether it would be something you would like or dislike.
How we built it
We used a machine-learning algorithm and API to create this program using count vectorizer and used test cases for the machine to "learn" what is good or bad then use
Challenges we ran into
The challenges we faced were definitely implementing the machine learning algorithm and using the MyAnimeList API. This API required a lot of access codes and keys that the website needed to confirm which would take too long, therefore we decided to use another API that implemented MAL and allowed us to use the data we needed.
Accomplishments that we're proud of
We are proud of being able to create this project that is fully functional and working. To be able to use different API's and implement a machine learning algorithm is something we are happy to have learned during this hackathon and definitely use in the future.
What we learned
We learned how to use API's and machine learning algorithms in our code using python and implement it to recommend anime.
What's next for Anime Recommendation Project
Creating this project in around a day definitely limited us to what we could do. We can definitely add more features and data for better machine learning and better user experience like making an interface.
Log in or sign up for Devpost to join the conversation.