Song Recommender

Inspiration

The inspiration for the Song Recommender came from the desire to create a personalized music recommendation system that takes into account not only the user's preferred genre but also their favorite artists, preferred decade, and current mood.

What it does

The Song Recommender is a smart algorithm that analyzes the user's music preferences and provides personalized song recommendations based on genre, artist, decade, and mood, creating a seamless and tailored music experience.

How we built it

We built the Song Recommender using Python and leveraged data analysis techniques, including CountVectorizer and cosine similarity, to calculate the song similarities based on various attributes. We also integrated user input to make the recommendations more personalized.

Challenges we ran into

One of the main challenges we faced was extracting the decade from song titles, especially when some titles contained spaces. To overcome this, we used regular expressions to find the decade in the song titles accurately.

Accomplishments that we're proud of

We are proud to have created a functional and user-friendly music recommender that goes beyond the usual genre-based recommendations, offering a more nuanced and enjoyable listening experience.

What we learned

During the development process, we gained valuable experience in working with data analysis techniques and leveraging user input to enhance the user experience. We also learned how to handle potential issues in extracting information from song titles.

What's next for Song Recommender

In the future, we plan to expand the Song Recommender's capabilities by integrating additional factors, such as song lyrics analysis, user feedback, and social media data, to provide even more accurate and tailored music recommendations. Additionally, we aim to develop a user-friendly web or mobile application for broader accessibility and convenience.

Built With

• python