BingeNite
Don’t know what to watch? Need new songs to listen to? Based on your mood and preferred genre, our project will predict the perfect new movie/song for you!
Created on 11th February 2024
•
BingeNite
Don’t know what to watch? Need new songs to listen to? Based on your mood and preferred genre, our project will predict the perfect new movie/song for you!
The problem BingeNite solves
The main purpose of BingeNite is to generate customized lists of entertainment media based on the user's mood and desired genre. Our website implements multiple datasets obtained from the Kaggle database website. To parse data from datasets, we used optimized Javascript algorithms and filtered the dataset based on user preferences. After obtaining a customized list of media for the user, we’ll be displaying contents using React.js and CSS styling.
Our inspiration for this project stemmed from the desire to create a personalized experience for users seeking entertainment recommendations. We recognized the abundance of movie and song datasets available on platforms like Kaggle and saw an opportunity to implement machine learning algorithms to customize suggestions based on user mood and preferred genres. Our website provides relevant recommendations, enhancing user engagement and satisfaction.
Challenges I ran into
One of the main challenges was handling and preprocessing large datasets, as well as fine-tuning the machine learning algorithms to accurately predict user preferences while balancing model complexity and performance.
Our project was built using a combination of Python, machine learning libraries such as scikit-learn and TensorFlow, and web development technologies like HTML, CSS, and JavaScript. We started by exploring and preprocessing movie and song datasets from Kaggle, extracting relevant features, and training machine learning models to predict user preferences based on mood and genre selections. We then developed a web application using React to serve as the interface for users to input their mood and genre preferences and receive personalized recommendations.
Throughout the project, we worked with data processing, machine learning, and web development, to preprocess and analyze large datasets, implement machine learning models for recommendation systems, and integrate them into a web application.
Tracks Applied (1)