NB: Due to the nature of this project, code cannot be shared publicly.
The main aim of this project was to build a Movie Recommender System that used Machine Learning to accurately recommend movies to users based on their interests and similar interests of other users.
With the popularity of cloud-based streaming services maintaining user retention without subjecting users with content overload when observing content available on their respective platforms is important thus a need for a robust recommender system that will provide users with personalised suggestion based on movies they have previously liked and other users with similar interests.
- Analyse and identify key insight in the Movies dataset (Jupyter Notebook)
- Create a movie recommender system (Jupyter Notebook)
- Create a user-friendly Movie Recommendation app (Streamlit)
- Report findings (PowerPoint presentation)
- Python (Jupyter Notebook, Streamlit (VScode), scikit-learn, nltk, surprise)
- Comet
- Github
- AWS EC2 and S3 bucket
The following is a sample of the analysis and insights drawn whilst working on the project
Through our exploration of the data, spanning as far back as the 1930s,a captivating trend emerged. The genres of drama and comedy took center stage, as the most popular choices among the vast array of movies produced. Their relatability has captivated audiences throughout the ages, making them beloved classics that continue to charm and entertain movie lovers.
We also found that the famous director Quentin Tarantino has directed the most highly rated movies to date. Which prompts us to further investigate what makes him more popular than other well known directors like stephen king and james cameroon. we discovered that it is his Unique Vision and Style as well as his Originality that has made his work stand out and leave a lasting impression with his viewers.
0227.mp4
Mantsali Sekoli - @Mantsali
Fatima Hassan - @fatimahassan99
Gideon Odekina - @godekina
Solomon Balogun - @manlikesolomon
Abeeb ADESINA - @deolabeeb
Tharollo Tevin Dikgale - @tevindikgale
Link to Kaggle competition - https://www.kaggle.com/competitions/edsa-movie-recommendation-predict