This project is a movie recommender system built using Streamlit. It suggests movies based on user preferences, aiming to provide personalized movie recommendations. The goal is to create a visually appealing and user-friendly application.
1> Personalized Recommendations: Get movie suggestions based on user inputs
2>Interactive UI: Built with Streamlit for an intuitive and engaging user experience
Through developing this movie recommender system, I have gained valuable insights and skills in several areas:
Learned the fundamentals of how recommender systems work and the different approaches such as collaborative filtering and content-based filtering.
Gained hands-on experience with Streamlit, a powerful tool for creating interactive web applications in Python.
Improved skills in data cleaning, processing, and analysis to ensure accurate and relevant recommendations.
Enhanced my ability to design intuitive and user-friendly interfaces that improve the overall user experience.
Techniques used
1>Stemming
2>Removing Stop Words
4>TOKENIZATION
3>Bag of Words Technique
4>Cosine Similarity Score
Stemming: Applied stemming to reduce words to their base or root form, improving the consistency of text data.
Removing Stop Words: Removed common stop words to reduce noise and focus on the significant words in the dataset.
Bag of Words Technique: Utilized the bag of words technique to convert text data into numerical format, enabling the application of machine learning algorithms.
Cosine Similarity Score: Employed cosine similarity to measure the similarity between movies based on their textual features, enhancing the accuracy of recommendations.
Developed better project management skills by organizing code, managing dependencies, and maintaining clear documentation.
1> Python
2> Streamlit
3> Pandas
4> Matplotlib
5> Seaborn
6> NLP libraries (such as NLTK )