Scribd
Upload
17 views13 pages

Movie Recommendation Presentation

Uploaded by

dheeraj kumar
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
17 views13 pages

Movie Recommendation Presentation

Uploaded by

dheeraj kumar
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 13

Movie Recommendation System

using Python
Developed using TMDb dataset and
Streamlit for Frontend
Submitted by: [Your Name]
Date: [Presentation Date]
Introduction
• • Movie recommendation system developed
to suggest movies based on user preferences.
• • Data sourced from TMDb on Kaggle,
containing 5000 movies.
• • Machine Learning techniques used for
recommendations.
• • Frontend developed using Streamlit for
interactive user experience.
Objectives
• • Build an intelligent system that recommends
movies based on input preferences.
• • Implement text-based filtering using Count
Vectorization.
• • Provide a user-friendly interface via
Streamlit.
Dataset Overview
• • Source: TMDb dataset from Kaggle.
• • 5000 movies with details like title, genres,
overview, and ratings.
• • Columns used: Title, Overview, Genres,
Keywords, Cast, Crew, etc.
Data Preprocessing and Filtering
• • Removal of missing data and duplicates.
• • Extracted relevant features (Title, Overview,
Genres, etc.).
• • Data normalization and handling categorical
variables.
Feature Extraction
• • Applied Count Vectorization to convert text
into a matrix of token counts.
• • Transformed textual data into numerical
form for machine learning.
Machine Learning Model
• • Cosine similarity used to find similar movies
based on vectorized text.
• • Recommendations generated by matching
user-selected movies with others based on
similarity.
Frontend with Streamlit
• • Created an interactive web application using
Streamlit.
• • Users input a movie title, and the system
provides top recommendations.
• • Simple and clean UI for user-friendly
experience.
Challenges Faced
• • Handling large datasets efficiently.
• • Data cleaning for 5000 movies.
• • Real-time recommendation system with
Streamlit frontend.
Results and Output
• • Example of movie recommendations
displayed.
• • Discuss accuracy and relevance of
recommendations.
Future Improvements
• • Implement more advanced NLP techniques
(e.g., TF-IDF or BERT).
• • Incorporate user ratings for personalized
recommendations.
Conclusion
• • Built a recommendation system using
Python and TMDb dataset.
• • Combined machine learning with a user-
friendly Streamlit frontend.
Thank You
• • Open for questions.

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy