Anime Recommendation System

Anime Recommendation System

Recommends anime from your tastes or a title you liked, using collaborative, content-based and popularity-based methods. A Streamlit app for anime fans and for people studying recommenders.

Made by krishnaveni76 on Hugging Face. These notes are Mindket's, written from its Space page and README; the app's own files and license are on Hugging Face.

About

What it is: This is an anime recommender that mixes three approaches. One learns from other people's ratings, one matches titles by their features, and one ranks titles by popularity. It draws on the AnimeList 2023 dataset, trimmed to titles with an average rating above 6.0 to save compute and storage. It is a Streamlit app hosted on Hugging Face, so you can try it in a browser with nothing to install.

Who it suits: Anime fans who want suggestions, and students or developers who want to see a full recommender with data ingestion, models and a web front end.

Industry | Who uses it | How they use it | Example
Entertainment | Anime fans | Get titles similar to ones they liked | Ask for shows like a favorite title
Machine learning | Students | Study three recommendation methods in one project | Read how SVD and KNN models are set up
Software | Developers | Look at a dockerized pipeline from ingestion to app | Read run_pipeline.py and the Dockerfile
Media | Curators | Browse lists ranked by popularity measures | Open a most-favorited list

Anyone who wants recommendations for something other than anime can skip it.

Where to use it: It runs in these places.

• A web browser, on the Space's page at Hugging Face
• Windows, with Python
• macOS, with Python
• Linux, with Python
• Docker, since the repository includes a Dockerfile

Use case | Who | What they get back
Find similar anime | Fans | Titles close to one you liked
Get personal suggestions | Fans | Titles that people with similar tastes rated well
Browse by popularity | Anyone | Ranked lists such as most popular or top rated

How to set it up: Using the Space online needs only a browser. A copy on your own computer needs the following.

• Python and pip
• The huggingface_hub package, which gives you the hf command
• Disk space for the repository, which holds 39 files

1. Install the huggingface_hub package.
2. Download the Space's files into a local folder.
3. Move into that folder.
4. Install Streamlit at the version the Space uses, then install the packages in requirements.txt.
5. Start the app with Streamlit.

pip install -U huggingface_hub
hf download krishnaveni76/Anime-Recommendation-System --repo-type space --local-dir Anime-Recommendation-System
cd Anime-Recommendation-System
pip install streamlit==1.41.1
pip install -r requirements.txt
streamlit run app.py

How to use it: Open the Space's page, or run the app on your computer and open the page Streamlit shows. Then pick a recommendation approach or a popularity list. The table lists the methods the project describes.

streamlit run app.py

Tool | What it does
SVD | Factors the user and title rating matrix to give personal picks
Item-KNN | Finds titles that users rated like a title you give it
User-KNN | Suggests titles liked by users with tastes like yours
Content-based model | Matches titles by features such as genres
Most Popular | Ranks titles by popularity score
Top Ranked | Ranks titles by their official ranking
Overall Top Rated | Sorts titles by average user rating
Most Favorited | Lists titles that fans marked as favorites most often
Highest Member Count | Lists titles with the biggest audience
Popular Among Members | Lists titles with many members and strong ratings
Highest Average Rating | Lists titles by average rating after missing values are handled

Example: You give the app an anime you enjoyed and ask for similar titles. It returns a list of shows that viewers with similar ratings also liked, or shows with similar genres.

For newcomers and experts: A recommender guesses what you will like from what other people liked or from what a title is like. The first small thing to try is opening one of the popularity lists in the online Space.

Collaborative filtering uses ratings, and the project offers SVD plus item-based and user-based nearest neighbors. Content-based filtering uses extracted features such as genres. The pipeline loads data from Hugging Face datasets, transforms it, trains the chosen model and stores it as an artifact. The app fetches data and trained models from the Hub.

Data is loaded from Hugging Face datasets
It is cleaned and features are extracted
A recommendation model is trained and saved
The Streamlit app serves the recommendations

Good to know: Titles with an average rating of 6.0 or lower are left out of the data.

• License: apache-2
• Cost to run: none named
• Data it reaches: datasets and trained models that the app fetches from the Hugging Face Hub
• Hardware: the Space is set to cpu-basic at Hugging Face, and what your own computer needs is not stated

On Hugging Face, 13 November 2026

• Likes: 9
• Built with: streamlit
• License: apache-2.0

Links

• Space: https://huggingface.co/spaces/krishnaveni76/Anime-Recommendation-System
• Files: https://huggingface.co/spaces/krishnaveni76/Anime-Recommendation-System/tree/main

Try it

Open the Space in your browser, or copy it to your own Hugging Face account from its page. Nothing in this kit runs by itself.