FHShubho/Anime_Recommender

Anime Recommender - Recommending similar anime using unsupervised KNN and K-Means

Anime Recommender

Recommending similar anime using KNN and K-Means

CSE445 Course Project and my first Machine Learning Project.

It's a content based recommender that recommends similar anime based on the similarities of anime information like source, type, genre, episode, rating, fanbase.

Dataset

• https://www.kaggle.com/aludosan/myanimelist-anime-dataset-as-20190204
• https://www.kaggle.com/marlesson/myanimelist-dataset-animes-profiles-reviews?select=profiles.csv

Algorithms

• Unsupervised K Nearest Neighbors
• K-Means

References

• https://scikit-learn.org/stable/modules/clustering.html
• https://medium.com/@haataa/how-to-measure-clustering-performances-when-there-are-no-ground-truth-db027e9a871c#:~:text=The%20Calinski%2DHarabasz%20index%20also,score%20%2C%20the%20better%20the%20performances