The concept of embedding, that is mapping categorical values to vectors, is used to find the relationship between books and use it for recommendation.
Dataset link - https://drive.google.com/drive/folders/1O49Bam3TbtfdLs8e9__75nVYVtKwUjDB?usp=sharing
All the codes and required files and dataset are attached. Go through the data_processing folder first, then continue with dataset_creation. Finally, move to Model_training folder where first execute model_creation_training.ipynb, then Embedding Extraction.ipynb followed by Finding_Similar_Books.ipynb.
data_processing and dataset_creation can be skipped as the resources created by these files are also attached here. Fully trained model is also attached to the drive link for reference.