Book Recommender System

Data Science Seminar Project

Recommending books using a Recommender System based on goodreads.com data from the UCSD Book Graph¹

Steps needed:

Data Preparation: Downloading Data, reading into Pandas DataFrames
Data Cleaning and Preprocessing: Keeping only needed data, string cleanup, etc.
Data Model Creation: creating Word Embeddings from item data like title, description, authors, etc.
Recommender System Model Creation: selecting a Neural-Network-based recommender system, e.g. NCF, WDN, DCN, etc.
RS Training
RS Evaluation

Optional:

combining the Book data with another dataset from a different domain, e.g. MovieLens 25M² to create a multi-media recommender system, suggesting books based on movie preferences and vice versa.
this would need more text processing to find similarities between the datasets, e.g. by extracting tags from movies and matching them to book descriptions and goodreads shelf-names

=> this idea has since been scrapped, since it's out of reach in the scale of this student project.

this repo needs some cleanup, main file is the keras_dcn.ipynb Notebook

Mengting Wan, Rishabh Misra, Ndapa Nakashole, Julian McAuley, https://sites.google.com/eng.ucsd.edu/ucsdbookgraph/home. ↩
F. Maxwell Harper and Joseph A. Konstan, https://grouplens.org/datasets/movielens/25m/ ↩

Name		Name	Last commit message	Last commit date
Latest commit History 47 Commits
documentation		documentation
.gitattributes		.gitattributes
.gitignore		.gitignore
01_data_preparation.ipynb		01_data_preparation.ipynb
02_feature_processing.ipynb		02_feature_processing.ipynb
README.md		README.md
collaborative_filtering.ipynb		collaborative_filtering.ipynb
email_callback.py		email_callback.py
goodreads.ipynb		goodreads.ipynb
goodreads_colab.ipynb		goodreads_colab.ipynb
keras_dcn.ipynb		keras_dcn.ipynb
wide_and_deep.ipynb		wide_and_deep.ipynb