Amazon-Product-Classifier-and-Recommendation-UCSD-Dataset

Apply classic ml algorithm for text embeddings and classifier, apply recommendation model for building recommendation system

Dataset Link

http://jmcauley.ucsd.edu/data/amazon/

NLP libraries

In order to save time, I use the spacy module, which has built-in functionality to calculate the average vector of a sequence of words.

While in another project named Stocksight, NLTK module has been applied. The link below shows the difference between these two:

https://medium.com/@akankshamalhotra24/introduction-to-libraries-of-nlp-in-python-nltk-vs-spacy-42d7b2f128f2

What's more, there are other famous NLP libraries worth mentioning. It can be checked out as follows:

https://elitedatascience.com/python-nlp-libraries

Evaluation metrics

As for the evaluation metrics, it's important to understand the difference between all metrics. Here is a good reference (in Chinese though):

https://www.cnblogs.com/futurehau/p/6109772.html

Recommendation System

A really good slide for recommendation system - Tensorrec: https://www.slideshare.net/JamesKirk58/boston-ml-architecting-recommender-systems

Ans here is the sourde code of Tensorrec:

https://github.com/jfkirk/tensorrec

Embedding

Hyperparameter tuning for size of embeddings plays a significant role in filtering recommendation model. This article introduces the function of embedding layer (in Chinese):

https://blog.csdn.net/u010412858/article/details/77848878

Collaborative-filtering and Content-based-filtering

A clear introduction about the difference between these two:

https://www.quora.com/What-is-the-difference-between-content-based-filtering-and-collaborative-filtering