Hey! I’ve worked with the amazon home and kitchen dataset for a school project, and it was a great learning experience. One thing I noticed is that products with more images tend to sell better.
For cleaning, I used Trifacta to automate a lot of the preprocessing. It’s a bit pricey but super efficient. Also, if you’re into NLP, spaCy is great for analyzing product reviews.
For cleaning, I used Trifacta to automate a lot of the preprocessing. It’s a bit pricey but super efficient. Also, if you’re into NLP, spaCy is great for analyzing product reviews.