Hi all!
I would like to kindly ask you a question regarding the Product10k dataset format. More precisely, in the train.csv file provided, each product has a class and associated group. The group id should be enough to compute the products’ hierarchical structure. More precisely, in the paper, it’s specified that there are ten macro groups to which products belong.
However, it is not very clear to me how we can actually compute these 10 groups from the 300 and more group labels in the csv file.
Thank you in advance for your time and help!
Have a nice day!