I am new to ML and still learning it.
My problem is to identify duplicate products. I have a dataset containing product details such as name, colour, size, description, features etc (there are roughly 70 columns).
I need to remove duplicate products.
I just completed some of the supervised ML model(classification and regression) and unsupervised clustering(K means and HC). I am also on the way of learning w2v and d2v.
But due to time constrain, I need to deliver a solution to the above problem statement. I am unsure as to how to proceed.
Any help and guidance would be appreciated