The material is a industry list. And we provide 10 sample description text for most of them. The text is about some business for sale or investment projects. We need some one to use machine learning and natural language to build a classification script. But we hope the script can classify some other kind of text, such as news, summary, etc. So NLP might be as import as the machine learning.
We know the amount is far from enough to do some machine learning with good results. That's why we need some help.
For some of the industries, we didn't find enough text (red-color area), Just do it with less sample. And we will try fill them later.
Some description will appear in multiple industry, Such as a plastic company, their products are for automotive industry. So they will be both "Plastic" and "Automotive general parts"
We need some one to train the machine with the material, and result we need is that after we input a "description" and it can tell us which industry(industries) it is.
And you might needs to deal with the following situation:
"A furniture manufacturer, they are selling themselves with the real estate and they have a rental vehicle."
Their industry should be only "Household Light Industry" instead of "Household Light Industry, Real Estate, Automobile service and leasing"
We have more text material, but they are not classified. If you think they are also helpful. Just let us know.
