I'm training a model with AI Builder to process invoices from 29 suppliers.
There are many invoices, and most have multiple sheets. I'd like to know how to train the model to work well with one or many sheets per invoice per supplier.
The collections are categorized by supplier, and I'm loading an average of 9 invoices per supplier, including invoices with more than 5 sheets.
Currently, it has a score of 81, and I'm noticing that some suppliers have a score below 80.
Should I load more invoices for those suppliers and continue training it?
What recommendations can you share?
Do you recommend loading more invoices with multiple sheets because the product table is long?
When training, do you recommend selecting all the products on each sheet?
Modelo V2 Collect...
Modelo V2 Collect...
Your file is currently under scan for potential threats. Please wait while we review it for any viruses or malicious content.
Based on what you show, I would train on more data especially for the vendors that have low overall scores. While the overall score may be 81, you have an outlier supplier with a score of 99. If you remove the high and low overall scores, it drops to a score of 69.6%.
Good luck!
Was this reply helpful?YesNo
Under review
Thank you for your reply! To ensure a great experience for everyone, your content is awaiting approval by our Community Managers. Please check back later.