Return reasons

Code the free-text reasons on returns and find the ones better product pages could prevent.

Run this on your file Download the template CSV

Columns to upload

Name the columns in your CSV like this. Extra columns are fine: every column of the row is sent with the questions.

Column	What it holds
`order_id`	Order ID
`product`	Product returned
`return_reason`	The reason the customer wrote

Questions

Each question adds a column to your file. The answer is one of the listed values, or Unsure when the model's confidence is below the cutoff: 70% for pick-one and scale questions, 80% for yes or no.

New column	Question	Possible answers
`reason`Pick one	Why did the customer return the product?	size or fit The listed size was right, but it did not fit the customer damaged Arrived broken or damaged not as described Different from the photos or description, size included wrong item Received a different product late Arrived too late changed mind No longer wanted it
`preventable`Yes or no	Could better photos, sizes or descriptions on the product page have prevented this return?	yes The customer expected something the page could have shown no The page could not have prevented it
`warehouse_fault`Yes or no	Did the warehouse or carrier cause the problem?	yes Wrong item, damage in transit, or late delivery no The product or the customer's choice

Example row

Column	Value
`order_id`	#10492
`product`	Stemless Glass Set of 4
`return_reason`	Much smaller than they look in the photos, more like juice glasses.

Answers from a test run on this row

Column	Answer	Confidence
`reason`	not as described	97%
`preventable`	yes	85%
`warehouse_fault`	no	93%

More ecommerce use cases

Use case	What it does	New columns
Product reviews	Find out what reviews say about each product and pick the ones you can quote on the product page.	`aspect` `sentiment` `defect` `quotable`
Product catalog tagging	Fill in missing tags and filters on a product catalog from titles and descriptions.	`audience` `season` `giftable` `description_quality`
Order notes	Pull the order notes that need someone to act before the order ships.	`note_type` `needs_action` `date_given`
Competitor product matching	Check whether the competitor listings you matched to your products are the same item before you compare prices.	`match` `same_size` `bundle`
Product listing quality check	Audit product titles and descriptions for missing attributes and mismatches before a marketplace or Google Shopping feed goes live.	`title_complete` `category_fits` `promo_text` `description_matches`