What are Decisions?
Decisions are the way to give feedback that Sift uses to recognize fraud patterns unique to your company. The more feedback you send to Sift Science, the more accurate your risk predictions will become. You can make decisions manually while reviewing a user in the console, or automatically for users that don’t require further investigation via Workflows.
You can connect Decisions to your system so that any action you take in Sift's Console (for example blocking an order or user) sends a message to your system to do the same.
Common decisions depend on your business and the types of abuse you're fighting. Here are some examples by abuse type:
- Payment Abuse: Bad Order, Good Order, Unclear, Add Verification.
- Content Abuse: Block Content, Good Content, Unclear, Restrict Account.
- Account Abuse: Bad Account, Good Account, Unclear, Restrict Account.
- Promo Abuse: Block Promo, Allow Promo, Unclear, Close Account.
When should I send Decisions?
You should send a Decision to Sift whenever you take business action against a user. This includes any decision made within your own manual review process or an automated decisions your applications makes on users. Make sure your developers integrate with Sift’s API so that whenever you make a Decision in your system, it’s automatically sent to Sift. It’s both easy to setup and will save you a lot of time going forward.
Keep in mind that it’s important to always keep the status of a user up to date. This includes sending decisions in the following scenarios:
- If you automatically block users that have had a Chargeback, send a Decision when the Chargeback is received.
- If your Support team decides to reverse an existing decision (eg unban a user who was initially blocked, send an updated Decision.
Do I need to use Sift's Review Queues or Workflows to make Decisions?
Nope! you can use any internal tools to make Decisions, just make sure that your developers augment your tool to send these Decisions to the Sift API at the same time. It's both easy to setup and will save you a lot of time going forward.
Should I send Decisions in production for test data?
- No! You should be using Sandbox mode (aka test mode) for any testing that you want to conduct. If you send this test data in production, it will pollute your live Sift scores and make them less accurate.
Should I send Block Decisions for non fraud related user bans?
Sift Decisions should only be made for risk/fraud realted reasons, so please don't set up Decisions related to Terms of Service Violations or other non fraud decisions (eg friendly fraud). Using Decisions to take action for non fraud reasons will make it harder for Sift to identify real fraud patterns that affect your business.