Guru's Verification engine ensures consistency, confidence, and trust in the knowledge your organization shares. Learn more.

Pricing Model Testing Changes

It is tempting to overfit pricing configuration for a partiular situation that arises. We can't assume changes to fit a single situation will work well in other timezones.

To test changes for one situation and their impact over a broader range of scenarios. We recommend:

Simulations

Simulate multi-week impact
Simulate multi-instrument impact
Observe:
- spreads by timezone
- predictivity of the model
- predictivity of the signals
- predictivity of the nodes
- availability (how long we were not firm during a trading week)

Pre-Post Implementation Checks

Make the changes during the week, to avoid outages over the weekend where configuration is incorrect, but this is only discovered over the weekend.
Do a rolling bounce of the related processes during the day.
Observe the following pre-and post the change
- spreads by timezone
- predictivity of the model
- predictivity of the signals
- predictivity of the nodes
availability (how long we were not firm during a trading week)

You must have Author or Collection Owner permission to create Guru Cards. Contact your team's Guru admins to use this template.