You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
This is pretty impressive. I was thinking if you could guide me in building a smart routing solution. For example there are multiple gateways for Money Movement in financial institutions like ACH, SWIFT, RTP etc. Need to enable routing through any channel based on a set of static and dynamic rules. The routing service fetches a list of available terminals from the gateway layer and applied business rules to filter out irrelevant terminals. The filtered input terminals are sent to the dynamic module for success probability assignment for each terminal. Various features like time-window-based features, etc., are computed from the past data and saved in the predictions are made for each terminal. There is a retry mechanism to go to the next best predicted probability if the first one doesnt succeed. I think this may pave a way to such a solution. Thoughts? ideas?
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
Uh oh!
There was an error while loading. Please reload this page.
-
Manoj,
This is pretty impressive. I was thinking if you could guide me in building a smart routing solution. For example there are multiple gateways for Money Movement in financial institutions like ACH, SWIFT, RTP etc. Need to enable routing through any channel based on a set of static and dynamic rules. The routing service fetches a list of available terminals from the gateway layer and applied business rules to filter out irrelevant terminals. The filtered input terminals are sent to the dynamic module for success probability assignment for each terminal. Various features like time-window-based features, etc., are computed from the past data and saved in the predictions are made for each terminal. There is a retry mechanism to go to the next best predicted probability if the first one doesnt succeed. I think this may pave a way to such a solution. Thoughts? ideas?
Beta Was this translation helpful? Give feedback.
All reactions