CPC G06Q 40/04 (2013.01) [G06Q 20/10 (2013.01)] | 23 Claims |
1. A computer implemented method comprising:
generating, by a processor, a plurality of latency tables based upon characteristics and processing times of at least a subset of a first plurality of messages, each having been previously processed by a transaction processing system comprising a serial arrangement of a plurality of stages, each of which comprises a queue coupled with an input of a transaction component and asynchronously processes inputs from the input queues, wherein each of the first plurality of messages is characterized by a characteristic and a calculated processing time of the message with respect to each of the plurality of stages, and storing the plurality of latency tables in a memory, wherein each of the latency tables comprises data uniquely indicative of processing times of messages having a particular characteristic; receiving, by the processor subsequent to the storing of the plurality of latency tables, a second plurality of messages not yet processed by the transaction processing system, each of which is characterized by a characteristic;
configuring, dynamically, a prediction of latency of the transaction processing system by: selecting, by the processor for each of the second plurality of messages and based upon the characteristic thereof, a latency table from the stored plurality of latency tables; simulating, by the processor, a processing time for each of the second plurality of messages based upon the selected latency table; and generating, by the processor, a latency prediction for the transaction processing system for the second plurality of messages based upon the simulated processing times for each of the second plurality of messages; and distributing, by the processor, the generated latency prediction to a corresponding participant of a plurality of participants via a data feed via a network coupled with the processor.
|