A distributed computer system implemented as an electronic trading exchange including an intelligent auction application to optimize, using predictive machine learning, allocation of computer and data communication resources for electronic orders, including auction orders, that are likely to be executed in an at a future auction, comprising:
- a transceiver configured to receive over a data communications network different types of input data including market data and electronic order book data and electronic orders from multiple source nodes including order entry systems associated with trading participants communicating with the data communications network;
- a processing system that includes at least one hardware processor, the processing system configured to:
- maintain an electronic order book and execute the auction;
- process the different types of input data and the electronic orders to generate an input data structure for each of the electronic orders;
- based on the input data structure, predict, using one or more predictive machine learning models, a probability of execution of each of the electronic orders at a future execution time corresponding to the future auction execution time of the auction;
- allocating computer and data communication resources for electronic orders that have a predicted probability of execution at the future auction execution time that equals or exceeds a predetermined probability threshold and avoiding allocating computer and data communication resources for electronic orders that have a predicted probability of execution at the future auction execution time that is less than the predetermined probability threshold;
- generate, prior to the future auction execution time and for dissemination to the trading participants by the transceiver over the data communications network, an auction prediction message that (i) identifies at least one electronic order eligible for the auction and (ii) indicates the predicted probability of execution of the at least one electronic order in the auction at the future auction execution time;
- monitoring and identifying changes that affect the electronic orders including changes to at least one of the electronic orders, auction imbalance information, or the electronic order book;
- and
- adapting the allocation of computer and data communication resources for electronic orders based on the changes to reduce an amount of data communicated over data communication networks, lower consumption of other computer system resources, and improve performance of the computer system.