Abstract
Systems that utilize real-time offer construction, such as flight search systems, can experience high volumes of computationally expensive queries that may have low conversion rates, potentially leading to inefficient resource allocation. A system for dynamic query prioritization can address this potential inefficiency. The system may intercept an incoming search query and use an analysis engine to assign a real-time priority score. This analysis engine can employ machine learning models trained on historical transaction data to determine the score. Based on this score, the system can apply a set of configurable controls to modulate the computational response. For example, the system could limit the number of offers returned or select a different search strategy. This approach can facilitate a more strategic allocation of computational resources by concentrating effort on queries with a higher probability of resulting in a transaction while reducing expenditure on lower-value traffic.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
Small, Christopher; Abraham, Thomas; de Silva, Rujith; Fraser, Allan; Letourneau, Jason; Maheshwari, Kartik; Moleiro White, Leonardo Andres; Poirot, Cedric; and Ravishankar, Ramitha Sai, "Dynamic Prioritization of Flight Search Queries to Control Computational Resource Allocation", Technical Disclosure Commons, ()
https://www.tdcommons.org/dpubs_series/9053