US 11,720,930 B2
Automated hybrid, optimized advertising auction system and method
Leonard Newnham, Buckingham (GB); Piyush Paliwal, Potsdam (DE); and Lampros Stavrogiannis, London (GB)
Assigned to Loop Me, Ltd., London (GB)
Filed by LoopMe Limited, London (GB)
Filed on May 24, 2022, as Appl. No. 17/752,601.
Claims priority of provisional application 63/192,185, filed on May 24, 2021.
Prior Publication US 2022/0374944 A1, Nov. 24, 2022
Int. Cl. G06Q 30/0273 (2023.01); G06Q 30/0241 (2023.01)
CPC G06Q 30/0275 (2013.01) [G06Q 30/0277 (2013.01)] 33 Claims
OG exemplary drawing
 
1. A method for, using a hybrid, optimized exchange operably connected to a demand-side platform (DSP), the hybrid, optimized exchange further operably connected to a supply-side platform (SSP), the hybrid, optimized exchange configured to receive an advertising request in an automated advertising auction system, the hybrid, optimized exchange further configured to conduct, using a bid floor, a hybrid, optimized DSP auction of the advertising request among a plurality of DSPS, thereby generating a winning DSP that makes a winning DSP bid after the SSP initiates an SSP auction of the advertising request, the hybrid, optimized exchange optimizing the bid floor provided to the plurality of DSPs in the hybrid, optimized DSP auction and simultaneously optimizing a shading factor used by the hybrid, optimized exchange to place a hybrid, optimized bid on behalf of the winning DSP in the SSP auction, the method comprising: receiving an advertising request for an online advertising auction; randomly assigning the received advertising request to one of three advertising request groups, 1) a baseline group comprising a default set of baseline advertising requests using one or more of a default bid floor and a default shading factor whose performance the hybrid, optimized exchange can compare to a performance of other advertising requests using one or more of the optimized bid floor and the optimized shading factor, 2) an exploration group comprising exploration advertising requests, the exploration group usable by the hybrid, optimized exchange to gather a useful set of training data regarding the advertising requests, and 3) an exploitation group comprising exploitation advertising requests, the exploitation group usable by the hybrid, optimized exchange to exploit one or more of the optimized bid floor and the optimized shading factor; retrieving one or more of the optimized bid floor and the optimized shading factor via a bid parameter query; doing one or more, if the advertising request was assigned to the exploitation group, of setting an exploitation group bid floor equal to the optimized bid floor and setting an exploitation group shading factor equal to the optimized shading factor; storing one or more of the exploitation group advertising request, the exploitation group bid floor and the exploitation group shading factor; doing one or more, if the advertising request was assigned to the baseline group, of setting a baseline group bid floor equal to the configured default bid floor and setting a baseline group shading factor equal to the configured default shading factor; storing one or more of the baseline group advertising request, the baseline group bid floor and the baseline group shading factor; retrieving optimized values for bid parameters for a current advertising request by sending a bid parameter query; doing one or more, if the advertising request was assigned to the exploration group, of applying to the advertising request a range of candidate exploration group bid floors, a bid floor range centered on the optimized bid floor, to explore an outcome of different candidate exploration group bid floors within the bid floor range and thereby to identify the optimized bid floor, and applying to the advertising request a range of candidate exploration group shading factors, the shading factor range centered on the optimized shading factor, to explore an outcome of different candidate exploration group shading factors within the shading factor range and thereby to identify the optimized shading factor; storing the training data; storing one or more of the exploration group advertising request, the exploration group bid floor and the exploration group shading factor; using the bid floor, conducting the hybrid, optimized DSP auction; determining a winning DSP bid by a winning DSP in the hybrid, optimized DSP auction; storing one or more of the winning DSP bid and the winning DSP; using the shading factor, placing an SSP bid for an SSP bid amount on behalf of the winning DSP in the SSP auction; receiving an SSP auction result from the SSP; storing the SSP auction result; determining that a training interval has elapsed, wherein the training interval comprises a period of time after a conclusion of which the hybrid, optimized exchange performs a periodic updated calculation of one or more of the optimal bid floor and the optimal shading factor; retrieving the training data; determining, using the training data, for a preselected advertising request subset, one or more of the optimized bid floor and the optimized shading factor; determining a baseline advertising request outcome; determining an exploitation advertising request outcome; comparing the outcome of the baseline advertising request with the outcome of the exploitation advertising request; determining an exploration advertising request outcome; computing a baseline SSP auction profit by computing a baseline SSP auction winning bid minus a baseline DSP winning bid for all advertising requests assigned to the baseline group, divided by a number of baseline advertising requests, and also computing a hybrid, optimized SSP auction profit provided by the hybrid, optimized exchange by computing an exploration- exploitation SSP auction winning bid minus an exploration-exploitation DSP winning bid for all advertising requests assigned to the exploration group or to the exploitation group, divided by a combined number of exploration advertising requests and exploitation advertising requests; dividing exploration requests into a plurality of buckets comprising non-overlapping, contiguous ranges of the bid floor, the plurality of buckets further comprising overlapping, contiguous ranges of the shading factor; computing hybrid, optimized profit by computing the SSP auction winning bid minus the DSP winning bid for a best bucket; determining the optimized bid floor as a midpoint of a range of bid floors contained in the best bucket; determining the optimized shading factor as a midpoint of a range of shading factors contained in the best bucket; and storing both the optimized bid floor and the optimized shading factor.