US 11,869,021 B2
Segment valuation in a digital medium environment
Kourosh Modarresi, Los Altos, CA (US); Jamie Mark Diner, Pittsburgh, PA (US); Elizabeth T. Chin, Westfield, NJ (US); and Aran Nayebi, Palo Alto, CA (US)
Assigned to Adobe Inc., San Jose, CA (US)
Filed by Adobe Inc., San Jose, CA (US)
Filed on Oct. 18, 2021, as Appl. No. 17/503,702.
Application 17/503,702 is a continuation of application No. 15/354,944, filed on Nov. 17, 2016, granted, now 11,182,804.
Prior Publication US 2022/0036385 A1, Feb. 3, 2022
Int. Cl. G06Q 30/0201 (2023.01); G06N 20/00 (2019.01); G06N 20/20 (2019.01); G06N 5/01 (2023.01); G06Q 30/0251 (2023.01); G06Q 30/0202 (2023.01); G06Q 30/02 (2023.01)
CPC G06Q 30/0201 (2013.01) [G06N 5/01 (2023.01); G06N 20/00 (2019.01); G06N 20/20 (2019.01); G06Q 30/02 (2013.01); G06Q 30/0202 (2013.01); G06Q 30/0269 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
obtaining, by a processing device, data describing a population and achievement of a metric by the population;
training, by the processing device, a machine learning model based on the data by employing a penalty term that is automatically adjusted through successive training iterations using different portions of the data and is configured to adjust bias and variance of the machine learning model to reduce over fitting and under fitting of the model, the model being an ensemble model formed using a plurality of sub-models having weighted contributions towards an overall result of the ensemble model that describes the achievement of the metric by the population;
identifying, by the processing device, a predefined number of attributes of the population from the data describing the population;
generating, by the processing device using the machine learning model, a valuation of a segment of the population based on a significance of respective attributes of the predefined number of attributes of the population on the achievement of the metric, the significance quantified as a score by adjusting a weight of each of the respective attributes to determine a relative effect of the respective attributes on the metric, the score generated from the data describing the achievement of the metric by the population; and
outputting, by the processing device, the valuation of the segment of the population.