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 |
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.
|