US 12,033,215 B2
Portfolio performance prediction
Danilo Prates de Oliveira, Vancouver (CA); Stanley Thomas Coleman, North Vancouver (CA); Nicholas Sertic, Vancouver (CA); William John Dall, New Westminster (CA); and Diego Andres Gonzalez Suarez, Vancouver (CA)
Assigned to Copperleaf Technologies Inc., Vancouver (CA)
Filed by Copperleaf Technologies Inc., Vancouver (CA)
Filed on Apr. 8, 2020, as Appl. No. 16/842,854.
Prior Publication US 2021/0319513 A1, Oct. 14, 2021
Int. Cl. G06Q 40/06 (2012.01); G06F 17/15 (2006.01); G06F 17/18 (2006.01); G06F 18/23 (2023.01); G06N 20/00 (2019.01)
CPC G06Q 40/06 (2013.01) [G06F 17/15 (2013.01); G06F 17/18 (2013.01); G06F 18/23 (2023.01); G06N 20/00 (2019.01)] 23 Claims
OG exemplary drawing
 
1. A method for portfolio performance prediction of a portfolio of projects, the method comprising:
receiving information regarding at least start date delays, duration increases and cost overruns for at least one project of the portfolio of projects;
training a machine learning model, using historical performance data for the at least one project and at least one of supervised or unsupervised machine learning modeling, to determine at least one of a cluster or a classification for the received information regarding the start date delays, duration increases and cost overruns for the at least one project;
determining, using the trained machine learning model, at least one cluster for the at least one project from the received information regarding at least the start date delays, duration increases and cost overruns for the at least one project of the portfolio of projects by grouping results of performance metrics that are based on a comparison of at least one historical plan with actual performance outcomes;
creating a statistical representation for each of the clusters of the at least one project of the portfolio of projects, including at least pessimistic, expected and optimistic values for each of the clusters;
predicting a performance of the at least one project of the portfolio of projects using information regarding the statistical representation of the clusters of the at least one project of the portfolio of projects;
updating a resource allocation schedule, that was determined based on an expected performance of the at least one project of the portfolio of projects, based on a comparison between the predicted performance of the at least one project of the portfolio of projects and the expected performance of the at least one project of the portfolio of projects; and
distributing at least one of funds or resources for the performance of the portfolio of projects in accordance with the updated resource allocation schedule.