METHOD OF GENERATING FEEDBACK FOR PROJECT PORTFOLIO MANAGEMENT

摘要

A computer executable method for producing a feedback metric for use in Project Portfolio Management (“PPM”). The method includes collecting data about a plurality of project proposals and collecting data about a plurality of completed projects, such that some of the data about proposals and completed projects pertain to the same project. The collected data is then used to estimate the parameters of a model by using a maximum likelihood technique, executed as an algorithm in the computer, that overcomes a Missing Data Problem (“MDP”). The method uses the estimated parameters generated by the algorithm to create feedback metrics for use in PPM and that are output from the computer.

主权项

1. A computer-implemented method for producing an objective feedback metric for an aspect of a Project Portfolio Management (“PPM”) implementation that has already been made, the method overcoming a sample selection bias that resulted from a project selection in which a portion less than 100% of a set of proposals had been selected and in which the selection was non-random, wherein the PPM implementation undergoes processing, prior to the inventive method, including:
collecting into a memory of a computer evaluation data about a plurality of rejected project proposals that were available to be selected during project selection and a plurality of selected proposals; and classifying each of a plurality of the selected proposals as either a good proposal or a bad proposal and entering the classifications into the memory of the computer, each classified proposal being classified based on results produced by implementation of same, the method comprising the steps, after the PPM implementation has been made, of: estimating any and all parameters of a distribution of evaluations that the PPM implementation made about at least one aspect of the good proposals as a first density function, using a processor of the computer, the good proposals including the good proposals that were rejected and the good proposals that were selected by the PPM implementation; estimating any and all parameters of a distribution of evaluations that the PPM implementation made about at least one aspect of the bad proposals as a second density function, using the processor of the computer, the bad proposals including the bad proposals that were rejected and the bad proposals that were selected by the PPM implementation, the first and second density functions overlapping each other; and estimating, using the processor of the computer, at least one of a fraction of proposals that were evaluated by the PPM implementation which comprise the fraction of evaluated proposals that are good proposals, namely, Pproposals, and a fraction of evaluated proposals that are bad proposals, namely, 1−Pproposals; calculating, with a processor of the computer, a likelihood of certain rejected project proposals producing their respective evaluation data that was collected into the memory, the likelihood calculation being made on the basis of the estimated parameters and the estimated fraction of proposals; using a maximum likelihood technique with a processor of the computer to fit the distributions' respective parameters and the fraction of proposals to the evaluation data and the classifications, the fitting process configuring the processor to overcome the sample selection bias, that resulted from the project selection selecting in a nonrandom manner less than 100% of the set of proposals, by including the likelihoods of said rejected project proposals that were calculated in the calculating step; producing the feedback metric by using at least one of the estimated parameters; and outputting the feedback metric from the computer onto a display.