Abstract: The present invention relates to systems and methods for model scoring and selection. Six or more metrics that are relevant to the model are initially selected, and weights are assigned to each metric. A first subset of the metrics are selected, including metrics for model fit and model error for primary regression. A second subset of metrics including at least two penalty functions are then selected for percentage of incidence. The scores from the primary regression and penalty calculations are aggregated into a final score. Multiple models can be scored and utilized to select a “best” model via an iterative culling of low scoring models and “breeding” of the high scoring models.
Type:
Grant
Filed:
September 30, 2020
Date of Patent:
May 28, 2024
Assignee:
PREVEDERE INC.
Inventors:
Loren Roger Marti, Richard Wagner, Elena Shatilova
Abstract: The present invention relates to systems and methods for model generation. The model is generated by selecting indicators that are relevant to the model, determining a strength score for each of the indicators, ranking the indicators by their strength scores, and bucketizing the indicators. Different permutations of the indicators are then selected for modeling in parallel. The model results are compared, and the ‘best’ model (most historically accurate) is selected for display within a report.
Type:
Grant
Filed:
December 14, 2018
Date of Patent:
January 19, 2021
Assignee:
PREVEDERE, INC.
Inventors:
Kyler Cooper, Jessica Emily Dolezal, Andrew Duguay, Alexander C. Elek, Danielle Marceau, Richard Wagner
Abstract: The present invention relates to systems and methods for forecasting using time series datasets. A composite may be generated by receiving datasets, normalizing them, and receiving formula configurations in order to combine the datasets together. The transformation of a dataset may be restricted if the accuracy of the transformation would be decreased, and if no suitable alternate dataset is available. A forecast may be generated using selected forecast type, calculation type, cutoff period, pre-adjustment, post-adjustment, indicators, and selected weights and offsets for the indicators. The forecast analysis may be updated by locking the time domain for one or more of the indicators. Forecast results may be outputted to a spreadsheet or other system utilizing add-ins. Any composite or forecast generated may be stored within a model repository for later use as an indicator.
Type:
Grant
Filed:
May 13, 2016
Date of Patent:
August 11, 2020
Assignee:
Prevedere, Inc.
Inventors:
Richard Wagner, Jason B. Kerns, Jose K. Paul, Alexander C. Elek
Abstract: The invention disclosed is a system for providing an aggregated econometric database with selectable sources of economic data. The econometric database is accessible to a system application that graphically displays econometric data over selected periods, and allows display of external economic data in conjunction with internal company metrics. The system applications further provide for identifying the features of indicators, economic and business forecasting, and providing alerts based on the available econometric data.
Abstract: The invention disclosed is a system for providing an aggregated econometric database with selectable sources of economic data. The econometric database is accessible to a system application that graphically displays econometric data over selected periods, and allows display of external economic data in conjunction with internal company metrics. The system applications further provide for identifying the features of indicators, economic and business forecasting, and providing alerts based on the available econometric data.