Value Index Score
Embodiments of the invention provide a technical solution by generating a value index score based on aggregation of a value from a combination of features as a unit. In one embodiment, instead of generating a value index score based on a collection of features with each feature being a discrete parameter, aspects of the invention generate the value index score while accounting for weights of a combination of features as a unit. Furthermore, embodiments of the invention generate a weight value for each feature and that the weight, not only will it be a factor in the calculation, but also be modifiable in response to other factors of the features.
1 . A computerized method for generating a value index score comprising:
receiving elements of an advertising deal from a data source;
conducting a logistic regression analysis to classify the received elements to identify metrics of the advertising deal;
constructing a data structure for each of the metrics, said data structure comprising data fields for storing data of a metric, data of a weight calculated for the metric, historical weight data of the metric, data for an affiliated deal, data of related metrics of the affiliated deal;
determining the weight of each of the metric using the logistic regression analysis;
storing the determined weight in the data structure; and
as a function of the weight of each of the metrics of the advertising deal, calculating a value index score for the advertising deal.
2 . The computerized method of claim 1 , wherein receiving elements of the advertising deal comprises receiving a plurality of advertising deals.
3 . The computerized method of claim 2 , wherein the data source of the plurality of advertising deals comprises one or more of the following: a demand side platform and a supply side platform.
4 . The computerized method of claim 1 , further comprising classifying each of the plurality of advertising deals to one or more metrics using a logistic regression algorithm within each of the plurality of advertising deals.
5 . The computerized method of claim 1 , further comprising refining the weight of each of the metrics after logistic regression analysis using one or more of the following: a linear regression analysis, a gradient boosting analysis, and a random forest analysis.
6 . The computerized method of claim 1 , further comprising receiving historical weight data of each of the metrics, said historical weight data of each of the metrics being stored in the data structure.
7 . The computerized method of claim 6 , further comprising conducting the logistic regression analysis to the weight of each of the metrics as a function of the received historical weight data.
8 . A computerized system for generating a value index score comprising:
a processor for receiving elements of an advertising deal from a data source connected to the processor via a network connection;
a graphical user interface (GUI) for providing to a user the received elements of the advertising deal;
wherein the processor conducts a logistic regression analysis to classify the received elements to identify metrics of the advertising deal;
a distributed data storage unit connected to the processor via the network connection generating a data structure for each of the metrics, said data structure comprising data fields for storing data of a metric, data of a weight calculated for the metric, historical weight data of the metric, data for an affiliated deal, data of related metrics of the affiliated deal;
wherein the processor determines the weight of each of the metric using the logistic regression analysis;
wherein the distributed data storage unit storing the determined weight in the data structure; and
as a function of the weight of each of the metrics of the advertising deal, wherein the processor calculates a value index score for the advertising deal.
9 . The computerized system of claim 8 , wherein the processor receives a plurality of advertising deals.
10 . The computerized system of claim 9 , wherein the data source of the plurality of advertising deals comprises one or more of the following: a demand side platform and a supply side platform.
11 . The computerized system of claim 8 , wherein the processor refines the weight of each of the metrics after logistic regression analysis using one or more of the following: a linear regression analysis, a gradient boosting analysis, and a random forest analysis.
12 . The computerized system of claim 8 , wherein the processor receives historical weight data of each of the metrics, wherein the distributed data storage unit stores the historical weight data of each of the metrics in the data structure.
13 . The computerized system of claim 12 , wherein the processor conducts the logistic regression analysis to the weight of each of the metrics as a function of the received historical weight data.
14 . A non-transitory computer readable medium stored thereon computer-executable instructions embodied in a software product, wherein the computer-executable instructions when executed by a processor comprising:
receiving elements of an advertising deal from a data source;
conducting a logistic regression analysis to classify the received elements to identify metrics of the advertising deal;
constructing a data structure for each of the metrics, said data structure comprising data fields for storing data of a metric, data of a weight calculated for the metric, historical weight data of the metric, data for an affiliated deal, data of related metrics of the affiliated deal;
determining the weight of each of the metric using the logistic regression analysis;
storing the determined weight in the data structure; and
as a function of the weight of each of the metrics of the advertising deal, calculating a value index score for the advertising deal.
15 . The non-transitory computer readable medium of claim 14 , further comprising classifying each of the plurality of advertising deals to one or more metrics using a logistic regression algorithm within each of the plurality of advertising deals.
16 . The non-transitory computer readable medium of claim 14 , wherein receiving elements of the advertising deal comprises receiving a plurality of advertising deals.
17 . The non-transitory computer readable medium of claim 16 , wherein the data source of the plurality of advertising deals comprises one or more of the following: a demand side platform and a supply side platform.
18 . The non-transitory computer readable medium of claim 14 , further comprising refining the weight of each of the metrics after logistic regression analysis using one or more of the following: a linear regression analysis, a gradient boosting analysis, and a random forest analysis.
19 . The non-transitory computer readable medium of claim 14 , further comprising receiving historical weight data of each of the metrics, said historical weight data of each of the metrics being stored in the data structure.
20 . The non-transitory computer readable medium of claim 19 , further comprising conducting the logistic regression analysis to the weight of each of the metrics as a function of the received historical weight data and further comprising updating the value index score for the advertising deal.