Digital advertising platform with demand path optimization

1. A digital advertising system, the system comprising:

one or more processors configured to execute a plurality of functional modules comprising:

an analytics module configured to:

receive client attributes associated with a website visitor and a requested web site;

define an analytics event based on analyzing the client attributes;

a machine learning module configured to:

receive the analytics event associated with the analytics module;

generate a prediction model that indicates a probability of success of a bid prediction for the analytics event, wherein the machine learning module comprises a scheduler configured for periodically generating model data sets and updating models in advance of generating the prediction model;

a management platform comprising a configuration module configured to:

receive the bid prediction; and

generate a candidate config based on the bid prediction;

a deployment module configured to:

receive a script associated with the candidate config; and

deliver the script to the website visitor.

2. The system of claim 1 , further comprising:

the analytics module further configured to:

augment and format data within the analytics event; and

generate an enriched analytics event; and

the machine learning module further configured to:

generate the prediction model based on the enriched analytics event.

3. The system of claim 1 , wherein the management platform further comprises a visualization module configured to:

provide a user interface for monitoring and control by a human administrator, wherein the user interface includes screens for entering bidding preferences and ad characteristics.

4. The system of claim 1 , further comprising a data warehouse associated with the machine learning module, the data warehouse is configured to:

store the model data sets.

5. The system of claim 1 , wherein the model data sets comprise a publisher's bidding preferences.

6. The system of claim 1 , wherein the scheduler generates updated models based on periodically accessing the model data sets.

7. The system of claim 1 , wherein the machine learning module generates prediction models comprising different configuration script options.

8. The system of claim 7 , wherein the prediction models further comprise ad options comprising ad delivery and ad placement.

9. The system of claim 1 , further comprising an optimization module configured to:

receive one or more candidate configs;

apply weights and additional features to select a candidate config from the one or more candidate configs, wherein the weights applied by the optimization module are determined by machine learning; and

generate a plurality of optimized scripts using the selected candidate config.

10. The system of claim 9 , wherein the weights applied by the optimization module are pre-determined within the management platform according to a website publisher's preference, wherein the pre-determined weights are determined by site-specific thresholds.

11. The system of claim 9 , wherein the one or more candidate configs are at least partially generated using settings entered by a human administrator via the management platform.

12. The system of claim 9 , wherein the optimization module is further configured to:

select the selected candidate config according to a plurality of features selected from page variations, number of bidders, number of geographies, bid timeout, bidder concurrency and client device type.

13. One or more non-transitory computer-readable media having computer-executable instructions that, when executed by a computing system having a processor and memory, cause the processor to perform operations, the operations comprising:

receiving client attributes associated with a website visitor and a requested web site;

defining an analytics event based on analyzing the client attributes;

generating a prediction model that indicates a probability of success of a bid prediction for the analytics event, wherein the prediction model is generated using a machine learning module comprising a scheduler configured for periodically generating model data sets and updating models in advance of generating the prediction model;

generating a config based on the bid prediction; and

delivering a script associated with the config to the website visitor.

14. The media of claim 13 , the operations further comprising:

augmenting and formatting data within the analytics event; and

generating an enriched analytics event, wherein the prediction model is generated based on the enriched analytics event.

15. The media of claim 13 , wherein the scheduler generates updated models based on periodically accessing the model data sets.

16. The media of claim 13 , wherein the machine learning module generates prediction models comprising different configuration script options.

17. A computer-implemented method, the method comprising:

receiving client attributes associated with a website visitor and a requested web site;

defining an analytics event based on analyzing the client attributes;

generating a prediction model that indicates a probability of success of a bid prediction for the analytics event, wherein the prediction model is generated using a machine learning module comprising a scheduler configured for periodically generating model data sets and updating models in advance of generating the prediction model;

generating a config based on the bid prediction; and

delivering a script associated with the config to the website visitor.

18. The method of claim 17 , the method further comprising:

augmenting and formatting data within the analytics event; and

generating an enriched analytics event, wherein the prediction model is generated based on the enriched analytics event.

19. The method of claim 17 , wherein the scheduler generates updated models based on periodically accessing the model data sets.

20. The method of claim 17 , wherein the machine learning module generates prediction models comprising different configuration script options.