Method and system for creating a predictive model for targeting web-page to a surfer
Systems and methods for determining predictive model types are provided. A method may include generating a predictive model for a web page of a web site, wherein the web page includes a configuration defining one or more objects presented with the web page, and wherein each object is associated with a predictive model. The method may include determining one or more predictive model types that are associated with the predictive model, determining one or more performance indicators that correspond to each determined predictive model type, wherein performance indicators represent one or more benefits to a website, selecting a predictive model type of the predictive model out of the one or more predictive model types, wherein the predictive model type is selected based on a performance indicator corresponding to the selected predictive model type, and determining a configuration of the web page using the selected predictive model type of the predictive model.
1. A method comprising:
merging a first set of events in a first database with a second set of events in a second database to generate an event table, wherein a set of objects includes objects of one or more webpages, and wherein the first set of events and the second set of events include events associated with the set of objects;
extracting a training table from the event table, wherein entries of the training table correspond to predictive features of the set of objects;
generating a training dataset from the training table, the training dataset including one or more bins for the predictive features, the one or more bins storing a predictive score based on a quantity of records in the first database associated with a predictive feature and a quantity of records in the first database and the second database associated with the predictive feature;
generating a particular predictive model from the training dataset; and
modifying a configuration of a particular webpage by applying the particular predictive model to the particular webpage.
2. The method of claim 1 , further comprising:
extracting a validation table from the event table; and
executing the particular predictive model using one or more entries of a validation table to validate the particular predictive model.
3. The method of claim 1 , further comprising:
generating one or more additional training datasets, each training dataset of the one or more additional training datasets being based on an object of the set of objects and a set of parameters; and
generating one or more predictive models using the one or more additional training datasets, wherein the particular predictive model is selected from among the one or more predictive models and the particular predictive model based on an assigned score.
4. The method of claim 1 , wherein the first database is configured to store events that correspond to an object of the set of objects being included within a webpage.
5. The method of claim 1 , wherein the second database is configured to store events that correspond to an object of the set of objects being selected by a user accessing a webpage.
6. The method of claim 1 , wherein a predictive model is generated for each object of the set of objects.
7. The method of claim 1 , wherein extracting a training table from the event table includes removing one or more irrelevant keys from the training table.
8. A system comprising: a processor; and a non-transitory computer-readable storage medium containing instructions which when executed by the processors, cause the processor to perform operations including: merging a first set of events in a first database with a second set of events in a second database to generate an event table, wherein a set of objects includes objects of one or more webpages, and wherein the first set of events and the second set of events include events associated with the set of objects; extracting a training table from the event table, wherein entries of the training table correspond to predictive features of the set of objects; generating a training dataset from the training table, the training dataset including one or more bins for the predictive features, the one or more bins storing a predictive score based on a quantity of records in the first database associated with a predictive feature and a quantity of records in the first database and the second database associated with the predictive feature; generating a particular predictive model from the training dataset; and
modifying a configuration of a particular webpage by applying the particular predictive model to the particular webpage.
9. The system of claim 8 , further comprising:
extracting a validation table from the event table; and
executing the particular predictive model using one or more entries of a validation table to validate the particular predictive model.
10. The system of claim 8 , further comprising:
generating one or more additional training datasets, each training dataset of the one or more additional training datasets being based on an object of the set of objects and a set of parameters; and
generating one or more predictive models using the one or more additional training datasets, wherein the particular predictive model is selected from among the one or more predictive models and the particular predictive model based on an assigned score.
11. The system of claim 8 , wherein the first database is configured to store events that correspond to an object of the set of objects being included within a webpage.
12. The system of claim 8 , wherein the second database is configured to store events that correspond to an object of the set of objects being selected by a user accessing a webpage.
13. The system of claim 8 , wherein a predictive model is generated for each object of the set of objects.
14. The system of claim 8 , wherein extracting a training table from the event table includes removing one or more irrelevant keys from the training table.
15. A non-transitory computer-readable storage medium containing instructions which when executed by one or more processors, cause the one or more processors to perform operations including:
merging a first set of events in a first database with a second set of events in a second database to generate an event table, wherein a set of objects includes objects of one or more webpages, and wherein the first set of events and the second set of events include events associated with the set of objects;
extracting a training table from the event table, wherein entries of the training table correspond to predictive features of the set of objects;
generating a training dataset from the training table, the training dataset including one or more bins for the predictive features, the one or more bins storing a predictive score based on a quantity of records in the first database associated with a predictive feature and a quantity of records in the first database and the second database associated with the predictive feature;
generating a particular predictive model from the training dataset; and
modifying a configuration of a particular webpage by applying the particular predictive model to the particular webpage.
16. The non-transitory computer-readable storage medium of claim 15 , further comprising:
extracting a validation table from the event table; and
executing the particular predictive model using one or more entries of a validation table to validate the particular predictive model.
17. The non-transitory computer-readable storage medium of claim 15 , further comprising:
generating one or more additional training datasets, each training dataset of the one or more additional training datasets being based on an object of the set of objects and a set of parameters; and
generating one or more predictive models using the one or more additional training datasets, wherein the particular predictive model is selected from among the one or more predictive models and the particular predictive model based on an assigned score.
18. The non-transitory computer-readable storage medium of claim 15 , wherein the second database is configured to store events that correspond to an object of the set of objects being selected by a user accessing a webpage.
19. The non-transitory computer-readable storage medium of claim 15 , wherein a predictive model is generated for each object of the set of objects.
20. The non-transitory computer-readable storage medium of claim 15 , wherein extracting a training table from the event table includes removing one or more irrelevant keys from the training table.