Break-based inventory forecasting
Techniques are disclosed for advantageously forecasting an inventory of a product having a particular duration (e.g., video content). The technique can include determining the particular configuration (e.g., maximum number of impressions, maximum amount of time permitted) of breaks identified within an impression log. Based on the number of breaks and the configurations of the breaks, the technique can forecast a future inventory of the product. In some implementations, the disclosed technique can identify an amount of a previous break that was not filled with video content. These forecasts can enable product sellers to better communicate with their customers, negotiate supply contracts, price their products, plan for business operations, etc.
1. A method comprising:
receiving, by a processing system from a forecast view user interface of a content publisher device, a request for a future forecast associated with an advertising campaign directed to target viewers having a group of viewer attributes; and
in response to the request for the future forecast:
accessing, by an impression log generator of the processing system, an impression log data database that stores stored data received from client devices indicating displayed impressions and viewer attributes associated with the displayed impressions;
generating, by the impression log generator of the processing system and based on the stored data, an impression log of prior video content presented to viewers having the group of viewer attributes;
determining, by an impression log analyzer of the processing system, signatures within the impression log that indicate breaks within the prior video content according to an analysis of the impression log, resulting in identified breaks;
determining, by the impression log analyzer of the processing system, a count of the identified breaks based on the signatures;
determining, by a break configuration determination engine of the processing system, configuration constraints for each of the identified breaks, wherein the configuration constraints comprise a maximum number of permitted impressions, and a maximum amount of permitted time for each permitted impression in each of the identified breaks in the impression log;
calculating, by the processing system, a maximum prior impressions inventory during a time period of the impression log based on an analysis of the maximum number of permitted impressions, the maximum amount of permitted time for each permitted impression in each of the identified breaks in the impression log, the count of the identified breaks, and a run time of a product having the group of viewer attributes; and
based on the calculating of the maximum prior impressions inventory, forecasting a future inventory for the product.
2. The method of claim 1 , wherein the forecasting the future inventory comprises applying a multiplier to the maximum prior impressions inventory.
3. The method of claim 1 , further comprising adjusting the forecasting of the future inventory according to a predetermined percentage of unfilled impressions in a same proportion as represented in the impression log.
4. The method of claim 1 , wherein the run time is selected from the group consisting of 15 seconds, 30 seconds, 45 seconds, and 1 minute.
5. The method of claim 1 , wherein the analysis of the impression log is based on a pod position field.
6. The method of claim 1 , wherein the analysis of the impression log is based on a size field.
7. The method of claim 1 , wherein the calculating the maximum prior impressions inventory is based on determining a lower value when comparing the maximum number of permitted impressions with ((the maximum amount of permitted time)/(the run time of the product)) and is further based on multiplying the count of the identified breaks by the lower value.
8. The method of claim 1 , further comprising:
adjusting the future inventory based on at least one of an existing and a predicted order line resulting in a future availability.
9. The method of claim 8 , further comprising:
representing at least one of the future inventory and the future availability as a number of impressions.
10. The method of claim 8 , further comprising:
representing at least one of the future inventory and the future availability as an amount of time.
11. The method of claim 1 , wherein the determining the signatures comprises identifying lines in the impression log comprising a criteria indicative of a break.
12. The method of claim 1 , wherein the determining the configuration constraints comprises identifying at least one configuration comprising a targeting expression corresponding to the identified breaks.
13. The method of claim 1 , further comprising:
analyzing the impression log to determine a count of previously viewed impressions;
determining an inventory of past impressions corresponding to the previously viewed impressions, based on the count of identified breaks and the configuration constraints; and
calculating a quantity of unfilled impressions.
14. A system comprising:
one or more computers programmed to perform operations comprising:
receiving, from a forecast view user interface, a request for a future forecast of an advertising campaign directed to target viewers having a group of viewer attributes;
accessing an impression log data database that stores stored data received from client devices indicating displayed impressions and viewer attributes associated with the displayed impressions;
generating, based on the stored data, an impression log of prior video content presented to viewers having the group of viewer attributes;
determining signatures within the impression log that indicate breaks within the prior video content according to an analysis of the impression log, resulting in identified breaks;
determining a count of the identified breaks based on the signatures;
determining configuration constraints for each of the identified breaks, wherein the configuration constraints comprise a maximum number of permitted impressions, and a maximum amount of permitted time for each permitted impression in each of the identified breaks in the impression log;
calculating a maximum prior impressions inventory during a time period of the impression log based on an analysis of the maximum number of permitted impressions, the maximum amount of permitted time for each permitted impression in each of the identified breaks in the impression log, the count of the identified breaks, and a run time of a product having the group of viewer attributes; and
based on the calculating of the maximum prior impressions inventory, forecasting a future inventory for the product.
15. The system of claim 14 , wherein the forecasting the future inventory comprises applying a multiplier to the maximum prior impressions inventory.
16. The system of claim 14 , wherein the operations further comprise adjusting the forecasting of the future inventory according to a predetermined percentage of unfilled impressions in a same proportion as represented in the impression log.
17. The system of claim 14 , wherein the calculating the maximum prior impressions inventory is based on determining a lower value when comparing the maximum number of permitted impressions with ((the maximum amount of permitted time)/(the run time of the product)) and is further based on multiplying the count of the identified breaks by the lower value.
18. The system of claim 14 , wherein the operations further comprise:
adjusting the future inventory based on at least one of an existing and a predicted order line resulting in a future availability.
19. The system of claim 14 , wherein the determining the signatures comprises identifying lines in the impression log comprising a criteria indicative of a break.
20. A non-transitory, computer-readable storage medium having instructions stored thereon, that when executed by a data processing apparatus cause the data processing apparatus to perform operations comprising:
receiving, from a forecast view user interface, a request for future forecast of an advertising campaign directed to target viewers having a group of viewer attributes;
accessing an impression log data database that stores stored data received from client devices indicating displayed impressions and viewer attributes associated with the displayed impressions;
generating, based on the stored data, an impression log of prior video content presented to viewers having the group of viewer attributes;
determining signatures within the impression log that indicate breaks within the prior video content according to an analysis of the impression log, resulting in identified breaks;
determining a count of the identified breaks based on the signatures;
determining configuration constraints for each of the identified breaks, wherein the configuration constraints comprise a maximum number of permitted impressions, and a maximum amount of permitted time for each permitted impression in each of the identified breaks in the impression log;
calculating a maximum prior impressions inventory during a time period of the impression log based on an analysis of the maximum number of permitted impressions, the maximum amount of permitted time for each permitted impression in each of the identified breaks in the impression log, the count of the identified breaks, and a run time of a product having the group of viewer attributes; and
based on the calculating of the maximum prior impressions inventory, forecasting a future inventory for the product.