Optimization of broadcast event effectiveness
Introduced herein are methods and systems for determining machine learning marketing strategy. For example, a computer-implemented method according to the disclosed technology includes steps of identifying one or more business metrics to be driven by a marketing plan; generating one or more response functions of the business metrics by performing a machine learning process on a marketing dataset; optimizing a spending subject of the marking plan subject to constraints to generate a marketing strategy based on multiple decision variables; and presenting the marketing strategy to an advertiser.
1. A computer-implemented method for assignment of measurable responses to a plurality of broadcast events, comprising:
storing, in a memory of a computer system, a set of historical data including measurements of a key performance indicator (KPI), subsets of the set of historical data include metadata comprising at least a timestamp, a channel, and a magnitude to be associated with each broadcast event of the plurality of broadcast events;
determining, by the computer system, the KPI from any combination of: views, downloads, phone calls, clicks, purchases, sign-ups, signatures, logins, or application interactions;
identifying, by a processor of the computer system, a regime switching point of predetermined difference in the measurements of the KPI in recent time versus in more distant past by identifying cutoff points in time;
crediting, by the computer system, the measurements of the KPI before the regime switching point to a first broadcast event of the plurality of broadcast events, and the measurements of the KPI after the regime switching point to a second broadcast event of the plurality of broadcast events, wherein the regime switching point occurs after a conclusion of the first broadcast event and the second broadcast event; and
calculating, by the computer system, a predicted effectiveness of a first future broadcast event having a same character as the first broadcast event based on the measurements of the KPI before the regime switching point and ignoring the measurements of the KPI after the regime switching point.
2. The method of claim 1 , further comprising:
calculating, by the computer system, a predicted effectiveness of a second future broadcast event having a same character as the second broadcast event based on the measurements of the KPI after the regime switching point and ignoring the measurements of the KPI before the regime switching point.
3. The method of claim 2 , further comprising:
updating, in the memory, the measurements of the KPI; and
determining, by the processor, an updated predicted effectiveness of the first future broadcast event as relative to the second future broadcast event based upon said updating of the measurements of the KPI.
4. The method of claim 1 , further comprising:
identifying, by the computer system, a beginning cutoff point in time and an ending cutoff point in time for the set of historical data, wherein measurements of the KPI before the beginning cutoff point in time are not credited to the first broadcast event and measurements of the KPI after the ending cutoff point in time are not credited to the second broadcast event.
5. The method of claim 1 , wherein either of the first broadcast event or the second broadcast event further include a medium, the medium is any of: print; picture; video; audio; or multimedia; and the channel is any of: a website; a television channel; a streaming video or video on demand service; a podcast personality; a radio station; or signage.
6. The method of claim 1 , wherein the character of the first broadcast event includes an emotional tone and the emotional tone is used as a further basis for said calculating the predicted effectiveness of the first future broadcast event.
7. The method of claim 1 , wherein the first broadcast event further includes an event length and the event length is used as a further basis for said calculating the predicted effectiveness of the first future event.
8. The method of claim 1 , wherein budget, day of week, national or local availability, inventory status, an age suitability, or spending timeframe is used as a further basis for said calculating the predicted effectiveness of the first future broadcast event.
9. The method of claim 1 , said identifying the regime switching point is further based on a low point between two peak points in the measurements of the KPI.
10. The system of claim 1 , wherein the character of the first broadcast event is any of: print; picture; video; audio; or multimedia.
11. A non-transitory computer-readable storage medium comprising computer instructions when executed by a processor, cause a computer system to perform those steps of:
storing, in a memory of the computer system, a set of historical data including measurements of a key performance indicator (KPI), subsets of the set of historical data include metadata comprising at least a timestamp, a channel, and a magnitude to be associated with each broadcast event of a plurality of broadcast events;
determining the KPI from any combination of: views, downloads, phone calls, clicks, purchases, sign-ups, signatures, logins, or application interactions;
identifying a regime switching point of predetermined difference in the measurements of the KPI in recent time versus in more distant past by identifying cutoff points in time;
determining whether the regime switching point is present based on satisfaction of a threshold within measurements of the KPI;
in response to an existence of the regime switching point, crediting the measurements of the KPI before the regime switching point to a first broadcast event of the plurality of broadcast events, and the measurements of the KPI after the regime switching point to a second broadcast event of the plurality of broadcast events, wherein the regime switching point occurs after a conclusion of the first broadcast event and the second broadcast event; and
calculating a predicted effectiveness of a first future broadcast event having a same character as the first broadcast event based on the measurements of the KPI before the regime switching point and ignoring the measurements of the KPI after the regime switching point.
12. The non-transitory computer-readable storage medium of claim 11 , wherein the threshold is a dynamic threshold based on a slope of the measurements of the KPI as a function of time.
13. The non-transitory computer-readable storage medium of claim 11 , wherein the regime switching point is identified as a low point between two peak points in the measurements of the KPI.
14. The non-transitory computer-readable storage medium of claim 11 , wherein the character of the first broadcast event includes an emotional tone and the emotional tone is used as a further basis for said calculating the predicted effectiveness of the first future event.
15. The non-transitory computer-readable storage medium of claim 11 , wherein the first broadcast event further includes an event length and the event length is used as a further basis for said calculating the predicted effectiveness of the first future event.
16. A system for assignment of measurable responses to a plurality of broadcast events, comprising:
a memory of a computer system storing a set of historical data including measurements of a key performance indicator (KPI), subsets of the set of historical include metadata comprising at least a timestamp, a channel, and a magnitude to be associated with each broadcast event of the plurality of broadcast event; and
a processor of the computer system including instructions stored in the memory to:
identify a regime switching point of predetermined difference in the measurements of the KPI in recent time versus in more distant past by identifying cutoff points in time;
determine whether the regime switching point is present based on satisfaction of a threshold within measurements of the KPI;
in response to an existence of the regime switching point, credit the measurements of the KPI before the regime switching point to a first broadcast event of the plurality of broadcast events, and the measurements of the KPI after the regime switching point to a second broadcast event of the plurality of broadcast events, wherein the regime switching point occurs after a conclusion of the first broadcast event and the second broadcast event; and
calculate a predicted effectiveness of a first future broadcast event having a same character as the first broadcast event based on the measurements of the KPI before the regime switching point and ignoring the measurements of the KPI after the regime switching point.
17. The system of claim 16 , wherein the threshold is a dynamic threshold based on a slope of the measurements of the KPI as a function of time.
18. The system of claim 16 , wherein the regime switching point is identified as a low point between two peak points in the measurements of the KPI.
19. The system of claim 16 , wherein the character of the first broadcast event includes an emotional tone and the emotional tone is used as a further basis for said calculating the predicted effectiveness of the first future event.
20. The system of claim 16 , wherein the first broadcast event further includes an event length and the event length is used as a further basis for said calculating the predicted effectiveness of the first future event.