Patent Application
20180300753
The television (TV) advertisement marketplace consists of buyers (e.g., TV advertising agencies) and sellers (e.g., TV content producers and distributors). Buyers want to maximize their return on investment by maximizing the number of times their advertisements are watched by their selected target audience, and sellers want to maximize the revenue they obtain by selling advertisement placements. These two goals are in conflict. On one hand, the buyers' budget limits and the selective nature of their orders causes any reasonable campaign schedule generator to select the most cost-effective placements from the point of view of the buyer. On the other hand, such a generated schedule limits the earnings potential for the seller if placement prices remain fixed.
A computerized system performs automated schedule optimization. In particular, the system solves the problem of determining the range of advertisement placement prices that a seller can select from, while still satisfying all of the constraints on the buyers' orders. The system generates such a range of prices automatically based on a variety of data. As a result, the system helps the seller to maximize the prices of the potential placements that can satisfy a set of orders from buyers.
For example, one embodiment of the present invention is directed to a method, performed by at least one computer processor executing computer program instructions stored on at least one non-transitory computer-readable medium, where the method includes: (A) identifying an initial ratecard percentage associated with a seller; (B) scaling the initial ratecard percentage up and down to produce a plurality of modified ratecard percentages; (C) selecting, from among the plurality of modified ratecard percentages, a minimum ratecard percentage that satisfies at least one buyer constraint in connection with a plurality of inventory units; and (D) selecting, from among the plurality of modified ratecard percentages, a maximum ratecard percentage that satisfies the at least one buyer constraint in connection with a plurality of inventory units having a plurality of associated rates. The at least one buyer constraint max include a maximum spending constraint. Step (B) may include selecting a first initial scaling factor and scaling the initial ratecard percentage based on the first initial scaling factor. Step (B) may further include selecting the first initial scaling factor to have a value greater than one, such that applying the first initial scaling factor to the initial ratecard percentage results in infeasibility of satisfying the at least one buyer constraint in connection with the plurality of inventory units. The at least one buyer constraint may include a maximum spending constraint, and step (C) may include: (C) (1) scaling the plurality of associated rates based on the first initial scaling factor and the initial ratecard percentage to produce a plurality of scaled rates; (C) (2) calculating a minimum deviation of the plurality of scaled rates from the maximum spending constraint; and (C) (3) selecting the maximum ratecard percentage based on the calculated minimum deviation.
Step (B) may further include selecting a second initial scaling factor and scaling the initial ratecard percentage based on the second initial scaling factor. Step (B) may further include selecting the second initial scaling factor to have a value less than one, such that applying the second initial scaling factor to the initial ratecard percentage results in infeasibility of satisfying the at least one buyer constraint in connection with the plurality of inventory units. The at least one buyer constraint may include a maximum spending constraint, and step (D) may include: (D) (1) scaling the plurality of associated rates based on the first initial scaling factor and the initial ratecard percentage to produce a plurality of scaled rates; (D) (2) calculating a minimum deviation of the plurality of scaled rates from the maximum spending constraint; and (D) (3) selecting the minimum ratecard percentage based on the calculated minimum deviation.
8. The method of claim 1, wherein (C) comprises scaling rates associated with the plurality of inventory units based on the plurality of modified ratecard percentages to produce a plurality of modified rates, and selecting the minimum ratecard percentage based on the plurality of modified rates. Step (D) may include scaling rates associated with the plurality of inventory units based on the plurality of modified ratecard percentages to produce a plurality of modified rates, and selecting the maximum ratecard percentage based on the plurality of modified rates.
Other features and advantages of various aspects and embodiments of the present invention will become apparent from the following description and from the claims.
The term “advertisement placement opportunity” (also known as an “advertising opportunity”) refers to a defined opportunity to provide an advertisement to one or more viewers via one or more inventory sources. An individual such opportunity may be referred to herein as an “avail,” a “unit of inventory,” or simply a “unit,” while multiple such opportunities may collectively be referred to as “inventory.”Examples of traditional advertisement placement opportunities includes a quarter-page portion of a particular page in a particular issue of a particular magazine, and a 30-second slot within a particular episode of a particular television program. Traditionally, during the process of selling traditional television advertisements, a television advertisement placement opportunity is expressed to advertising buyers in terms of the time during which the buyer's advertisement will air if the buyer purchases the advertisement placement opportunity. Alternatively, for example, advertisement placement opportunities may be expressed in terms of an audience model representing an audience (e.g., an actual or predicted audience) associated with the advertisement placement opportunity, as described in U.S. patent application Ser. No. 14/663,703, filed on Mar. 20, 2015, entitled, “Audience-Based Television Advertising Transaction Engine,” which is incorporated by reference herein.
The term “inventory source” refers herein to one or more output devices for producing advertisement output to a user, such as a screen for producing visual output and/or a speaker for producing auditory output. An inventory source may use one or more such output devices to produce output as part of delivering an advertisement to the user within an advertisement placement opportunity. Examples of inventory sources include televisions, desktop computers, laptop computers, tablet computers, smartphones, and wearable computers. As used herein, the term “impression” refers to a single exposure of a single person or home exposed to a single advertisement.
Consider a television program distributed by a television advertisement seller (e.g., television content producer and distributor). Dispersed within this television program are one or more advertisement placement opportunities, e.g., commercial breaks, that can be sold to television advertisement buyers. This set of advertisement placement opportunities is an example of the seller's “inventory,” as that term is used herein. In conventional systems, the seller typically prices its inventory at the individual unit level. For example, if the inventory associated with the television program consists of three advertisement placement opportunities, then each of these three advertisement placement opportunities is a “unit” of inventory, and the seller typically assigns a price (or range of prices) to each of these three advertisement placement opportunities. The three prices may be the same as, or different from, each other.
When the television program airs, the content (e.g., advertisement) within each such unit of inventory will actually be watched by a certain number of people. Even if it is not feasible to measure the actual number of viewers who watch an individual unit of content (e.g., before the unit of content is aired), the number of people who watch the content within each such unit of inventory may be predicted or estimated in a variety of ways.
A useful measure in the description that follows is Cost Per Mille (CPM), which represents the cost of purchasing a unit of inventory per thousand people who are exposed to that unit of inventory. The “unit CPM” for a particular unit of inventory may be defined as 1000*(Price of the unit)/(Number of people exposed to the unit). A useful graphical representation of the price distribution in a given inventory is given by the histogram of units at different unit CPM levels as shown in
The entire set of people who are exposed to a particular advertisement within a particular unit of inventory is referred to herein as the “exposed audience.” The chart shown in
Any particular television advertising campaign, associated with a particular buyer, may include one or more parameters, each of which may have an associated value or range of values. Such parameters typically include at least a target CPM constraint. For example, the buyer might have a $100,000 budget and desire to spend at a rate of $12.50 CPM for the entire exposed audience. Such a constraint corresponds to a total of 8,000,000 impressions of the target audience. Any television advertising campaign schedule generator, therefore, when provided with such a constraint, attempts to buy units from the available inventory so that the average unit CPM of the selected units (defined as 1000*(sum of dollars spent)/(sum of impressions)) is as close to the campaign's target CPM as possible. It is worth noting that the mathematical properties of the TV advertisement scheduling problem are such that it not practical for a person to attempt to solve any instance of it without the use of specialized software and/or hardware. This is shown graphically in
In
In the example of
A “ratecard percentage” is a percentage by which all of the unit prices in an inventory may be scaled (multiplied). Sellers often apply a ratecard percentage to some or all of the units in a particular inventory to increase (i.e., apply a premium) or decrease (i.e., apply a discount) the prices of those units. For example, a seller might apply a ratecard percentage that is greater than 100% to particularly valuable units, such as units delivered during prime time. As another example, a seller might apply a ratecard percentage that is less than 100% to units that are sold to a buyer who purchases a large number of such units, in order to provide a volume discount to that buyer.
The process of pricing exploration disclosed herein in connection with embodiments of the present invention effectively scales the ratecard percentages up and/or down in an attempt to: (1) discover the minimum and maximum possible rates that are achievable, meaning the minimum and maximum possible rates which allow the buyer's specified constraints (e.g., maximum spending constraint) to be satisfied; and (2) enable the seller to explore the qualitative nature of the advertising schedules that are produced within the feasible rate range, given a particular set of buyer constraints. The term “feasible rate range” refers to the range of rates (e.g., unit CPM rates) that can be produced, given a particular set of buyer constraints, based on the premise that it is mathematically possible to satisfy the buyer's constraints given the available inventory. If it is not possible to satisfy the buyer's constraints given the available inventory, then the buyer's constraints are considered to be “infeasible.”
As the rates within a particular inventory are scaled up and/or down, the inventory CPM distribution changes. The net effect of such changes on inventory CPM distribution depends on whether the scaling factor(s) applied to the inventory rates are greater than one or less than one (i.e., 100%). A chart illustrating an example in which a premium of 100% (i.e., a scaling factor of 2) is applied is shown in FIG. 3. In this example, the scaling factor of 100% has been applied to all of the rates (i.e., unit CPM prices) in the inventory of
Now consider the chart in
As the examples in
As described generally above, embodiments of the present invention may vary the scaling factor up and/or down in order to identify a minimum discount, as illustrated by the system 700 of
The system 700 and method 800 are applied to a particular advertising campaign of a buyer. That advertising campaign has a particular set of constraints. Such constraints may include any one or more constraints; embodiments of the present invention are not limited to use in connection with campaigns having any particular constraints. In the particular example illustrated in
The system 700 and method 800 may scale the initial prices associated with the inventory 716 in any of a variety of ways. For example, one embodiment of the present invention uses the following process to identify the minimum and maximum discounts to apply to the prices of the inventory 716:
More specifically, to calculate the minimum ratecard percentage that can be used to produce a feasible schedule, the schedule generator 706 may perform the following steps:
To summarize the process described above, to obtain the maximum ratecard percentage and corresponding scaling factor, the schedule generator 706 uses an initially large scaling factor to increase the rates associated with the available inventory 716 by a large amount that results in infeasibility, and then decreases those rates (by decreasing the scaling factor) such that applying that scaling factor to the rates stops producing infeasible schedules (see
The minimum scaling factor, when applied to the unit CPM distribution, produces the largest possible discount while still achieving feasibility. Conversely, the maximum scaling factor, when applied to the unit CPM distribution, produces the largest possible premium while still achieving feasibility. Once the maximum and minimum scaling factors have been produced using the process described above, the schedule generator 706 may produce schedules at any intermediate ratecard percentage by scheduling the unit CPM distribution using a factor that is greater than or equal to the minimum scaling factor and less than or equal to the maximum scaling factor. The process disclosed herein guarantees that any schedules produced using any scaling factor within this range are feasible.
Embodiments of the present invention may automatically generate a number X of schedules within the minimum and maximum ratecard percentages (i.e., using scaling factors that are greater than or equal to the minimum scaling factor and less than or equal to the maximum scaling factor), where X may be any number. The set of X scaling factors within this range may be selected in any way, such as by evenly spacing them within the range. Output representing the resulting schedules may be generated and provided to the user. Furthermore, a graph representing performance measures may be generated and displayed to the user, as in the example shown in
Such a graphical depiction of the number of advanced target impressions (shown as “Adv. Imps” in
Sometimes, as in the example in
One advantage of embodiments of the present invention is that they solve the problem of determining the range of advertisement placement prices that a seller can select from, while still satisfying all of the constraints on the buyers' orders. The system generates such a range of prices automatically based on a variety of data. As a result, the systems helps the seller to maximize the prices of the potential placements that can satisfy a set of orders from buyers.
It is to be understood that although the invention has been described above in terms of particular embodiments, the foregoing embodiments are provided as illustrative only, and do not limit or define the scope of the invention. Various other embodiments, including but not limited to the following, are also within the scope of the claims. For example, elements and components described herein may be further divided into additional components or joined together to form fewer components for performing the same functions.
Any of the functions disclosed herein may be implemented using means for performing those functions. Such means include, but are not limited to, any of the components disclosed herein, such as the computer-related components described below.
The techniques described above may be implemented, for example, in hardware, one or more computer programs tangibly stored on one or more computer-readable media, firmware, or any combination thereof. The techniques described above may be implemented in one or more computer programs executing on (or executable by) a programmable computer including any combination of any number of the following: a processor, a storage medium readable and/or writable by the processor (including, for example, volatile and non-volatile memory and/or storage elements), an input device, and an output device. Program code may be applied to input entered using the input device to perform the functions described and to generate output using the output device.
Embodiments of the present invention include features which are only possible and/or feasible to implement with the use of one or more computers, computer processors, and/or other elements of a computer system. Such features are either impossible or impractical to implement mentally and/or manually. For example, embodiments of the present invention automatically apply a variety of scaling factors to a unit CPM distribution using a multi-step process that would be impossible or impractical to implement mentally and/or manually. More generally, the problem of scheduling television advertisements belongs to a class of problems known to be computationally hard (see, e.g., “The complexity of scheduling TV commercials,” Electronic Notes in Theoretical Computer Science, Vol. 40, pages 162-185 (2001), Klemens Hagele and Colm Dunlaing and Soren Riis. A human, therefore, would find it overwhelming and, as a practical matter, impossible to schedule television advertisements within the applicable temporal and other constraints.
Any claims herein which affirmatively require a computer, a processor, a memory, or similar computer-related elements, are intended to require such elements, and should not be interpreted as if such elements are not present in or required by such claims. Such claims are not intended, and should not be interpreted, to cover methods and/or systems which lack the recited computer-related elements. For example, any method claim herein which recites that the claimed method is performed by a computer, a processor, a memory, and/or similar computer-related element, is intended to, and should only be interpreted to, encompass methods which are performed by the recited computer-related element(s). Such a method claim should not be interpreted, for example, to encompass a method that is performed mentally or by hand (e.g., using pencil and paper). Similarly, any product claim herein which recites that the claimed product includes a computer, a processor, a memory, and/or similar computer-related element, is intended to, and should only be interpreted to, encompass products which include the recited computer-related element(s). Such a product claim should not be interpreted, for example, to encompass a product that does not include the recited computer-related element(s).
Each computer program within the scope of the claims below may be implemented in any programming language, such as assembly language, machine language, a high-level procedural programming language, or an object-oriented programming language. The programming language may, for example, be a compiled or interpreted programming language.
Each such computer program may be implemented in a computer program product tangibly embodied in a machine-readable storage device for execution by a computer processor. Method steps of the invention may be performed by one or more computer processors executing a program tangibly embodied on a computer-readable medium to perform functions of the invention by operating on input and generating output. Suitable processors include, by way of example, both general and special purpose microprocessors. Generally, the processor receives (reads) instructions and data from a memory (such as a read-only memory and/or a random access memory) and writes (stores) instructions and data to the memory. Storage devices suitable for tangibly embodying computer program instructions and data include, for example, all forms of non-volatile memory, such as semiconductor memory devices, including EPROM, EEPROM, and flash memory devices; magnetic disks such as internal hard disks and removable disks; magneto-optical disks; and CD-ROMs. Any of the foregoing may be supplemented by, or incorporated in, specially-designed ASICs (application-specific integrated circuits) or FPGAs (Field-Programmable Gate Arrays). A computer can generally also receive (read) programs and data from, and write (store) programs and data to, a non-transitory computer-readable storage medium such as an internal disk (not shown) or a removable disk. These elements will also be found in a conventional desktop or workstation computer as well as other computers suitable for executing computer programs implementing the methods described herein, which may be used in conjunction with any digital print engine or marking engine, display monitor, or other raster output device capable of producing color or gray scale pixels on paper, film, display screen, or other output medium.
Any data disclosed herein may be implemented, for example, in one or more data structures tangibly stored on a non-transitory computer-readable medium. Embodiments of the invention may store such data in such data structure(s) and read such data from such data structure(s).
| Number | Date | Country | |
|---|---|---|---|
| 62486151 | Apr 2017 | US |
