Professional Documents
Culture Documents
Interfaces
Publication details, including instructions for authors and subscription information:
http://pubsonline.informs.org
This article may be used only for the purposes of research, teaching, and/or private study. Commercial use
or systematic downloading (by robots or other automatic processes) is prohibited without explicit Publisher
approval, unless otherwise noted. For more information, contact permissions@informs.org.
The Publisher does not warrant or guarantee the articles accuracy, completeness, merchantability, fitness
for a particular purpose, or non-infringement. Descriptions of, or references to, products or publications, or
inclusion of an advertisement in this article, neither constitutes nor implies a guarantee, endorsement, or
support of claims made of that product, publication, or service.
INFORMS is the largest professional society in the world for professionals in the fields of operations research, management
science, and analytics.
For more information on INFORMS, its publications, membership, or meetings visit http://www.informs.org
Vol. 45, No. 6, NovemberDecember 2015, pp. 485500
ISSN 0092-2102 (print) ISSN 1526-551X (online) http://dx.doi.org/10.1287/inte.2015.0825
2015 INFORMS
Advertisement Spots
Saravanan Venkatachalam
Department of Industrial and Systems Engineering, Wayne State University, Detroit, Michigan 48202, saravanan.v@wayne.edu
Amit Aggarwal
iHeartMedia Inc., New York, New York 10019, AmitAggarwal@iheartmedia.com
In this paper, we describe the implementation of an optimization suite (OS) to facilitate the scheduling of radio
advertisements for one of the largest media companies in the United States. Advertisements are scheduled
adhering to complex criteria from the advertisers with the objective of maximizing the revenue for the company.
Advertisers offer two types of flexibility for demand fulfillment: market flexibility provides an opportunity to
shift the demand across demographics, and time flexibility allows the demand to be shifted across the broadcast-
ing time horizon. The scale of inventories, fair and equitable distribution, flexibilities, and other complex criteria
from the advertisers necessitated the development of a sophisticated OS to generate rosters for the placement of
advertisements. The OS uses optimization models and four heuristics procedures to generate an advertisement
placement roster for each station. The company has adapted the OS into its information systems to seamlessly
incorporate optimization into its decision-making process.
Keywords: prescriptive analytics; decision support; radio broadcasting; advertisement placement; advertisement
schedules; time and market flexibility.
History: This paper was refereed.
iHeartMedia, Inc. (IHM), which owns over 850 sta- Literature Review
tions in more than 150 cities, is one of the largest To the best of the authors knowledge, the literature
providers of network radio programming and traffic contains no references to scheduling commercials on
information in the United States. As part of its wide-
Downloaded from informs.org by [129.100.253.90] on 13 October 2017, at 08:09 . For personal use only, all rights reserved.
problem sizes of approximately 2640 advertisement GRP orders. GRPs are collected by marketing agen-
spots. cies and used to quantify the order fulfillments for the
Jones (2000) introduced the advertising allocation placement of advertisements. IHM has approximately
problem as an example of combinatorial auctions for 200 markets, and each market typically has 1020 sta-
Downloaded from informs.org by [129.100.253.90] on 13 October 2017, at 08:09 . For personal use only, all rights reserved.
which hundreds of potential advertisers can submit tions. It divides a day into eight parts, which we refer
bids for airing their commercials in advertising slots. to as day parts, of three hours each.
The author proposed a mixed-integer programming IHM has three departments that work closely to-
(MIP) model, which considers the locations of the gether to sell and schedule advertisement spots: the
time slots. The model is computationally prohibitive sales department sells advertisements to be aired dur-
and uses a constraint-programming heuristic to find ing program breaks; the traffic department schedules
feasible solutions. The campaigns are assumed to advertisements on programs that meet the advertis-
be continuous; breaks are not allowed between the ers requirements; and the billing department bills
weeks of the advertisement schedule (i.e., the adver- advertisers for the advertisements that they have
tisements must run each week of the schedule). scheduled and have been aired. The schedulers within
Zhang (2006) used a two-step hierarchical approach the traffic department are responsible for preparing
to allocate television advertisements. The author pro- rosters for the inventory of advertisement slots. This
poses a winner-determination problem to select adver- team prepares rosters for all the markets for the fol-
tisers; subsequently, an assignment program schedules lowing week. Prior to implementing the OS, this was
the selected advertisers commercials. The winner- a weeklong process. Each week, the team finalizes the
determination problem uses a column-generation rosters for the following week by Thursday night, and
algorithm, and the assignment program is an MIP sends the rosters to the broadcasting team in each
model. The author reported computational results for individual market on Friday. Inevitably, last-minute
a maximum of 32 programs and 200 advertisers and orders will need to be included with minimal dis-
presented an approximation algorithm to solve the ruptions to the existing roster, and unsold spots will
model. be replaced by the paid spots. The objective of the
Market and time flexibilities are unique aspects work we present in this paper is to assist the traf-
of the radio advertising market and are typically fic department in preparing the rosters with fair and
not found in the television advertising market. In equitable distribution and with all other restrictions
exchange for lower rates, some advertisers allow a that are included in the advertiser orders. All of the
percentage of their demand to shift between defined remaining unsold inventory, which we call overdeliv-
markets and time periods. As a result, we need to eries, may be allotted to the advertisers; overdeliv-
consider all the markets together in making decisions. eries for an advertiser are typically used for public
Our approach also allows discontinuous campaigns service announcements or allocated for other internal
(i.e., breaks between the weeks of the advertisement purposes (e.g., promotions).
schedule).
Current Practice and the Need for Analytics
An advertisers order typically has multiple order
Background lines. Each order line specifies the details of the
A market refers to a large demographic representation demand, including market, broadcasting granularity
(e.g., Houston market, New York market); a station (e.g., daily, weekly, quarterly, monthly, or yearly),
is an entity that broadcasts advertisements within a inclusion and exclusion rules, preferences, days in
given market. Stations are (1) rated with GRP, (2) non- a week, air services (i.e., types of programs), rate,
rated without GRP, or (3) noncommercial. Nonrated broadcast type, and type of order (i.e., spot or GRP),
stations are new or have low demographic coverage. for airing that advertisers advertisements. Figure 1
Noncommercial stations are typically religious chan- shows a sample order form. The form captures the
nels. Approximately 70 percent of the stations are details for an order line, such as quantity, market,
rated; therefore, only these stations can be used for inventory group, broadcast times, weeks on and (or)
Venkatachalam et al.: Media Company Uses Analytics to Schedule Radio Advertisements
488 Interfaces 45(6), pp. 485500, 2015 INFORMS
Air days: Air services: Air formats: Exclude titles: For stations:
Disp: All services: All formats: Market:
Monday: News wire: Country: Rated:
Tuesday: AP-15s: Oldies: Nonrated:
Wednesday Beach: Jazz hits: Noncommercial:
Thursday: Weather channel: O.D.:
Friday: Real traffic: Classical:
Saturday: Web traffic:
Sunday:
Figure 1: IHM uses a mock customer order screen to capture various requirements and restrictions for an adver-
tisers order line. The inclusion and exclusion selections for an order line define its inventory.
off, rate, spot type, and spot distribution. The form Feature Inefficiency
includes fields that capture days, service, formats, and
stations, and define the inventory to be used for the Scheduling in a sequential Low-quality schedules for orders with
manner fewer restrictions and priorities
placement of an advertisement of an order line. We
Scheduling only one market or Suboptimal inventory use
refer to these as inclusion-exclusion rules for the order week at a time
lines. Order lines typically specify the proportion of Fairness and equitable Not modeled
spots to be placed in the rated and nonrated stations distribution
Solution requires manual updates Inefficient and error prone
in a spot order; GRP order lines can be satisfied only Scheduling only one week in the Short-sighted planning process
by rated stations. future
The advertisers order lines can be for discontin- Time and market flexibility Not modeled
uous campaigns; in these campaigns, the advertiser
Table 1: The list of features depicts the practice at IHM prior to imple-
selects the broadcasting weeks and (or) days from the menting the OS. Some key features, such as fairness, equitable dis-
entire orders broadcasting horizon. Advertisers give tribution, time, and market flexibility, are desirable characteristics for
their preferences for stations, days of the week, and advertisement rosters; however, IHM did not model them because of their
complexities.
day parts. Advertiser orders also specify the period
within which a predefined number of advertisements
is to be broadcast. This period can be daily, weekly,
monthly, or quarterly. Prior to implementing the OS, The following flexibilities, which we build into the
IHM used an in-house process to prepare the rosters. OS, provide advertisers with better opportunities for
This process used a rule-based approach by which it placing advertisements. Market flexibility (MF) offers
ranked the order lines based on a series of criteria and an advertiser the opportunity to move the demand
scheduled the order lines based on their rankings. The in an order line from the specified market to another
rosters were applicable to only the first week in the desirable market. As an incentive, based on the adver-
planning horizon. Table 1 shows some challenges that tisers flexibility, additional advertisement spots are
this practice presented. provided in the market to which the advertisements
Venkatachalam et al.: Media Company Uses Analytics to Schedule Radio Advertisements
Interfaces 45(6), pp. 485500, 2015 INFORMS 489
50 50
Downloaded from informs.org by [129.100.253.90] on 13 October 2017, at 08:09 . For personal use only, all rights reserved.
30 30
20 20
10 10
0 0
8_28_8
8_98_15
8_168_22
8_238_29
8_309_5
9_69_12
9_139_19
9_209_26
9_2710_3
8_28_8
8_98_15
8_168_22
8_238_29
8_309_5
9_69_12
9_139_19
9_209_26
9_2710_3
Weeks Weeks
Figure 2: The graphs illustrate the movement of an order lines demand from the Los Angeles to New York market
as a result of market flexibility.
are moved. To illustrate, suppose an advertisers inventory utilization, and help IHM to place the
order line specifies 100 spots for the Los Angeles advertisements based on advertisers preferences. A
market in the next five weeks. If the order line also time-flexible order line offers the flexibility to sched-
includes the New York market as acceptable with a ule the advertisement spots within a range of the
limit of 20 percent, then the order line allows broad- planning horizon without strictly adhering to an
casting 80 advertisement spots in the Los Angeles equal distribution of an order line. To illustrate, sup-
market and the remaining 20 in the New York mar- pose an advertisers order line requests 100 spots
ket; however, because of the 20 percent incentive pro- in four weeks with a TF factor of 20 percent. The
vided, the advertiser will receive 24 broadcast spots number of advertisement spots to be broadcast based
in the New York market. MF is applicable only in on the order line ranges from 20 to 30 each week.
markets acceptable to the advertiser. This flexibility
TF is illustrated in Figure 3, where the pressure on
allows IHM to compensate an advertiser who wishes
inventory in week 8_16 to 8_22 is eased by spread-
to advertise in a high-demand market by using inven-
ing order lines across weeks 8_98_15 and 8_238_29.
tories from other markets. The example in Figure 2
TF also requires the advertisers consent. MF and TF
shows the net effect of moving excess demand from
the Los Angeles market to the New York market. This are unique features in radio advertisements, which
shift in demand is significant in terms of revenue gen- are not available for scheduling television advertising.
eration because it provides a means to move an adver- Another consideration in placing advertisements is
tisers demand across markets, thereby increasing the that advertisers prefer to avoid repeat broadcasts, that
fill rate for the order lines. is, broadcasting the same order line from an adver-
Time flexibility (TF) permits uneven distribution of tiser at same time and same station for two or more
placements for an advertisers order line across place- consecutive days or multiple times within a same day
ment weeks to accommodate the varying amounts part. In addition, order lines with spot requirements
of overall market demand for inventory in the have limitations on the number of spots that can be
placement weeks. These flexibilities provide better broadcast on a nonrated or noncommercial station.
Venkatachalam et al.: Media Company Uses Analytics to Schedule Radio Advertisements
490 Interfaces 45(6), pp. 485500, 2015 INFORMS
8_98_15
8_168_22
8_238_29
8_309_5
9_69_12
9_139_19
9_209_26
9_2710_3
IT system
Inventory data Roster
Downloaded from informs.org by [129.100.253.90] on 13 October 2017, at 08:09 . For personal use only, all rights reserved.
SD model SD post-processing
SD model SD post-processing
MW MW
model post-processing
SD model SD post-processing
LP model Heuristics
SD model SD post-processing
OS
MIP model Heuristics
Figure 4: The optimization suite consists of a linear programming model to determine the targets for the markets,
a mixed-integer programming model for each market to assign individual inventory spot to an advertisers order
line, and a series of heuristics to improve the quality of the solution.
Data Characteristics
Weeks No. of markets No. of stations No. of day parts No. of inventory
Downloaded from informs.org by [129.100.253.90] on 13 October 2017, at 08:09 . For personal use only, all rights reserved.
Table 3: The number of inventory spots indicates the magnitude of the planning horizon. A higher number of day
parts compared to inventory spots indicates that some day parts have no inventory to schedule.
Model characteristics
Weeks No. of markets No. of constraints No. of variables No. of nonzeros No. of SD models
Downloaded from informs.org by [129.100.253.90] on 13 October 2017, at 08:09 . For personal use only, all rights reserved.
Table 4: The number of constraints, variables, and nonzeros indicate the characteristics of the market-week
model; the number of SD models represents the number of station-day mixed-integer programming models
solved during each run.
the MW and SD models to meet IHMs needs. We also The overall optimality was compromised because of
created various combinations of penalty profiles. A using sequential optimization, an LP model for MW,
user from the traffic department selects a suitable pro- and a rounding heuristic to determine the targets for
file based on his or her requirements. In Table 4, No. the SD models.
of markets represents the total number of markets; During the implementation of the OS, IHMs
No. of constraints, No. of variables, and No. of nonze- responsibilities included defining business require-
ros represent the total number of constraints, vari- ments, design review, data collection and formatting,
ables, and nonzeros, respectively, for the MW model, testing and validation of placements, and system inte-
and No. of SD models is the total number of SD mod- gration. The duties of the OS provider included gath-
els created. We developed the models using Java with ering business requirements, data validation, devel-
CPLEX 12.1 as the optimization engine. For the imple- opment and tuning of mathematical models and
mentation, we used Dell T710 (two quad core pro- heuristics, results review, and project management.
cessors) hardware with 64GB main memory running IHM and the OS provider staff members together
on RedHat Enterprise Linux 5.5 (x86-64). Barrier opti- expended approximately 6,500 person-hours.
mizer in CPLEX was used to solve the MW model. For
a 10-week planning horizon, it takes approximately Benefits Summary
15 minutes on average to reach optimality. We used IHMs initial interest in the development of an OS
different levels of optimality gaps for the SD models, was driven by customer service issues and a desire to
a 0.5 percent MIP gap for the first week of the plan- have better visibility of its future inventory availabil-
ning horizon, and one percent for the other weeks. ity. Using the previous spot-placement process, IHM
Because the OS is run every week, we used a lower could not accurately deliver GRP orders; it focused
percentage for an MIP gap for the first week in the only on creating the placements for the next broad-
planning horizon. The overall run time for a 10-week cast week. The OS benefits IHM in the following
planning horizon is approximately five hours using ways:
the hardware listed above. Because the SD models are 1. Enhanced inventory usage: Market and time
independent of each other, we solve them in parallel. flexibilities help to shift the demand, and the OS
Venkatachalam et al.: Media Company Uses Analytics to Schedule Radio Advertisements
494 Interfaces 45(6), pp. 485500, 2015 INFORMS
improves inventory usage. The previous placement fashion. In IHMs previous process, no bound was
process recognized only spot orders; therefore, IHM placed on the number of overdelivery spots allo-
had to translate GRP orders into an estimated num- cated to an advertiser. For example, an advertiser who
ber of spots. An order line would specify the required purchased 100 spots might have received 200 spots
Downloaded from informs.org by [129.100.253.90] on 13 October 2017, at 08:09 . For personal use only, all rights reserved.
GRPs in a market, and IHM would estimate the in overdelivery. This practice on a potentially recur-
required number of spots by assuming a fair and ring pattern could cause the advertisers to expect
equitable distribution of spots across the specified sta- large quantities of overdelivery spots and to there-
tions based on the stations available inventory. How- fore reduce their paid spots based on this expectation.
ever, if other spot-based orders requested only spe- Furthermore, in a competitive space, advertisers who
cific stations (cherry-picking), which are commonly may have paid higher rates and who are more valu-
the higher-rated stations, then the estimated number able to the organization are overshadowed with the
of spots would be insufficient to meet the targeted sheer magnitude of spots (both paid and overdeliv-
GRP demand. In some cases using the former pro- ered). Although this does not have a direct revenue
cess, the GRP delivery shortage for an order could be impact, it contributes to the advertisers goodwill,
as high as 25 percent. Over the course of a year, the which helps IHM to maintain a better client relation-
revenue impact could total $1,000,000 (or more) and ship and maintain revenues.
could damage customers goodwill. IHM has been 4. Enhanced business processes: Accurate inven-
able to provide GRP estimates to the OS, thus allow- tory visibility for the future weeks allows the sales
ing the OS to accurately assess the orders GRP targets teams to know which inventory is low so that they
and alleviating these problems. can try to get premium pricing for any additional
2. Enhanced customer service: The OS also pro- advertisers who want to purchase the inventory. Con-
vides fairer and more equitable distribution of the versely, if the sales teams know which inventory is
spots across the days of week and day parts. A good plentiful, they can be more aggressive with their pric-
distribution keeps the allocated placements in closer ing to sell it. The OS has also increased the efficiency
alignment with customer expectations. Although of placement operations. Compared to the volume of
the improved distribution provides no direct rev- spots handled previously, the IHM operations staff
enue impact, it improves customer goodwill, which can now handle twice the volume of spots it handled
typically translates into future revenue from the previously.
advertisers. 5. Monetary benefits: Considering the spot orders
3. Streamlined allocation of overdelivery: The OS only, the OS improved revenue by one percent over
also streamlines the allocation of overdelivery spots. the previous placement process, which translates into
In any available commercial spot that is not sold, multiple millions of dollars on an annual recurring
something must be aired during its specified time or basis. Furthermore, in a typical week, the increase in
be assimilated back into the radio program (e.g., the inventory utilization for spot orders is approximately
on-air personalities must fill the additional time). The two percent. The difference in the revenue and spot
available commercial time may be filled with items placement percentages is attributable to the focus on
such as additional free spots to the advertiser (overde- placing higher-revenue spots first so that the addi-
livery), public service announcements, or promotional tional spots are of lower revenue value than those that
items. The previous placement process would typi- were placed initially, and provide a better overall uti-
cally allocate any unsold spots to those advertisers lization of inventory. Based on gross profit, IHM con-
who had purchased the most number of spots. This servatively estimates the monetary benefit it receives
process tended to reward the volume purchasers of as a result of enhanced customer service and better
spots rather than the advertisers who bought smaller business processes to be over $500,000 per year.
quantities, but paid higher rates. The OS allows a We can summarize the key benefits of the OS as
more targeted delivery of the excess inventory to follows:
those customers who are deemed more valuable, An increase of one percent in invoiced revenue
thereby assigning overdelivery in a more structured on the placement of spot orders;
Venkatachalam et al.: Media Company Uses Analytics to Schedule Radio Advertisements
Interfaces 45(6), pp. 485500, 2015 INFORMS 495
Additional revenue of more than $1,000,000 each Ra I Set of all rated inventory (market, week, station,
year from the GRP orders as a result of better fulfill- period) belonging to advertiser a A from the
ment of GRP targets; inventory set I.
Decrease in customer complaints as a result of Na I Set of all nonrated inventory (market, week,
Downloaded from informs.org by [129.100.253.90] on 13 October 2017, at 08:09 . For personal use only, all rights reserved.
Model Formulation whereas constraint (6) defines the soft lower bound for MF,
X X X because the penalty helps to provide a minimum guarantee
max 4ra + ail 54Xail + Yail 5 to the advertisers order to be broadcast in the requested
aA iRa Na lLa market. For constraints (7) and (8), the parameter asw is
Downloaded from informs.org by [129.100.253.90] on 13 October 2017, at 08:09 . For personal use only, all rights reserved.
f
XX X 0
Uamw e
XX X
4Uasw + Vasw 5 calculated as the ratio of the number of potential inven-
aA mM wW aA sS wW tory spots for the advertiser in a particular station s, to the
sum of potential inventory spots for the advertiser from all
s 0 potential stations. The variables Uasw and Vasw get the sur-
XXX
Vast (1)
aA sS tT plus and slack from attaining the target for the advertiser
a for station s to maintain the fair and equitable distribu-
Inventory constraints
tion. Constraint (9) limits the number of spots allotted to
X
Xail +
X
Yail dal a A1 l La 1 (2) advertiser a for a particular period t; hence, it helps the
iRa iNa postprocessing process to efficiently minimum separation
requirements. Finally, constraint (10) gives the inclusion and
Xail istr
XX X
s1 t Ist 1 (3) (or) exclusion for the variables based on the requirements
aA lLa iRa Ist
of an advertisers order. For conciseness, we have defined
Yail istn
XX X
s1 t Ist 0 (4) only the variables and constraints for a rated station. Sim-
aA lLa iNa Ist ilar to constraints (5)(9), constraints and variables should
also be defined for nonrated and commercial stations. Sim-
Time and market flexibility constraints ilarly, F&E constraints are defined only at a station level,
X X
Xail uamw a A1 m M1 w W1 (5) and similar type of variables and constraints should be con-
iImw Ra lLa structed to assure F&E at days of week, program types, and
day parts. We solve the model as an LP model; it gives the
0
X X
Xail + Uamw lamw a A1 m M1 w W1 (6) consolidated target for each advertisers order line in each
iImw Ra lLa
market and week. However, continuous targets from the LP
Affiliate F&E constraints model will be incorrect for the subsequent SD model; hence,
we use a rounding heuristic, which we explain in the MW
X X X X
Xail Uas0 w as0 w Xail Postprocessing section.
iIs 0 w Ra lLa iIsw Ra lLa
MW Postprocessing
a A1 s 0 S1 w W1 (7)
The following rounding heuristic is used to round off the
MW model targets to be used in the SD model. For each
X X X X
Xail + Vas0 w as0 w Xail
iIs 0 w Ra lLa iIsw Ra lLa advertiser a, order line La , and market for order-line m, let
xw and yw be the targets from the MW model for the rated,
a A1 s 0 S1 w W1 (8)
nonrated, and noncommercial allocation in week w. Let xw0 ,
Time-separation constraints yw0 be their rounded values, respectively.
1. Spot orders (not time flexible): For each week w, round
0
X X
Xail Vast ast a A1 s S1 t T1 (9) xw and yw target values such that the total delivery in each
iIst Ra lLa week is equal to the closest integer value of the original
sum, and thus does not exceed the weekly demand; that is,
Select and exclude constraints
xw0 + yw0 xw + yw + 005, w. The change in the values is
Xail 0 a A1 i Ra 1 l La 1 limited to rounding up or down; that is, xw xw0 xw +
0 Yail ail a A1 i Na 1 l La 1 (10) 1, w, and similarly, yw yw0 yw + 1, w.
Xail 1 Yail 00 2. Time flexibility: The goal is to round xw , yw for all
w = 11 0 0 0 1 W by shifting fractional values among them such
In the objective function, we maximize the potential rev- that:
enue from the advertisers less the penalties resulting from (a) Total delivery over all weeks should be equal to the
MF and TF, deviation from F&E, and exceeding the targets closest integer value of the original sum, and thus does
based on minimum time separation. Constraint (2) states not exceed the total demand, which we achieve by
that the assignment for any advertiser should not exceed its X 0
4xw + yw0 5
X
order-line demand, and constraints (3) and (4) state that the 4xw + yw 5 + 005 1 w0
same inventory cannot be assigned to more than one adver- w w
tiser. The derived parameter uamw gives the hard upper (b) Total delivery in each week does not exceed the TF
bound on the number of inventory spots to be allowed for percentage constraint, which we achieve by
the market and week for an advertiser based on its adoption
toward MF. Constraint (5) defines the hard upper bound, xw0 + yw0 xw + yw + 11 w0
Venkatachalam et al.: Media Company Uses Analytics to Schedule Radio Advertisements
Interfaces 45(6), pp. 485500, 2015 INFORMS 497
(c) Total nonrated delivery over all weeks should not R0a I Set of all rated individual inventory feeds (feed,
exceed the total nonrated demand, which we achieve by market, week, station, period) belonging to
X 0
X
advertiser a A from inventory set I.
yw yw + 11 w0 N0a I Set of all nonrated individual inventory feeds
Downloaded from informs.org by [129.100.253.90] on 13 October 2017, at 08:09 . For personal use only, all rights reserved.
w w
(feed, market, week, station, period) belonging to
(d) The change in the values is limited to rounding up advertiser a A from inventory set I.
or down, which we achieve by Gt Set of all inventory feeds that are to be broadcast
xw xw0 xw + 11 w and together at period t.
yw yw0 yw + 11 w0 Parameters
0
5. GRP Orders (market and nonmarket flexibility): For GRP asw Target quantity from the MW model to be assigned
orders, we round xw for all w = 11 0 0 0 1 W by shifting frac- to advertiser a for station s for F&E rotation.
tional values among them such that:
(a) Total GRP delivery from rated spots over all weeks Penalties
should equal the closest rounded value (two decimal e Penalty for each unit of assignment that is above or
places) of the original sum, and thus does not exceed below the F&E target.
GRP demand. We achieve this by s Penalty for each unit of assignment exceeding the
allowable amount in a period.
xw 102 xw + 005 102 0
X 0 X
b Penalty for back-to-back placement.
w w
X X
Xafl +
X X 0
Yafl + Pal = asw a A1 l La 1 gap in solving the SD model, overdelivery of unallocated
lLa f R0 a lLa iN0 a inventory spots, and violation of minimum time separation
(13) between similar types of advertisements.
1. Recovery heuristic: The recovery heuristic schedules
Back-to-back advertiser constraints order lines to inventory feeds that are within specifications,
but are unscheduled so far. Here, we show the order of exe-
Xafl + Xaf 0 l Bafl 1 cution:
a A1 l La 1 f1 f 0 R0 a 1 t4f 5 t4f 0 5 = 11 (14) (a) Close the MIP optimality gap from the SD model.
For any order line with an unmet MW target, and if spots
Affiliate F&E constraints are unscheduled after solving the SD model, we assign
the spots to the order line to minimize bumping.
0
X X
Xafl Uas0 w + Vas0 w = as 0w a A1 (15) (b) Overdelivery for compliance.
f R0 a Is 0 w lLa The algorithm works as follows: Let L be the set of order
lines to be scheduled, and D be the set of broadcast dates.
Group-link constraints
Perform the following for each order line l in L:
Xafl Xaf 0 l = 0 a A1 l La 1 f1 f 0 R0 a Gt 1 (16) Recovery heuristic:
Time-separation constraints Step 1: Initialization: Let q be the target quantity for this
algorithm to schedule an order line l on broadcast dates
0
X X
Xafl Vast ast a A1 t T1 (17) in D. Let S be the set of all unscheduled spots for l with
f Ist R0 a lLa broadcast dates in D.
Step 2: If q 0 or S = , STOP.
Select and exclude constraints
Step 3: Let s be the first element in S. Let x be the number
Xafl 801 19 a A1 i R0 a 1 l La 1 of demand units that s can satisfy for an order line l (x
(18) may be greater than 1 for simulcast or linked groups, or
Yafl 801 19 a A1 i N0 a 1 l La 0
fractional for GRP). Schedule s to l. Set q q x, and
Constraint (12) allocates each inventory feed to only one S S \ 8s9. Go to Step 1.
advertiser a for an order line l. Constraint (13) deduces the
4. Overdelivery heuristic: The overdelivery heuristic is
unallocated demand for each customers order line based
used to deplete the unsold inventory for the upcoming
on the target from the MW model. For advertiser as order
scheduling week in an F&E manner. The quantity allotted
line l, Xafl and Yafl give the allotted rated and nonrated
to each order line is proportional to the demand quantity of
inventory feeds, respectively. Constraint (14) captures the
the order line. The heuristic works as follows: Let w be the
value for Bail to be penalized in the objective function for the
first week of the planning horizon. For each market m, let
allotment of back-to-back inventory feeds, that is, inventory
u be the total unscheduled inventory of market m in week
feeds that are broadcast exactly at the same time on two
w. Let S be the set of all stations in the market. Let L be the
consecutive days for the same advertiser a. Constraint (15)
set of order lines in market m that accept overdelivery and
is similar to the F&E constraint from the MW model; it cap-
have demand in week w. Let q be the total ordered quantity
tures the slack and surplus assignments based on the MW
in week w. Perform the following process for each order
model target, and the slack and surplus are penalized in the
line l in L:
objective function. If any inventory feed in a simulcast or
linked group is assigned to an order line on a given broad- Overdelivery heuristic:
cast date, then all feeds in that simulcast or linked group Step 1: Initialize j = 1. Let q l be the demand of order line
must be assigned to the same order line on that broadcast l in week w. Calculate the target total overdelivery quan-
date on different stations. Constraint (16) assures the allot- tity for l as t l = u q l /q. Let ul be the number of spots
ment of group-link inventories to the same advertiser a and (scheduled or unscheduled) that are within specifications
order line l. Constraint (17) is similar to constraint (9) in for an order line l in market m in week w.
the MW model, which gives the bound on the number of Step 2: If j > S, STOP.
spots to be broadcast for period t, so the time-separation Step 3: Let usj be the number of spots (scheduled or
constraint can be handled efficiently in the postprocessing unscheduled) for an order line l in station sj in week w.
of the SD model. Constraint (18) gives the binary restric- Calculate the station-wise target for order line l as t sj =
tions for Xafl and Yafl variables. t l usj /ul .
Venkatachalam et al.: Media Company Uses Analytics to Schedule Radio Advertisements
Interfaces 45(6), pp. 485500, 2015 INFORMS 499
Step 4: Let U sj be the set of all unscheduled spots that Lilien GL, Kotler P, Moorthy KS (1992) Marketing Models (Prentice-
can be scheduled to l as overdelivery with broadcast date Hall, Englewood Cliffs, NJ).
in w. Mahajan V, Muller E (1986) Advertising pulsing policies for gener-
ating awareness for new products. Marketing Sci. 5(2):89106.
Step 5: If t sj 0 or U sj = , set j j + 1, and go to Step 1. Nielsen (2014) How U.S. adults use radio and other forms of
Downloaded from informs.org by [129.100.253.90] on 13 October 2017, at 08:09 . For personal use only, all rights reserved.
Step 6: Let u be the first element in U sj . Schedule u to l. audio. Accessed July 7, 2014, http://www.nielsen.com/
Set t sj t sj 11 and U sj U sj \ 8u9. Go to Step 4. content/dam/corporate/us/en/newswire/uploads/200%9/11/
VCM_Radio-Audio_Report_FINAL_29Oct09.pdf.
7. Sequence-constraint heuristic: Sequential constraints to Radio Advertising Bureau (2014) Radios ROI advantage. Accessed
address the minimum separation among similar types of July 7, 2014, http://www.rab.com/public/ral/studyDocs/
advertisement spots are difficult to include in the MW or SD roiFull.pdf.
optimization models, because including them would expo- Rust RT, Eechambadi NV (1989) Scheduling network television
nentially increase the number of constraints in the model. programs: A heuristic audience flow approach to maximizing
audience share. J. Advertising 18(2):1118.
Hence, in both the MW and the SD models, we address Simon H (1982) Adpuls: An advertising model with wearout and
sequential constraints as upper limits for each advertiser pulsation. J. Marketing Res. 19(3):352363.
type for any day part. The upper limit on the allowed Webster JG (1985) Program audience duplication: A study of
number of assignments for an advertiser type is expected television inheritance effects. J. Broadcasting Electronic Media
to be helpful in the postprocessing. We set the following 29(2):121133.
Zhang X (2006) Mathematical models for the television advertising
heuristic in the postprocessing to remove any violations of
allocation problem. Internat. J. Oper. Res. 1(3):302322.
sequence constraints. These models are very small; they typ-
ically have 2030 variables and 1015 constraints, and are
Verification Letter
solved in parallel.
John Kaufman, President, Business Operations, iHeart-
Sequence-constraint heuristic procedure: Media, Inc., 125 West 55th St., New York, NY 10019, writes:
Step 1: Based on the SD solution, let t be the day part at To whomsoever it may concern:
which the sequence constraint is violated. Let the time- The purpose of this letter is to verify the paper
line T be set as T = 8t1 t + 19. Initialize k = 1. titled Media Company Using Analytics to Schedule
Step 2: Construct a SD model only for the set T with all Radio Advertisement Spots. The optimization suite (OS)
the assignments from the solution as targets for the order described in this paper is currently being used within the
lines. If feasible, then use the new solution and go to sales planning/placement processes on a daily basis by
Step 2. multiple of our businesses. We have achieved the quantita-
Step 3: On infeasibility, add the day part k if 4t 4k tive and qualitative benefits described in the Benefits section
155 < 4k + 15 t and k < maxLimit, then add 4k 15 to of this paper from using the OS in our Total Traffic and
the set T ; otherwise add 4k + 15 to T . Increment k and go Weather Network (TTWN) business unit.
to Step 2.
Saravanan Venkatachalam is an assistant professor in the
Industrial and Systems engineering department at Wayne
References State University. He has nine years of work experience in
the design and development of decision support systems in
Arbitron (2014) Radio landscape 2013. Accessed July 7, 2014, http:// the domains of supply chain management, revenue man-
www.arbitron.com/downloads/radio_landscape_pt1.pdf. agement, and contact center operations. He has a PhD in
Bollapragada S, Bussieck MR, Mallik S (2004) Scheduling commer-
Industrial Engineering from Texas A&M University.
cial videotapes in broadcast television. Oper. Res. 52(5):679689.
Bollapragada S, Cheng H, Phillips M, Garbiras M, Scholes M, Fion Wong is a pricing and revenue management prac-
Gibbs T, Humphreville M (2002) NBCs optimization systems titioner who has solved real-world revenue optimization
increase revenues and productivity. Interfaces 32(1):4760. problems in the media, airline, and hospitality industries.
Federal Communications Commission (2014) Broadcast radio AM Techniques that she has applied include mathematical pro-
and FM application status lists. Accessed July 7, 2014, http:// gramming, time-series forecasting, and consumer choice
www.fcc.gov/encyclopedia/broadcast-radio-am-and-fm-applic
modeling. Fion has a Master of Science degree in industrial
%ation-status-lists.
Goodhardt GJ, Ehrenberg ASC, Collins MA (1975) The Television engineering from Georgia Institute of Technology. She cur-
Audience: Patterns of Viewing (Saxon House Westmead, UK). rently works at the Revenue Management department of
Headen RS, Klompmaker JE, Rust RT (1979) The duplication of Delta Air Lines in Atlanta.
viewing law and television media schedule evaluation. J. Mar- Emrah Uyar is a senior operations research consul-
keting Res. 16(3):333340. tant at JDA International Ltd, Bracknell, UK. He has
Henry MD, Rinne HJ (1984) Predicting program shares in new time seven years of experience in design and implementation
slots. J. Advertising Res. 24(2):917.
Jones JL (2000) Incompletely specified combinatorial auction:
of pricing/revenue management solutions in various ser-
An alternative allocation mechanism for business-to-business vice industries including media, leisure, transportation and
negotiations. Unpublished doctoral dissertation, University of hospitality. He has a PhD in industrial engineering from
Florida, Gainesville, FL. Georgia Institute of Technology and is a former Thomas
Venkatachalam et al.: Media Company Uses Analytics to Schedule Radio Advertisements
500 Interfaces 45(6), pp. 485500, 2015 INFORMS
Johnson Fellow. He also holds Richard E. Rosenthal Young MBA from the Fuqua School of Business at Duke University
Researcher Award 2010 from INFORMS. and a BEE from the Georgia Institute of Technology.
Stan Ward is a senior practice director for the JDA Soft- Amit Aggarwal is currently executive vice president of
ware Group, Inc. He has over 23 years of experience in Revenue Management at iHeartMedia, Inc. He has more
Downloaded from informs.org by [129.100.253.90] on 13 October 2017, at 08:09 . For personal use only, all rights reserved.
pricing/revenue management and large scale data ana- than 15 years of experience in revenue strategy, pricing, sys-
lytics as a consultant, implementer and innovator across tems and data across several industries including airlines
industries, including television broadcasting, radio, pack- (Priceline.com), hotels (Starwood Hotels and Resorts), and
age delivery, hotels, cruise lines, and airlines. He earned an media (iHeartMedia, Inc.).