Systems and methods for controlling initialization of advertising campaigns
A system is provided for controlling initialization of an online advertising campaign. The system includes a sensor configured to determine current performance of the online advertising campaign and a memory for storing performance information obtained by the sensor, a set of campaign initialization controller instructions, a campaign volume model, and a network average time-of-day pattern. The system also includes an estimator configured to predict future campaign performance based on the performance information obtained by the sensor, the campaign volume model, and the network average time-of-day pattern. The system also includes an initialization controller configured to generate a bid allocation control signal and generate a bid price control signal based on the future campaign performance predicted by the estimator, according to the instructions stored in the memory. A method for controlling initialization of an online advertising campaign is also provided.
1 . A system for controlling initialization of an online advertising campaign, the system comprising:
a sensor configured to determine a current condition of the online advertising campaign;
a memory for storing the condition obtained by the sensor, a set of campaign initialization controller instructions, a campaign volume model, and a network average time-of-day pattern;
an estimator configured to predict future campaign performance based on the condition obtained by the sensor, the campaign volume model, and the network average time-of-day pattern; and
an initialization controller configured to generate a bid allocation control signal and generate a bid price control signal based on the future campaign performance predicted by the estimator, according to the instructions stored in the memory, wherein the bid allocation control signal and bid price control signal are used to adjust future performance of the online advertising campaign.
2 . The system of claim 1 , wherein the sensor is configured to determine a marginal volume and a reference volume of the online advertising campaign.
3 . The system of claim 1 , wherein the estimator is configured to estimate a marginal volume of the online advertising campaign as a function of an effective allocation control signal and an effective price control signal.
4 . The system of claim 1 , wherein the estimator is configured to estimate a marginal volume of the online advertising campaign based on a time-of-day pattern for a network on which the online advertising campaign is running.
5 . The system of claim 1 , wherein the estimator is configured to estimate a marginal volume of the online advertising campaign as a function of an effective allocation control signal, an effective price control signal, and a time-of-day pattern for a network on which the campaign is running.
6 . The system of claim 1 , wherein the initialization controller is configured to adjust bid price and bid allocation simultaneously and in real-time.
7 . The system of claim 1 , wherein the initialization controller is configured to generate the bid allocation control signal based on a predetermined ramp-up function.
8 . The system of claim 7 , wherein the predetermined ramp-up function is a linear function starting from a small number between 0 and 1.
9 . The system of claim 4 , wherein the initialization controller is configured to generate the bid price control signal based on the marginal volume estimated by the estimator.
10 . The system of claim 1 , wherein the initialization controller is configured to generate the bid price control signal based on the campaign volume model to achieve a delivery goal.
11 . The system of claim 1 , wherein the initialization controller is configured to generate the bid price control signal based on the time-of-day pattern to achieve a delivery goal.
12 . The system of claim 4 , wherein the initialization controller is configured to generate the bid price control signal by recursively estimating a parameter of the campaign volume model, using the network average time-of-day pattern.
13 . The system of claim 1 , wherein the initialization controller is configured to automatically increase the bid allocation control signal to avoid campaign under-delivery or over-delivery.
14 . The system of claim 1 , wherein operation of the initialization controller is independent of the size of, or number of, campaigns operating in an advertising network.
15 . A computer-implemented method for controlling initialization of an online advertising campaign, the method comprising:
using a sensor to determine a current condition of the online advertising campaign;
storing in a memory, the condition obtained by the sensor, a set of campaign initialization controller instructions, a campaign volume model, and a network average time-of-day pattern;
predicting future campaign performance based on the condition obtained by the sensor, the campaign volume model, and the network average time-of-day pattern;
generating a bid allocation control signal; and
generating a bid price control signal based on the future campaign performance predicted by the estimator, according to the instructions stored in the memory;
wherein the bid allocation control signal and bid price control signal are used to adjust future performance of the online advertising campaign.
16 . The method of claim 15 , wherein the performance is defined by one of a marginal volume and a reference volume of the online advertising campaign.
17 . The method of claim 15 , wherein the future campaign performance is defined by a marginal volume of the campaign.
18 . The method of claim 17 , wherein the marginal volume of the campaign is estimated as a function of an effective allocation control signal and an effective price control signal.
19 . The method of claim 17 , wherein the marginal volume of the campaign is estimated as a function of a time-of-day pattern of the campaign.
20 . The method of claim 17 , wherein the marginal volume of the campaign is estimated as a function of an effective allocation control signal, an effective price control signal, and the network average time-of-day pattern.
21 . The method of claim 15 , wherein the bid allocation control signal is generated based on a predetermined ramp-up function.
22 . The method of claim 21 , wherein the predetermined ramp-up function is a linear function starting from a small number between 0 and 1.
23 . The method of claim 15 , wherein the bid price control signal is generated based on the estimated marginal volume.
24 . The method of claim 15 , wherein the bid price control signal is generated by recursively estimating a parameter of the network average time-of-day pattern.
25 . The method of claim 15 , wherein the bid price control signal is generated based on the campaign volume model to achieve a delivery goal.
26 . The method of claim 15 , wherein the bid price control signal is generated based on the time-of-day pattern to achieve a delivery goal.
27 . The method of claim 15 , wherein the bid price control signal is generated by recursively estimating a parameter of the campaign volume model, using the network average time-of-day pattern.
28 . The method of claim 15 , wherein the bid allocation control signal is automatically increased to avoid campaign under-delivery or over-delivery.
29 . The method of claim 15 , wherein generation of the bid allocation control signal and bid price control signal is independent of the size of, or number of, campaigns operating in an advertising network.
30 . A computer-implemented method for controlling re-initialization of an online advertising campaign, the method comprising:
using a sensor to determine a current condition of the online advertising campaign;
storing in a memory, the current condition obtained by the sensor, a set of campaign re-initialization controller instructions, a campaign volume model, and a network average time-of-day pattern;
determining whether the current condition exceeds a predetermined re-initialization threshold; and
initiating a re-initialization sequence if the current condition exceeds the predetermined re-initialization threshold, wherein the re-initialization sequence includes:
predicting future campaign performance based on the condition obtained by the sensor, the campaign volume model, and the network average time-of-day pattern;
generating a bid allocation control signal; and
generating a bid price control signal based on the future campaign performance predicted by the estimator, according to the instructions stored in the memory;
wherein the bid allocation control signal and bid price control signal are used to adjust future performance of the online advertising campaign.
31 . A computer-readable storage medium storing a computer program which, when executed by a computer, causes the computer to perform a method comprising the steps of:
using a sensor to determine a current condition of an online advertising campaign;
storing in a memory, the condition obtained by the sensor, a set of campaign initialization controller instructions, a campaign volume model, and a network average time-of-day pattern;
predicting future campaign performance based on the performance information obtained by the sensor, the campaign volume model, and the network average time-of-day pattern;
generating a bid allocation control signal; and
generating a bid price control signal based on the future campaign performance predicted by the estimator, according to the instructions stored in the memory;
wherein the bid allocation control signal and bid price control signal are used to adjust future performance of the online advertising campaign.
32 . A computer-implemented method for controlling initialization of an online advertising campaign, the method comprising:
using a sensor to determine a current condition of the online advertising campaign;
storing in a memory, the condition obtained by the sensor, a set of campaign initialization controller instructions, a campaign volume model, and a network average time-of-day pattern;
predicting future campaign performance based on the condition obtained by the sensor, the campaign volume model, and the network average time-of-day pattern;
generating a bid price control signal based on the future campaign performance predicted by the estimator, according to the instructions stored in the memory; and
generating a bid allocation control signal, wherein the bid allocation control signal is defined by u a (k), with:
u
a
(
k
)
=
min
(
u
a
(
k
0
)
+
u
a
,
max
(
k
0
)
-
u
a
(
k
0
)
T
ramp
-
up
(
k
-
k
0
)
,
u
a
,
max
(
k
0
)
)
for
k
≥
k
0
for each time k, where u a,max 0 defines a maximum allocation control signal, and T ramp-up defines a ramp-up window.