USING COMPETITIVE ALGORITHMS FOR THE PREDICTION AND PRICING OF ONLINE ADVERTISEMENT OPPORTUNITIES
In embodiments of the present invention, improved capabilities are described for applying a plurality of algorithms to predict performance of online advertising placements. The plurality of algorithms to predict performance may include advertiser data, historic event data, user data, real-time event data, contextual data, and third-party commercial data. Further, a computer program product, based on the methods and systems of the present invention, may include a set of instructions for tracking performance of the plurality of algorithms under a variety of market conditions. In embodiments, the computer program product may include a set of instructions for determining performance conditions for an algorithm, and/or include a set of instructions for tracking market conditions. Further, the computer program product may include a set of instructions for selecting an algorithm for predicting performance of advertising placements based on current market conditions.
1 . A computer implemented method, the method comprising the steps of:
applying a plurality of algorithms to predict performance of online advertising placements;
tracking performance of the plurality of algorithms under a variety of market conditions;
determining performance conditions for a type of algorithm;
tracking market conditions; and
selecting an algorithm for predicting performance of advertising placements based on current market conditions.
2 . The computer implemented method of claim 1 , wherein at least one of the plurality of algorithms to predict performance includes advertiser data.
3 . The computer implemented method of claim 1 , wherein at least one of the plurality of algorithms to predict performance includes historic event data.
4 . The computer implemented method of claim 1 , wherein at least one of the plurality of algorithms to predict performance includes user data.
5 . The computer implemented method of claim 1 , wherein at least one of the plurality of algorithms to predict performance includes real-time event data.
6 . The computer implemented method of claim 1 , wherein at least one of the plurality of algorithms to predict performance includes contextual data.
7 . The computer implemented method of claim 1 , wherein at least one of the plurality of algorithms to predict performance includes third-party commercial data.
8 . A computer program product embodied in a computer readable medium that, when executing on one or more computers, performs the steps of:
predicting, using a primary model, an economic valuation of each of a plurality of available web publishable advertisement placements based in part on past performance and prices of similar advertisement placements;
predicting, through a second model, an economic valuation of each of the plurality of web publishable advertisement placements; and
comparing the valuations produced by the primary model and the second model to determine a preference between the primary model and the second model.
9 . The computer program product of claim 8 , wherein the primary and second models are used as active models responding to purchase requests.
10 . The computer program product of claim 8 , wherein the purchase requested is a time limited purchase request.
11 . The computer program product of claim 8 , wherein the second model replaces the primary model as the active model responding to purchase requests.
12 . The computer program product of claim 8 , wherein the replacement is based on a prediction that the second model will perform better than the primary model under the current market conditions.
13 . The computer program product of claim 12 , wherein the prediction is based at least in part on machine learning.
14 . The computer program product of claim 12 , wherein the prediction is based at least in part on historical advertising performance data.
15 . The computer program product of claim 12 , wherein the prediction is based at least in part on historical event data.
16 . The computer program product of claim 12 , wherein the prediction is based at least in part on real-time event data.
17 . The computer program product of claim 8 , wherein comparing the valuations includes retrospectively comparing the extent to which the models reflect actual economic performance of advertisements.
18 . A computer program product embodied in a computer readable medium that, when executing on one or more computers, performs the steps of:
predicting, using a primary model, an economic valuation of each of a plurality of available mobile device advertisement placements based in part on past performance and prices of similar advertisement placements;
predicting, through a second model, an economic valuation of each of the plurality of mobile device advertisement placements; and
comparing the valuations produced by the primary model and the second model to determine a preference between the primary model and the second model.
19 . The computer program product of claim 18 , wherein the primary and second models are active models responding to purchase requests.
20 . The computer program product of claim 18 , wherein the second model replaces the primary model as the active model responding to purchase requests.
21 . The computer program product of claim 18 , wherein the replacement is based on a prediction that the second model will perform better than the primary model under the current market conditions.
22 . The computer program product of claim 18 , wherein comparing the valuations includes retrospectively comparing the extent to which the models reflect actual economic performance of advertisements.