Evaluating coincident interaction indicators
Disclosed are embodiments for determining the impact of one or more latent factors on user interaction metrics based at least in part on an impact model. The embodiments identify a value for a user interaction metric, the user interaction metric measuring interaction with content and identify an impact for a latent factor on the user interaction metric, the impact determined based at least in part on a model providing a relationship between the user interaction metric and the latent factor. Additionally, embodiments may involve adjusting an attribute of the electronically provided content based at least in part on the impact of the latent factor on the user interaction metric.
1. In an environment in which electronic advertisements are provided to consumers via an electronic network, a method for modifying an electronic advertisement based on a latent-factor-adjusted measure of advertisement effectiveness, the method comprising performing, by a processing device, operations comprising:
providing an electronic advertisement to users via the electronic network;
tracking user interactions with the electronic advertisement to identify a measurement value for a user interaction metric to use as a measure of advertisement effectiveness, the user interaction metric measuring user interaction with the electronic advertisement on computing devices of the users, wherein the user interaction metric comprises a number of clicks, number of mouse overs, number of page views, number of mouse gestures, amount of time elapsed before a mouse gesture, amount of time spent on a web page including the electronic advertisement, or frequency of accesses to the electronic advertisement;
estimating, by an applied impact model, an impact value, wherein:
the impact value correlates a latent factor to the measurement value, wherein the latent factor is an aspect of the users or economy that is not directly observable, wherein the latent factor is one of an economic factor, brand equity factor, brand loyalty factor, or a brand goodwill factor,
the impact value is determined based at least in part on the applied impact model providing a relationship between the user interaction metric and the latent factor,
wherein the relationship identifies how the user interaction metric changes based on change in the latent factor, wherein the relationship changes over time, and wherein the impact value quantifies a change in the measurement value resulting from the change in the latent factor;
determining a reduced measurement value, wherein the reduced measurement value is the measurement value subtracted by the change quantified by the impact value, wherein an improved measure of advertisement effectiveness is based on the reduced measurement value;
modifying the electronic advertisement based at least in part on the reduced measurement value; and
providing the modified electronic advertisement to additional users via the electronic network.
2. The method of claim 1 , wherein the applied impact model is a dynamic impact model.
3. The method of claim 1 , wherein the latent factor impacts the significance of the measurement value as a measure of advertisement effectiveness.
4. The method of claim 1 , wherein the reduced measurement value is determined based on the estimated impact value correlating brand loyalty to the measurement value.
5. A system comprising:
a processor for executing instructions stored in computer-readable medium on one or more devices,
the instructions comprising one or more modules configured to perform the steps comprising:
providing an electronic advertisement to users via the electronic network;
tracking user interactions with the electronic advertisement to identify a measurement value for a user interaction metric to use as a measure of advertisement effectiveness, the user interaction metric measuring user interaction with the electronic advertisement on computing devices of the users, wherein the user interaction metric comprises a number of clicks, number of mouse overs, number of page views, number of mouse gestures, amount of time elapsed before a mouse gesture, amount of time spent on a web page including the electronic advertisement, or frequency of accesses to the web page;
estimating, by an applied impact model, an impact value, wherein:
the impact value correlates a latent factor to the measurement value, wherein the latent factor is an aspect of the users or economy that is not directly observable, wherein the latent factor is one of an economic factor, brand equity factor, brand loyalty factor, or a brand goodwill factor,
the impact value is determined based at least in part on the applied impact model providing a relationship between the user interaction metric and the latent factor, wherein the relationship identifies how the user interaction metric changes based on change in the latent factor, wherein the relationship changes over time, and wherein the impact value quantifies a change in the measurement value resulting from the change in the latent factor;
determining a reduced measurement value, wherein the reduced measurement value is the measurement value subtracted by the change quantified by the impact value, wherein an improved measure of advertisement effectiveness is based on the reduced measurement value;
modifying the electronic advertisement based at least in part on the reduced measurement value; and
providing the modified electronic advertisement to additional users via the electronic network.