System and method for improving image-based advertisement success

1. A method using a computer system for improving online advertising success for an image-based advertisement, comprising:

receiving, at the computer system, an advertisement transmitted from an advertisement-serving system;

identifying, by the computer system, at least one visual characteristic of the advertisement by analyzing the advertisement using one or more machine learning algorithms to identify at least one of an object, a color, or a background of the advertisement;

classifying, by the computer system, the advertisement into at least one advertisement category based on the identified at least one visual characteristic;

analyzing, by the computer system using a deep learning neural network, a plurality of advertisements stored in a storage that is accessible to the computer system and which belong to the at least one advertising category to identify at least one visual characteristic associated with successful online advertisements, wherein an online advertisement is considered to be successful when the online advertisement meets a prescribed performance criteria, wherein the prescribed performance criteria comprises at least one of a click-through-rate, an impression count, or a number of clicks;

generating, by the computer system, at least one recommendation for improving the image-based advertisement based on the identified at least one successful advertisement visual characteristic;

causing, by the computer system, the advertisement-serving system to serve the image-based advertisement when it is determined that the image-based advertisement includes the at least one successful advertisement visual characteristic; and

causing, by the computer system, the advertisement-serving system to request a different image-based advertisement when it is determined that the image-based advertisement does not include the at least one successful advertisement visual characteristic.

2. The method of claim 1 , wherein the at least one visual characteristic includes at least one object, wherein the classification is based on a prominence of the at least one object.

3. The method of claim 2 , wherein the analysis further comprises:

determining, for each object, whether the object is common to at least two advertising categories; and

identifying each object that is common to at least two advertising categories as a stop-object, wherein the classification is not based on the stop-objects.

4. The method of claim 1 , wherein the at least one recommendation includes any of: adding a visual characteristic, changing a visual characteristic, replacing a visual characteristic, and a size of a visual characteristic to be inserted.

5. The method of claim 1 , further comprising:

prompting a user to accept or reject the at least one recommendation.

6. The method of claim 5 , further comprising:

receiving, from the user, a modification to the at least one recommendation; and

modifying the at least one recommendation based on the modification.

7. The method of claim 1 , further comprising:

retrieving the image-based advertisement from a database.

8. A method comprising:

receiving, at a computer system, an advertisement;

identifying, by the computer system, at least one visual characteristic of the advertisement by analyzing the advertisement using one or more machine learning algorithms to identify at least one of an object, a color, or a background of the advertisement;

classifying, by the computer system, the advertisement into at least one advertisement category based on the identified at least one visual characteristic;

analyzing, by the computer system using a deep learning neural network, a plurality of advertisements stored in a storage that is accessible to the computer system and which belong to the at least one advertising category to identify at least one visual characteristic associated with successful online advertisements, wherein an online advertisement is considered to be successful when the online advertisement meets a prescribed performance criteria, wherein the prescribed performance criteria comprises at least one of a click-through-rate, an impression count, or a number of clicks;

generating, by the computer system, at least one recommendation for improving the image-based advertisement based on the identified at least one successful advertisement visual characteristic;

modifying the image-based advertisement so as to implement the at least one recommendation; and

transmitting the modified image-based advertisement over a computer network for display on a web page on a user device.

9. A computer system for improving online advertising success for an image-based advertisement, comprising:

a processing unit; and

a memory, the memory containing instructions that, when executed by the processing unit, configure the system to:

receive, at the computer system, an advertisement transmitted from an advertisement-serving system;

identify, by the computer system, at least one visual characteristic of the advertisement by analyzing the advertisement using one or more machine learning algorithms to identify at least one of an object, a color, or a background of the advertisement;

classify, by the computer system, the advertisement into at least one advertisement category based on the identified at least one visual characteristic;

analyze, by the computer system using a deep learning neural network, a plurality of advertisements stored in a storage that is accessible to the computer system and which belong to the at least one advertising category to identify at least one visual characteristic associated with successful online advertisements, wherein an online advertisement is considered to be successful when the online advertisement meets a prescribed performance criteria, wherein the prescribed performance criteria comprises at least one of a click-through-rate, an impression count, or a number of clicks;

generate, by the computer system, at least one recommendation for improving the image-based advertisement based on the identified at least one successful advertisement visual characteristic;

cause, by the computer system, the advertisement-serving system to serve the image-based advertisement when it is determined that the image-based advertisement includes the at least one successful advertisement visual characteristic; and

cause, by the computer system, the advertisement-serving system to request a different image-based advertisement when it is determined that the image-based advertisement does not include the at least one successful advertisement visual characteristic.

10. The computer system of claim 9 , wherein the at least one visual characteristic includes at least one object, wherein the classification is based on a prominence of the at least one object.

11. The computer system of claim 9 , wherein the system is further configured to:

determine, for each object, whether the object is common to at least two types of advertisements; and

identify each object that is common to at least two types of advertisements as a stop-object, wherein the classification is not based on the stop-objects.

12. The computer system of claim 9 , wherein the at least one recommendation includes any of: adding a visual characteristic, changing a visual characteristic, replacing a visual characteristic, and a size of a visual characteristic to be inserted.

13. The computer system of claim 9 , wherein the system is further configured to:

prompt a user to accept or reject the at least one recommendation.

14. The computer system of claim 13 , wherein the system is further configured to:

receive, from the user, a modification to the at least one recommendation; and

modify the at least one recommendation based on the modification.

15. The computer system of claim 9 , wherein the system is further configured to:

retrieve the image-based advertisement from a database.

16. The method of claim 1 , further comprising:

selecting, based on the at least one recommendation, an advertisement from a predefined set of advertisements.