Smart copy optimization in customer acquisition and customer management platforms
In some examples, special-purpose machines are provided that facilitate smart copy optimization in a network service or publication system, including software-configured computerized variants of such special-purpose machines and improvements to such variants, and to the technologies by which such special-purpose machines become improved compared to other special-purpose machines that facilitate adding the new features. Such technologies can include special artificial-intelligence (AI), machine-learning (ML), and natural-language-processing (NLP) techniques.
1. A copy optimization tool comprising:
a memory;
a neural network including:
a plurality of input nodes, wherein each input node includes a memory location for storing an input value;
a plurality of hidden nodes, wherein each hidden node is connected to each input node and includes computational instructions, implemented in machine code, for computing output values, respectively; and
a plurality of output nodes, wherein each of the output nodes includes a memory location for storing a respective output signal indicative of an output value or feature for a trained model;
one or more computer processors, configured to execute instructions programmed using a set of machine code, wherein the instructions, when executed by the one or more computer processors, cause the one or more computer processors to perform operations comprising:
extracting a text input from a candidate copy content;
using the trained model, accessing comparable historical copy content to generate historical comparison content;
profiling a historical performance of the historical comparison content in a context of CRM marketing, based on one or more of the following metrics:
a variance in the historical performance of the comparison content;
a frequency of use of a historical subject line or comparable copy content; and
a recency of use of a historical subject line or comparable copy content;
matching the text input from the candidate copy content with the comparable copy content based on one or more matching algorithms;
identifying historical matches of comparable copy content matching the text input of the candidate copy content;
ranking the historical matches based on one or more of the following rules:
a quality of a match;
a volume of historical subject lines or comparable copy content;
a word count; and
a recency or frequency of a historical subject line or comparable copy content; and
applying a weighting factor to the historical matches based on a past seasonality of historical matches.
2. The copy optimization tool of claim 1 , wherein the operations further comprise:
identifying a plurality of drivers in the extracted text using the trained model based on the profiled historical performance.
3. The copy optimization tool of claim 2 , wherein the plurality of drivers include positive and negative drivers.
4. The copy optimization tool of claim 3 , wherein the operations further comprise changing at least one of the negative drivers to a positive driver and transmitting a modified candidate copy content having the changed driver.
5. A method for copy optimization, comprising:
extracting, with a processor, a text input from a candidate copy content;
using a trained model of a neural network, accessing, with the processor, comparable historical copy content to generate historical comparison content; the neural network including
a plurality of input nodes, wherein each input node includes a memory location for storing an input value;
a plurality of hidden nodes, wherein each hidden node is connected to each input node and includes computational instructions, implemented in machine code, for computing output values, respectively; and
a plurality of output nodes, wherein each of the output nodes includes a memory location for storing a respective output signal indicative of an output value or feature for a trained model;
profiling, with the processor, a historical performance of the historical comparison content in a context of CRM marketing, based on one or more of the following metrics:
a variance in the historical performance of the comparison content;
a frequency of use of a historical subject line or comparable copy content; and
a recency of use of a historical subject line or comparable copy content;
matching, with the processor the text input from the candidate copy content with the comparable copy content based on one or more matching algorithms;
identifying, with the processor, historical matches of comparable copy content matching the text input of the candidate copy content; and
ranking, with the processor, the historical matches based on one or more of the following rules:
a quality of a match;
a volume of historical subject lines or comparable copy content;
a word count; and
a recency or frequency of a historical subject line or comparable copy content; and
applying, with the processor, a weighting factor to the historical matches based on a past seasonality of historical matches.
6. The method of claim 5 , further comprising:
identifying, with the processor, a plurality of drivers in the extracted text using the trained model based on the profiled historical performance.
7. The method of claim 6 , wherein the plurality of drivers include positive and negative drivers.
8. The method of claim 7 , further comprising changing, with the processor, at least one of the negative drivers to a positive driver and transmitting a modified candidate copy content having the changed driver.
9. A non-transitory computer-readable medium storing instructions that, when executed by one or more computer processors of a computer, cause the computer to perform operations comprising:
extracting a text input from a candidate copy content;
using a trained model of a neural network, accessing comparable historical copy content generate historical comparison content; the neural network including
a plurality of input nodes, wherein each input node includes a memory location for storing an input value;
a plurality of hidden nodes, wherein each hidden node is connected to each input node and includes computational instructions, implemented in machine code, for computing output values, respectively; and
a plurality of output nodes, wherein each of the output nodes includes a memory location for storing a respective output signal indicative of an output value or feature for a trained model;
profiling a historical performance of the historical comparison content in a context of CRM marketing, based on one or more of the following metrics:
a variance in the historical performance of the comparison content;
a frequency of use of a historical subject line or comparable copy content; and
a recency of use of a historical subject line or comparable copy content;
matching the text input from the candidate copy content with the comparable copy content based on one or more matching algorithms;
identifying historical matches of comparable copy content matching the text input of the candidate copy content; and
ranking the historical matches based on one or more of the following rules:
a quality of a match;
a volume of historical subject lines or comparable copy content;
a word count; and
a recency or frequency of a historical subject line or comparable copy content; and
applying a weighting factor to the historical matches based on a past seasonality of historical matches.
10. The computer-readable medium of claim 9 , wherein the operations further comprise:
identifying a plurality of drivers in the extracted text using the trained model based on the profiled historical performance.
11. The computer-readable medium of claim 10 , wherein the plurality of drivers include positive and negative drivers.
12. The computer-readable medium of claim 11 , wherein the operations further comprise changing at least one of the negative drivers to a positive driver and transmitting a modified candidate copy content having the changed driver.