Method and apparatus for predicting customer behavior
A method and apparatus for predicting customer behavior is disclosed. The method comprises organizing a transcribed, diarized text of a conversation in a call, into a predefined number of sets, determining features corresponding to a sentiment score, a percentage and/or count of positive words, and a percentage and/or count of negative words for each of the a predefined number of sets, determining word count features corresponding to the word count for each of the a predefined number of sets, determining features corresponding to a call talk time, a call hold time and a call hold percentage based on the transcribed text. Based on all the determined features, the method determines whether the customer is satisfied or not, the customer activity based on an activity profile of the customer, and whether the customer used escalation terms based on the transcribed text. Based on the customer satisfaction, customer activity, and the customer use of escalation terms, the method determines a probability of a customer action.
1. A computer-implemented method for predicting customer behavior, the method comprising:
organizing a transcribed, diarized text of a conversation in a call, into a predefined number of sets;
determining features corresponding to a sentiment score, a percentage and/or count of positive words, and a percentage and/or count of negative words for each of the predefined number of sets;
determining word count features corresponding to the word count for each of the predefined number of sets;
determining features corresponding to a call talk time, a call hold time and a call hold percentage based on the transcribed text for the entire call;
determining customer satisfaction based on all the determined features;
determining customer activity based on a customer activity profile of the customer;
determining whether the customer used escalation terms in the call, based on the transcribed text; and
determining a probability of a customer action based on the customer satisfaction, the customer activity and the customer use of escalation terms.
2. The method of claim 1 , wherein the predefined number of sets is 12, and corresponds to (1) entire call, (2) entire agent conversation, (3) entire customer conversation, (4) call beginning, (5) call middle, (6) call end, (7) beginning of agent conversation, (8) middle of agent conversation, (9) end of agent conversation, (10) beginning of customer conversation, (11) middle of customer conversation, and (12) end of customer conversation.
3. The method of claim 1 , determining the customer satisfaction comprises using an Artificial Intelligence/Machine Learning (AI/ML) module trained to determine whether the customer is satisfied or not, based on an input of all the determined features.
4. The method of claim 1 , wherein the customer activity profile customer activity profile includes information such as activity levels, demographic information, or type of websites visited.
5. The method of claim 1 , further comprising determining, based on the probability exceeding a predefined threshold value, that the customer is likely to post a negative review on the social media.
6. An apparatus for predicting customer behavior, the apparatus comprising:
at least one processor;
a memory communicably coupled to the at least one processor, the memory comprising computer-executable instructions, which when executed by the at least one processor, perform a method comprising:
organizing a transcribed, diarized text of a conversation in a call, into a predefined number of sets,
determining features corresponding to a sentiment score, a percentage and/or count of positive words, and a percentage and/or count of negative words for each of the predefined number of sets,
determining word count features corresponding to the word count for each of the predefined number of sets,
determining features corresponding to a call talk time, a call hold time and a call hold percentage based on the transcribed text for the entire call,
determining customer satisfaction based on all the determined features,
determining customer activity based on a customer activity profile of the customer,
determining whether the customer used escalation terms in the call, based on the transcribed text, and
determining a probability of a customer action based on the customer satisfaction, the customer activity and the customer use of escalation terms.
7. The apparatus of claim 6 , wherein the predefined number of sets is 12, and corresponds to (1) entire call, (2) entire agent conversation, (3) entire customer conversation, (4) call beginning, (5) call middle, (6) call end, (7) beginning of agent conversation, (8) middle of agent conversation, (9) end of agent conversation, (10) beginning of customer conversation, (11) middle of customer conversation, and (12) end of customer conversation.
8. The apparatus of claim 6 , determining the customer satisfaction comprises using an Artificial Intelligence/Machine Learning (AI/ML) module trained to determine whether the customer is satisfied or not, based on an input of all the determined features.
9. The apparatus of claim 6 , wherein the customer activity profile customer activity profile includes information such as activity levels, demographic information, or type of websites visited.
10. The apparatus of claim 6 , further comprising determining, based on the probability exceeding a predefined threshold value, that the customer is likely to post a negative review on the social media.