USING COGNITIVE COMPUTING TO PROVIDE A PERSONALIZED BANKING EXPERIENCE
Techniques are disclosed utilizing cognitive computing to improve banking experiences. A customer's account may be monitored to determine an amount of customer interactions, and that the amount of customer interactions for the customer through at least one self-service channel is less than the amount of customer interactions for the customer through at least one full-service channel. When the amount of customer interactions for the customer through the at least one self-service channel is less than the amount of customer interactions through the at least one full-service channel, the system may generate an electronic offer for the customer that includes a reward for an account associated with the customer if the customer increases usage of the at least one self-service channel and decreases usage of the at least one full-service channel for future customer interactions with the vendor.
1 . A computer-implemented method comprising:
training, via one or more processors, a machine learning model based on historical financial profiles associated with a plurality of users,
wherein the trained machine learning model is configured to identify spending patterns associated with the plurality of users;
receiving, via the one or more processors, financial data associated with a customer from one or more financial institutions;
generating, via the one or more processors, a financial profile of the customer based at least in part on the financial data,
wherein generating the financial profile comprises predicting, using the trained machine learning model and based on the spending patterns associated with the plurality of users, at least one spending pattern of the customer;
monitoring, via the one or more processors, amounts of customer interactions between the customer and a vendor in:
at least one full-service channel in which the customer and at least one human agent of the vendor interact during the customer interactions, and
at least one self-service channel in which the customer conducts the customer interactions with the vendor without interacting with the at least one human agent,
wherein the customer and the vendor have an ongoing contractual relationship associated with a customer account, and the customer interactions are associated with the customer account;
determining, via the one or more processors, that a first amount of customer interactions for the customer through the at least one self-service channel is less than a second amount of customer interactions for the customer through the at least one full-service channel;
determining, via the one or more processors, a custom reward associated with the customer, wherein:
determining the custom reward comprises determining an amount of reward points associated with the vendor or a retailer, based on the at least one spending pattern of the customer predicted by the trained machine learning model,
the customer is eligible to receive the custom reward based on the customer increasing usage of the at least one self-service channel and decreasing usage of the at least one full-service channel for future customer interactions with the vendor, and
the custom reward is determined in response to determining that the first amount of customer interactions is less than the second amount of customer interactions; and
transmitting, via the one or more processors, an electronic offer to a mobile device of the customer, the electronic offer indicating the custom reward.
2 . The computer-implemented method of claim 1 , further comprising:
depositing, via the one or more processors, the custom reward into an account associated with the customer.
3 . (canceled)
4 . The computer-implemented method of claim 1 , wherein the financial profile further indicates at least one of: a plurality of vendors at which the customer shops, an education level for the customer, identities of offerings the customer has purchased, or types of the offerings the customer has purchased.
5 . The computer-implemented method of claim 1 , wherein at least one customer interaction conducted via the at least one self-service channel includes the customer enrolling into and receiving e-statements.
6 . The computer-implemented method of claim 1 , wherein at least one customer interaction conducted via the at least one self-service channel includes the customer enrolling into an automatic payment program.
7 . The computer-implemented method of claim 1 , wherein at least one customer interaction conducted via the at least one self-service channel includes the customer visiting a website associated with the vendor.
8 . A computer-implemented method comprising:
training, via one or more processors, a machine learning model based on historical financial profiles associated with a plurality of users,
wherein the trained machine learning model is configured to identify spending patterns associated with the plurality of users;
receiving, via the one or more processors, financial data associated with a customer from one or more financial institutions;
generating, via the one or more processors a financial profile of the customer based at least in part on the financial data,
wherein generating the financial profile comprises predicting, using the trained machine learning model and based on the spending patterns associated with the plurality of users, at least one spending pattern of the customer;
monitoring, via the one or more processors, amounts of customer interactions the customer has with a vendor in each of multiple communication channels including:
one or more full-service channels in which the customer and at least one human agent of the vendor interact during the customer interactions; and
one or more self-service channels in which the customer conducts the customer interactions with the vendor without interacting with the at least one human agent,
wherein the customer and the vendor have an ongoing contractual relationship associated with a customer account, and the customer interactions are associated with the customer account;
determining, via the one or more processors, that a majority of the customer interactions between the customer and the vendor are via the one or more self-service channels relative to the one or more full-service channels;
determining, via the one or more processors, a customized amount of reward points, associated with the vendor or a retailer, to award the customer based upon the majority of the customer interactions being via the one or more self-service channels, wherein the customized amount of reward points is determined:
based on the at least one spending pattern of the customer predicted by the trained machine learning model, and
in response to determining that the majority of the customer interactions are via the one or more self-service channels; and
depositing, via the one or more processors, the customized amount of reward points into an account associated with the customer.
9 . The computer-implemented method of claim 8 , wherein the financial profile further indicates at least one of: a plurality of vendors at which the customer shops, an education level for the customer, identities of offerings the customer has purchased, or types of the offerings the customer has purchased.
10 . The computer-implemented method of claim 8 , further comprising:
transmitting, via the one or more processors, an indication of the customized amount of reward points to a mobile device associated with the customer.
11 . The computer-implemented method of claim 8 , wherein at least one customer interaction conducted via the one or more self-service channels includes the customer enrolling into and receiving e-statements.
12 . The computer-implemented method of claim 8 , wherein at least one customer interaction conducted via the one or more self-service channels includes the customer enrolling into an automatic payment program.
13 . The computer-implemented method of claim 8 , wherein at least one customer interaction conducted via the one or more self-service channels includes the customer visiting a website associated with the vendor.
14 . A computer system comprising at least one of one or more local or remote processors, sensors, servers, or transceivers configured to:
train a machine learning model based on historical financial profiles associated with a plurality of users,
wherein the trained machine learning model is configured to identify spending patterns associated with the plurality of users;
receiving financial data associated with a customer from one or more financial institutions;
generate a financial profile of the customer based at least in part on the financial data,
wherein generating the financial profile comprises predicting, using the trained machine learning model and based on the spending patterns associated with the plurality of users, at least one spending pattern of the customer;
monitor amounts of customer interactions the customer has with a vendor in each of multiple communication channels comprising:
at least one full-service channel in which the customer and at least one human agent of the vendor interact during the customer interactions; and
at least one self-service channel in which the customer conducts the customer interactions with the vendor without interacting with the at least one human agent,
wherein the customer and the vendor have an ongoing contractual relationship associated with a customer account, and the customer interactions are associated with the customer account;
determine that a first amount of customer interactions for the customer through the at least one self-service channel is less than a second amount of customer interactions for the customer through the at least one full-service channel;
determine a custom reward associated with the customer, wherein:
determining the custom reward comprises determining an amount of reward points associated with the vendor or a retailer, based on the at least one spending pattern of the customer predicted by the trained machine learning model,
the customer is eligible to receive the custom reward based on the customer increasing usage of the at least one self-service channel and decreasing usage of the at least one full-service channel for future customer interactions with the vendor, and
the custom reward is determined in response to determining that the first amount of customer interactions is less than the second amount of customer interactions; and
transmit an electronic offer to a mobile device of the customer, the electronic offer indicating the custom reward.
15 . The computer system of claim 14 , wherein the computer system is further configured to:
deposit the amount of reward points into an account associated with the customer.
16 . (canceled)
17 . The computer system of claim 14 , wherein the financial profile further indicates at least one of: a plurality of vendors at which the customer shops, one or more preferred vendors of the plurality of vendors, an education level of the customer, or products the customer has purchased.
18 . The computer system of claim 14 , wherein at least one customer interaction conducted via the at least one self-service channel includes the customer enrolling into and receiving e-statements.
19 . The computer system of claim 14 , wherein at least one customer interaction conducted via the at least one self-service channel includes the customer enrolling into an automatic payment program.
20 . The computer system of claim 14 , wherein at least one customer interaction conducted via the at least one self-service channel includes the customer visiting a website associated with the vendor.
21 . (canceled)
22 . The computer-implemented method of claim 1 , further comprising:
receiving, via the one or more processors, one or more additional types of data associated with the customer, including at least one of:
web browsing data,
social media usage data,
retailer-reported information,
demographic data,
an income level, or
assets of the customer; and
generating, via the one or more processors, the financial profile of the customer based at least in part on the one or more additional types of data.
23 . The computer-implemented method of claim 22 , wherein the at least one spending pattern is predicted, using the trained machine learning model, based at least in part on the one or more additional types of data.