Machine learning model for personalized user interfaces

1 . A method comprising:

presenting, using a processing unit, a user interface on a computing device, the user interface including:

a first portion configured to receive a selection of a set of subjective attributes associated with financial goals of a user; and

a second portion configured to receive a selection of a set of objective attributes the user, the set of objective attributes including a demographic attribute of the user;

inputting the set of objective attributes and the set of subjective attributes into a machine learning model;

in response to the inputting, receiving an output from the machine learning model, the output identifying a nearest cluster centroid of a plurality of cluster centroids based on the set of objective attributes and the set of subjective attributes as selected by the user via the first portion and the second portion of the user interface;

identifying, using the output and the processing unit, a cluster identifier, the cluster identifier determined by referencing a lookup table that maps each of the plurality of cluster centroids to a respective cluster identifier;

querying a datastore using the cluster identifier to receive a set of quantitative financial attributes of a plurality of users associated with the cluster identifier;

for a quantitative financial attribute of the quantitative financial attribute in the set of quantitative financial attributes:

calculating an average of the quantitative financial attribute for the plurality of users associated with the cluster identifier; and

comparing the average to a value of the quantitative financial attribute of the user;

based on the comparing, classifying the quantitative financial attribute as a positive attribute or negative attribute for the user; and

updating the user interface to present a comparison of the set of quantitative financial attributes of the plurality of users associated with the cluster identifier to the set of quantitative financial attributes for the user.

2 . The method of claim 1 , wherein inputting the set of objective attributes and the set of subjective attributes into the machine learning model includes:

encoding the set of objective attributes and the set of subjective attributes into a numerical vector.

3 . The method of claim 2 , wherein the machine learning model is a trained machine learning model using a k-means clustering algorithm with a plurality of cluster centroids.

4 . The method of claim 3 , the output of the machine learning model is based on a Euclidean distance calculation between the numerical vector and the plurality of cluster centroids.

5 . The method of claim 1 , wherein updating the user interface to present the comparison of the set of quantitative financial attributes of the plurality of users associated with the cluster identifier to the set of quantitative financial attributes for the user includes:

segmenting the user interface into a positive attribute portion and a negative attribute portion; and

presenting the quantitative financial attribute into the positive attribute portion or negative attribute portion based on the classifying.

6 . The method of claim 1 , wherein the first portion includes an input element for each of the set of subjective attributes and wherein upon receiving a selection of a respective input element, an outline style of the respective input element is updated.

7 . A non-transitory computer-readable medium comprising instructions, which when executed by a processing unit configure the processing unit to perform operations comprising:

presenting a user interface on a computing device, the user interface including:

a first portion configured to receive a selection of a set of subjective attributes associated with financial goals of a user; and

a second portion configured to receive a selection of a set of objective attributes the user, the set of objective attributes including a demographic attribute of the user;

inputting the set of objective attributes and the set of subjective attributes into a machine learning model;

in response to the inputting, receiving an output from the machine learning model, the output identifying a nearest cluster centroid of a plurality of cluster centroids based on the set of objective attributes and the set of subjective attributes as selected by the user via the first portion and the second portion of the user interface;

identifying, using the output, a cluster identifier, the cluster identifier determined by referencing a lookup table that maps each of the plurality of cluster centroids to a respective cluster identifier;

querying a datastore using the cluster identifier to receive a set of quantitative financial attributes of a plurality of users associated with the cluster identifier;

for a quantitative financial attribute of the quantitative financial attribute in the set of quantitative financial attributes:

calculating an average of the quantitative financial attribute for the plurality of users associated with the cluster identifier; and

comparing the average to a value of the quantitative financial attribute of the user:

based on the comparing, classifying the quantitative financial attribute as a positive attribute or negative attribute for the user; and

updating the user interface to present a comparison of the set of quantitative financial attributes of the plurality of users associated with the cluster identifier to the set of quantitative financial attributes for the user.

8 . The non-transitory computer-readable medium of claim 7 , wherein inputting the set of objective attributes and the set of subjective attributes into the machine learning model includes:

encoding the set of objective attributes and the set of subjective attributes into a numerical vector.

9 . The non-transitory computer-readable medium of claim 8 , wherein the machine learning model is a trained machine learning model using a k-means clustering algorithm with a plurality of cluster centroids.

10 . The non-transitory computer-readable medium of claim 9 , the output of the machine learning model is based on a Euclidean distance calculation between the numerical vector and the plurality of cluster centroids.

11 . The non-transitory computer-readable medium of claim 7 , wherein updating the user interface to present the comparison of the set of quantitative financial attributes of the plurality of users associated with the cluster identifier to the set of quantitative financial attributes for the user includes:

segmenting the user interface into a positive attribute portion and a negative attribute portion; and

presenting the quantitative financial attribute into the positive attribute portion or negative attribute portion based on the classifying.

12 . The non-transitory computer-readable medium of claim 7 , wherein the first portion includes an input element for each of the set of subjective attributes and wherein upon receiving a selection of a respective input element, an outline style of the respective input element is updated.

13 . A system comprising:

a processing unit; and

a storage device comprising instructions, which when executed by the processing unit, configure the processing unit to perform operations comprising:

presenting a user interface on a computing device, the user interface including:

a first portion configured to receive a selection of a set of subjective attributes associated with financial goals of a user; and

a second portion configured to receive a selection of a set of objective attributes the user, the set of objective attributes including a demographic attribute of the user;

inputting the set of objective attributes and the set of subjective attributes into a machine learning model;

in response to the inputting, receiving an output from the machine learning model, the output identifying a nearest cluster centroid of a plurality of cluster centroids based on the set of objective attributes and the set of subjective attributes as selected by the user via the first portion and the second portion of the user interface;

identifying, using the output, a cluster identifier, the cluster identifier determined by referencing a lookup table that maps each of the plurality of cluster centroids to a respective cluster identifier;

querying a datastore using the cluster identifier to receive a set of quantitative financial attributes of a plurality of users associated with the cluster identifier;

for a quantitative financial attribute of the quantitative financial attribute in the set of quantitative financial attributes:

calculating an average of the quantitative financial attribute for the plurality of users associated with the cluster identifier; and

comparing the average to a value of the quantitative financial attribute of the user;

based on the comparing, classifying the quantitative financial attribute as a positive attribute or negative attribute for the user; and

updating the user interface to present a comparison of the set of quantitative financial attributes of the plurality of users associated with the cluster identifier to the set of quantitative financial attributes for the user.

14 . The system of claim 13 , wherein inputting the set of objective attributes and the set of subjective attributes into the machine learning model includes:

encoding the set of objective attributes and the set of subjective attributes into a numerical vector.

15 . The system of claim 14 , wherein the machine learning model is a trained machine learning model using a k-means clustering algorithm with a plurality of cluster centroids.

16 . The system of claim 15 , the output of the machine learning model is based on a Euclidean distance calculation between the numerical vector and the plurality of cluster centroids.

17 . The system of claim 13 , wherein updating the user interface to present the comparison of the set of quantitative financial attributes of the plurality of users associated with the cluster identifier to the set of quantitative financial attributes for the user includes:

segmenting the user interface into a positive attribute portion and a negative attribute portion; and

presenting the quantitative financial attribute into the positive attribute portion or negative attribute portion based on the classifying.