Work income visualization and optimization platform
Provided are systems and methods that rely on machine learning to recommend employment opportunities. In one example, a method may include identifying, via execution of a first machine learning model, income data and spending data of a user, identifying, via execution of a second machine learning model, skill attributes of the user, determining, via execution of a third machine learning model, a recommended job for the user, where the determining comprises inputting the outputs from the first and second machine learning models into the third machine learning model, and displaying, via a user interface, a description of the recommended job.
1. A computing system comprising:
a hardware processor configured to:
receive a request to generate a job recommendation for a user, wherein the request comprises a payload of user data and an identifier of a type of recommendation to be made,
dynamically select a subset of machine learning models and a subset of input data sources for generating the type of recommendation from among a larger set of machine learning models and generate a communication path that interconnects the subset of input data sources with inputs of the subset of machine learning models and that also interconnects input and output of the subset of machine learning models in sequence with each other at a host platform to create a dynamically selected path between the subset of input data sources and the subset of machine learning models and within the larger set of machine learning models;
identify, via execution of the dynamically-selected subset of machine learning models, skill attributes of the user based on the payload of user data, wherein the hardware processor inputs a job description of the user from the payload of user data into the dynamically-selected subset of machine learning models which outputs the skill attributes;
determine, via execution of the dynamically-selected subset of machine learning models, a recommended job for the user, wherein the hardware processor inputs the skill attributes into the dynamically-selected subset of machine learning models which outputs an identifier of the recommended job;
dynamically select a template with predefined content embedded therein from among a plurality of templates based on the type of recommendation to be made; and
populate the selected template with a description of the recommended job and display, via a user interface, the populated template with the description of the recommended job.
2. The computing system of claim 1 , wherein the dynamically-selected subset of machine learning models comprises an ensemble that includes a natural language processing (NLP) algorithm and a decision tree algorithm.
3. The computing system of claim 1 , wherein the dynamically-selected subset of machine learning models comprises an ensemble that includes a natural language processing (NLP) algorithm and a clustering algorithm.
4. The computing system of claim 1 , wherein the dynamically-selected subset of machine learning models comprises a collaborative filtering model that receives vectors output from two or more machine learning models among the dynamically-selected subset of machine learning models, and which outputs a vector that identifies the recommended job.
5. The computing system of claim 1 , wherein the hardware processor is further configured to receive a schedule of work of the user, and determine, via execution of the dynamically-selected subset of machine learning models, a recommended change to the schedule of work of the user.
6. The computing system of claim 1 , wherein the hardware processor is further configured to insert the description of the recommended job into a blank space within the selected template.
7. The computing system of claim 6 , wherein the hardware processor is configured to output the filled-in template via a mobile application and transmit the filled-in template via an electronic message.
8. A method comprising:
receiving a request to generate a job recommendation for a user, wherein the request comprises a payload of user data and an identifier of a type of recommendation to be made;
dynamically selecting a subset of machine learning models and a subset of input data sources for generating the type of recommendation from among a larger set of machine learning models and generating a communication path that interconnects the subset of input data sources with inputs of the subset of machine learning models and that also interconnects inputs and outputs of the subset of machine learning models in sequence with each other at a host platform to create a dynamically selected path between the subset of input data sources and the subset of machine learning models and within the larger set of machine learning models;
identifying, via execution of the dynamically-selected subset of machine learning models, skill attributes of the user based on the payload of user data, wherein the identifying the skill attributes comprises inputting a job description of the user from the payload of user data into the dynamically-selected subset of machine learning models which outputs the skill attributes;
determining, via execution of the dynamically-selected subset of machine learning models, a recommended job for the user, wherein the determining comprises inputting the skill attributes into the dynamically-selected subset of machine learning models which outputs an identifier of the recommended job;
dynamically selecting a template with predefined content embedded therein from among a plurality of templates based on the type of recommendation to be made; and
populating the selected template with a description of the recommended job and displaying, via a user interface, the populated template with the description of the recommended job.
9. The method of claim 8 , wherein the dynamically-selected subset of machine learning models comprises an ensemble that includes a natural language processing (NLP) algorithm and a decision tree algorithm.
10. The method of claim 8 , wherein the dynamically-selected subset of machine learning models comprises an ensemble that includes a natural language processing (NLP) algorithm and a clustering algorithm.
11. The method of claim 8 , wherein the dynamically-selected subset of machine learning models comprises a collaborative filtering model that receives vectors output from two or more machine learning models among the dynamically-selected subset of machine learning models, and which outputs a vector that identifies the recommended job.
12. The method of claim 8 , further comprises receiving a schedule of work of the user, and determining, via execution of the dynamically-selected subset of machine learning models, a recommended change to the schedule of work of the user.
13. The method of claim 8 , wherein the populating comprises inserting the description of the recommended job into a blank space within the selected template description.
14. The method of claim 13 , wherein the displaying comprises at least one of outputting the filled-in template via a mobile application and transmitting the filled-in template via an electronic message.
15. A non-transitory computer-readable medium comprising instructions which when executed by a processor cause a computer to perform a method comprising:
receiving a request to generate a job recommendation for a user, wherein the request comprises a payload of user data and an identifier of a type of recommendation to be made;
dynamically selecting a subset of machine learning models and a subset of input data sources for generating the type of recommendation from among a larger set of machine learning models and generating a communication path that interconnects the subset of input data sources with inputs of the subset of machine learning models and that also interconnects inputs and outputs of the subset of machine learning models at a host platform to create a dynamically selected path between the subset of input data sources and the subset of machine learning models and within the larger set of machine learning models;
identifying, via execution of the dynamically-selected subset of machine learning models, skill attributes of the user based on the payload of user data, wherein the identifying the skill attributes comprises inputting a job description of the user from the payload of user data into the dynamically-selected subset of machine learning models which outputs the skill attributes;
determining, via execution of the dynamically-selected subset of machine learning models, a recommended job for the user, wherein the determining comprises inputting the skill attributes into the dynamically-selected subset of machine learning models which outputs an identifier of the recommended job;
dynamically selecting a template with predefined content embedded therein from among a plurality of templates based on the type of recommendation to be made; and
populating the selected template with a description of the recommended job and displaying, via a user interface, the populated template with the description of the recommended job.
16. The non-transitory computer-readable medium of claim 15 , wherein the dynamically-selected subset of machine learning models comprises an ensemble that includes a natural language processing (NLP) algorithm and a decision tree algorithm.
17. The non-transitory computer-readable medium of claim 15 , wherein the dynamically-selected subset of machine learning models comprises an ensemble that includes a natural language processing (NLP) algorithm and a clustering algorithm.
18. The non-transitory computer-readable medium of claim 15 , wherein the dynamically-selected subset of machine learning models comprises a collaborative filtering model that receives vectors output from two or more machine learning models among the dynamically-selected subset of machine learning models, and which outputs a vector that identifies the recommended job.
19. The non-transitory computer-readable medium of claim 15 , further comprises receiving a schedule of work of the user, and determining, via execution of the dynamically-selected subset of machine learning models, a recommended change to the schedule of work of the user.
20. The non-transitory computer-readable medium of claim 15 , wherein the populating comprises inserting the description of the recommended job into a blank space within the selected template, wherein the displaying comprises at least one of outputting the filled-in template via a mobile application and transmitting the filled-in template via an electronic message.