Using artificial intelligence models to identify a producer and consumer match

A system comprising:

• a memory;
• and
• one or more processing devices coupled to the memory, the one or more processing devices configured to perform operations comprising:
• identifying, from among a plurality of third-party service providers, a subset of third-party service providers to provide services to a first client organization, wherein one or more services provided by the subset of third-party service providers are to be facilitated via a software-as-a-service (SaaS) management platform;
• identifying, by the one or more processing devices, a set of weights for a ranking model configured to generate scores indicating a likelihood that respective services provided by a respective third-party service provider of the subset of third-party service providers are a match for the first client organization, wherein a value of each weight of the set of weights reflects an output value from a respective artificial intelligence (AI) model of a plurality of AI models;
• providing a first input to a first trained AI model, the first input comprising first consumer data comprising demographic data that identifies i) an age of each of a plurality of employees associated with the first client organization, and ii) a family status of each of the plurality of employees associated with the first client organization;
• generating, by the first trained AI model in response to the first input, a first output indicating, for each of the subset of third-party service providers, a likelihood that the plurality of employees will consume the one or more services provided by the subset of third-party service providers;
• responsive to generating the first output indicating the likelihood that the plurality of employees will consume the one or more services, adjusting a first value of a first weight of the set of weights using a second value that is derived from the first output of the first trained AI model to generate an adjusted set of weights, wherein adjusting the first value of the first weight to generate the adjusted set of weights is performed to improve an accuracy of the ranking model to estimate a likelihood that the subset of third-party service providers is able to provide the one or more services to the first client organization;
• providing a second input to the ranking model, the second input comprising second consumer data comprising consumer preference data indicating criteria for the one or more services provided by the subset of third-party service providers and identified by the first client organization;
• generating, by the ranking model, a set of scores for each of the subset of third-party service providers using the adjusted set of weights as parameters to the ranking model, each score of the set of scores indicating the likelihood that the respective services provided by the respective third-party service provider of the subset of third-party service providers are suitable for the first client organization;
• responsive to determining that a first score of the set of scores satisfies a threshold score, selecting, among the subset of third-party service providers, a first third-party service provider as suitable for the first client organization;
• and
• providing, to an agent device associated with the SaaS management platform, a notification indicating that the first third-party service provider is suitable for the first client organization.

A non-transitory computer-readable storage medium comprising instructions that, responsive to execution by one or more processing devices, cause the one or more processing devices to perform operations comprising:

• identifying, from among a plurality of third-party service providers, a subset of third-party service providers to provide services to a first client organization, wherein one or more services provided by the subset of third-party service providers are to be facilitated via a software-as-a-service (SaaS) management platform;
• identifying, by the one or more processing devices, a set of weights for a ranking model configured to generate scores indicating a likelihood that respective services provided by a respective third-party service provider of the subset of third-party service providers are a match for the first client organization, wherein a value of each weight of the set of weights reflects an output value from a respective artificial intelligence (AI) model of a plurality of AI models;
• providing a first input to a first trained AI model, the first input comprising first consumer data comprising demographic data that identifies i) an age of each of a plurality of employees associated with the first client organization, and ii) a family status of each of the plurality of employees associated with the first client organization;
• generating, by the first trained AI model in response to the first input, a first output indicating, for each of the subset of third-party service providers, a likelihood that the plurality of employees will consume the one or more services provided by the subset of third-party service providers;
• responsive to generating the first output indicating the likelihood that the plurality of employees will consume the one or more services, adjusting a first value of a first weight of the set of weights using a second value that is derived from the first output of the first trained AI model to generate an adjusted set of weights, wherein adjusting the first value of the first weight to generate the adjusted set of weights is performed to improve an accuracy of the ranking model to estimate a likelihood that the subset of third-party service providers is able to provide the one or more services to the first client organization;
• providing a second input to the ranking model, the second input comprising second consumer data comprising consumer preference data indicating criteria for the one or more services provided by the subset of third-party service providers and identified by the first client organization;
• generating, by the ranking model, a set of scores for each of the subset of third-party service providers using the adjusted set of weights as parameters to the ranking model, each score of the set of scores indicating the likelihood that the respective services provided by the respective third-party service provider of the subset of third-party service providers are suitable for the first client organization;
• responsive to determining that a first score of the set of scores satisfies a threshold score, selecting, among the subset of third-party service providers, a first third-party service provider as suitable for the first client organization;
• and
• providing, to an agent device associated with the SaaS management platform, a notification indicating that the first third-party service provider is suitable for the first client organization.