Abstract: Methods and systems disclosed herein describe an experimentation platform that identifies one or more proxy metrics for testing a configuration and/or new design of a product. The experimentation platform may receive an input identifying one or more configurations, components, and/or products to test and/or optimize. The experimentation platform may identify one or more performance metrics used to test and/or optimize the one or more configurations, components, and/or products. Based on the one or more identified performance metrics, the experimentation platform may identify one or more proxy metrics to represent the one or more performance metrics. The one or more identified proxy metrics may be one or more engagement metrics or a combination of engagement metrics. The experimentation platform may then use the one or more proxy metrics to analyze the one or more configurations, components, and/or products and recommend a configuration, component, and/or product for deployment.

Abstract: Methods and systems disclosed herein describe an experimentation platform that identifies one or more proxy metrics for testing a configuration and/or new design of a product. The experimentation platform may receive an input identifying one or more configurations, components, and/or products to test and/or optimize. The experimentation platform may identify one or more performance metrics used to test and/or optimize the one or more configurations, components, and/or products. Based on the one or more identified performance metrics, the experimentation platform may identify one or more proxy metrics to represent the one or more performance metrics. The one or more identified proxy metrics may be one or more engagement metrics or a combination of engagement metrics. The experimentation platform may then use the one or more proxy metrics to analyze the one or more configurations, components, and/or products and recommend a configuration, component, and/or product for deployment.

Abstract: Methods and systems are for using machine learning models to locate information in an organizational graph. A search system may use techniques described herein to determine relevant data (e.g., organizational knowledge) to retrieve from a knowledge graph for input to a machine learning model. The search system may retrieve more relevant data from the knowledge graph through the use of time data that may enable the search system to avoid outdated information. The search system may also limit the data that may be used in determining an answer to a query. By doing so, the search system may be able to answer queries more efficiently (e.g., using less computing resources, less processing power, etc.).

Abstract: A topic tracking platform is disclosed that includes a machine-learning model that may be trained to expose topics in a corpus in response to a training table. Because topics are exposed, rather than searched for using existing taxonomies, the sensitivity of a topic tracking platform may be increased, and emerging topic trends may be more quickly flagged. Exposed topics may be automatically labelled, increasing the specificity of the topic tracking platform by overcoming the potential for topic labelling inconsistencies currently experienced in the art. Documents may be scored for each topic using information provided at a token granularity, and the contribution that each token of each document contributes to the topic may be visually represented. In some aspects, mechanisms are provided for reviewing topics of the corpus at varying granularities, including at a topic level, document level or token level granularity.

Abstract: A topic tracking platform is disclosed that includes a machine-learning model that may be trained to expose topics in a corpus in response to a training table. Because topics are exposed, rather than searched for using existing taxonomies, the sensitivity of a topic tracking platform may be increased, and emerging topic trends may be more quickly flagged. Exposed topics may be automatically labelled, increasing the specificity of the topic tracking platform by overcoming the potential for topic labelling inconsistencies currently experienced in the art. Documents may be scored for each topic using information provided at a token granularity, and the contribution that each token of each document contributes to the topic may be visually represented. In some aspects, mechanisms are provided for reviewing topics of the corpus at varying granularities, including at a topic level, document level or token level granularity.

Abstract: A system and method for digitally testing a webpage are disclosed herein. The system receives, via one or more application programming interface (API) endpoints, user data. The user data includes one or more indications of one or more users interacting with the one or more variants of the webpage. The system inputs the one or more indications into a machine learning model. The machine learning model includes a Bayesian multi-arm bandit algorithm. The system generates, using the machine learning model, one or more results comprising causal performance estimates and a set of decision rules to adaptively design further testing experiments based on the causal performance estimates. The system generates a portal accessible to one or more end users. The portal includes the one or more results.

Abstract: A system for recommending personalized rewards based on customer profiles and customer preferences includes one or more processors configured to access customer parameters associated with the first customer and customer parameters associated with a plurality of second customers from a database. The values of customer parameters of the first customer are compared with the values of the customer parameters of the plurality of second customers to identify of the plurality of second customers having customer parameter values that correspond to the customer parameter values associated with the first customer. A list of reward purchase categories is determined based on analyzing customer profiles associated with the identified plurality of second customers. Personalized rewards associated with the selected one or more reward categories are transmitted to the user device associated with the first customer, the personalized rewards to accrue based on consumer purchase transactions by the first customer.

Abstract: A topic tracking platform is disclosed that includes a machine-learning model that may be trained to expose topics in a corpus in response to a training table. Because topics are exposed, rather than searched for using existing taxonomies, the sensitivity of a topic tracking platform may be increased, and emerging topic trends may be more quickly flagged. Exposed topics may be automatically labelled, increasing the specificity of the topic tracking platform by overcoming the potential for topic labelling inconsistencies currently experienced in the art. Documents may be scored for each topic using information provided at a token granularity, and the contribution that each token of each document contributes to the topic may be visually represented. In some aspects, mechanisms are provided for reviewing topics of the corpus at varying granularities, including at a topic level, document level or token level granularity.

Abstract: A system for recommending personalized rewards based on customer profiles and customer preferences includes one or more processors configured to access customer parameters associated with the first customer and customer parameters associated with a plurality of second customers from a database. The values of customer parameters of the first customer are compared with the values of the customer parameters of the plurality of second customers to identify of the plurality of second customers having customer parameter values that correspond to the customer parameter values associated with the first customer. A list of reward purchase categories is determined based on analyzing customer profiles associated with the identified plurality of second customers. Personalized rewards associated with the selected one or more reward categories are transmitted to the user device associated with the first customer, the personalized rewards to accrue based on consumer purchase transactions by the first customer.