Abstract: A largely automated method of categorizing spend data is provided that does not require a prior in-depth knowledge of an organization's transactional data. Natural language processing is applied to text data from transactional data to generate a consolidated cleaned data set (CDS) containing information for categorization. Logs for transactions are clustered based on similarity, forming the minimal data set (MDS). An automated algorithm selects a subset of high-value clusters that are categorized by requesting users to manually categorize one or more representative logs from each cluster of the subset. A model is then trained using the subset of manually categorized clusters and used to predict spend categories for the remaining logs with high accuracy. The AI engine automatically analyzes the predictions based on client context and either auto-tunes the machine learning model or identifies a new subset of clusters to be manually categorized. This loop may continue until 95%-100% of the spend is categorized.

Abstract: A graph may be initially seeded with nodes representing applications and tags describing subjective qualities of the applications. A system generates tags for new applications using a supervised machine learning model. The system extracts signals from a newly detected application. The system inputs the signals into a machine learning model, and receives, as output from the model, tags that correspond to the new application and levels of confidence for each tag. The system updates the graph to include one or more nodes corresponding to the new application, with the tags linked to the one or more nodes with an edge that has a weight corresponding to the level of confidence. The system receives a query corresponding to the tag and provides a response to the query based on the one or more nodes corresponding to the new application.

Abstract: A graph includes nodes representing applications and tags describing subjective qualities of the applications. The system generates tags for applications using a large language model (LLM). The system receives the name of an application and generates a prompt for an LLM based on the name. The prompt includes a request for one or more tags associated with the application. The system provides the prompt to the LLM for execution and receives, as output from the LLM, candidate tags. The system inputs the candidate tags into a classifier trained to classify candidate tags into known tags, tags that already exist in a graph. The system receives, as output from the classifier, known tags. The system updates the graph to include a node corresponding to the application, the node linked to the known tags with one or more edges.

Abstract: A graph includes nodes representing applications and tags describing subjective qualities of the applications. The system responds to queries for user personas by using an LLM to match the persona to applications in the graph. The system receives a natural language query describing a persona. The system generates a prompt for an LLM based on the query and provides the prompt to the LLM for execution. The system receives, as output from the LLM, candidate applications. The system inputs the candidate applications into a classifier trained to classify candidate applications into known applications, applications that already exist in a graph. The system receives, as output from the classifier, known applications. The system determines, for each known application, a quality score of the known application and determines that the quality score exceeds a quality score threshold. In response, the system provides the known applications for display at a user interface.

Abstract: A largely automated method of categorizing spend data is provided that does not require a prior in-depth knowledge of an organization's transactional data. Natural language processing is applied to text data from transactional data to generate a consolidated cleaned data set (CDS) containing information for categorization. Logs for transactions are clustered based on similarity, forming the minimal data set (MDS). An automated algorithm selects a subset of high-value clusters that are categorized by requesting users to manually categorize one or more representative logs from each cluster of the subset. A model is then trained using the subset of manually categorized clusters and used to predict spend categories for the remaining logs with high accuracy. The AI engine automatically analyzes the predictions based on client context and either auto-tunes the machine learning model or identifies a new subset of clusters to be manually categorized. This loop may continue until 95%-100% of the spend is categorized.