Abstract: A method and system are provided for training a machine learning (ML) system for predicting delays in processing pipelines. In one embodiment, the method includes receiving labelled historical data pertaining to a pipeline, the labelled data including trigger objects initiating the pipeline and one or more processing times corresponding to one or more stages of the pipeline. The method includes identifying features associated with the trigger objects, formatting the labelled data and, randomly splitting the formatted labelled data into a full training dataset and a testing dataset. Additionally, the method includes distributing the full training dataset into several partial datasets and, in an ensemble ML system, training each of several ML subsystems using a respective partial dataset to provide a respective individual inference model predicting respective processing times, and deriving and storing an ML model for prediction of delays by aggregating the individual inference models.

Abstract: A method and system are provided for matching database records. According to one embodiment, the method includes receiving a record from a first database, and selecting a sequence of characters within the record. The method also includes identifying a key associated with a second, dissimilar database by comparing the selected sequence with a number of historical records. The comparison is performed using one or more analytical processes, where at least one analytical process is a machine-learning (ML) process. The method further includes matching, using the key, the record from the first database with another record from the second database, where the other record includes the identified key.

Abstract: A method and system are provided for training a machine learning (ML) system for predicting delays in process pipelines. According to one embodiment, a method for training includes receiving labelled historical data pertaining to a pipeline, where the labelled data includes trigger objects initiating the pipeline and one or more processing times corresponding to one or more stages of the pipeline. The method also includes identifying one or more features associated with the trigger objects, formatting the labelled data and, using a pseudorandom generator, randomly splitting the formatted labelled data into a full training dataset and a testing dataset.