Installing, configuring, and administering IBM Business Automation Machine Learning Server

Edit online

Machine Learning Server enables services such as Decision Recommendation, Intelligent Task Prioritization, and Workforce Insights.

 V20.0.0.2  If you are installing multiple services for Machine Learning Server, only one instance of Machine Learning Server is required. For instructions on configuring the services, see Configuring Machine Learning Server services. The following list briefly describes each of the services that can be configured with Machine Learning Server:

Decision Recommendation
Decision Recommendation is a service that generates recommendations for business processes that involve decision making by building a predictive machine learning model pipeline by using process execution logs and business data. You can build the decision recommendation model by identifying the activity in the process that requires a decision, and the corresponding related variables. After the predictive model is built, you can obtain:
  • The recommendation for each decision activity.
  • The confidence interval of the recommendations.
  • Explanations for the recommendations by using the major contributing features the model uses.
Intelligent Task Prioritization
With Intelligent Task Prioritization, a task list uses historic runtime data to automatically prioritize tasks, leading to workforce efficiency improvements. Tasks are assigned to a user in an optimal sequence to maximize throughput according to:
  • Who is an expert for that task.
  • The impact of the worker for that task predicted by processing times.

Task experts are determined by using a self-supervised classification neural network that predicts the likelihood of whether a worker will complete a task faster than the workforce average. Processing time is determined by using a regressive neural network that predicts how long it takes a worker to complete a task in seconds. These models are hosted in Machine Learning Server.

Workforce Insights

Workforce Insights enables the computation of various process-related key performance indicators, such as the execution time for activities, waiting time for activities, activity execution frequency, reworks, actor efficiency rankings, team utilization statistics, and team throughput. For more information about enabling Workforce Insights, see Enabling Workforce Insights.