Rose Williams

Partitioning knowledge bases between advanced notification and clinical decision support systems

Due to the varying rates of change of ephemeral administrative and enduring clinical knowledge in decision support systems (DSSs), the functional partition of knowledge base (KB) components can lead to more efficient and cost-effective system implementation and maintenance. Our prototype loosely couples a clinical event monitor developed by Columbia University Medical Center (CUMC) with a secure notification service proxy developed by IBM Research to form a novel and complex clinical event communication service.

Delivery Management Effort Allocation Using Learning-Based Profit Estimation

This manuscript presents a new approach for estimating projects profit based on available data from the same projects past as well as the past available data from all other projects in the same class. We build a statistical model that allows such inference in spite of known erratic financial behavior of services projects. Then, using the estimated profit along with its confidence margin, we propose a strategy for future allocation of project management effort to different projects.

Success in predicting troubled projects requires an adaptable model

Software risk management is a well established discipline that has generated continued academic interest as the complexity and nature of software projects have evolved over time. Traditional risk management techniques have been focused on identifying and codifying best practices that prevent or reduce the failure rate. Large IT organizations have assimilated many of these findings in their risk management practice. However, adopting these best practices does not guarantee that risk is eliminated or even reduced to an acceptable level — new software development models driven by globalization, competition and an ever changing software landscape create new patterns of trouble. Systems that predict trouble early in the project life cycle have had significant impact on our global portfolio of thousands of projects. Managers have mitigated the risks that were identified in our system. As such, the key predictors and their importance have shifted. We have discovered that our prediction model requires frequent updates — and this was not included in our initial design. We have learned that it is equally important to design and select statistical algorithms that will support automated model retraining as a way of incorporating a feedback loop of human behavior responding to our predictions.