The Five Tribes of Machine Learning and What You Can Take From Each
There are 5 main schools of thought in machine learning, and each has its own master algorithm. What we need is a single algorithm combining the key features of them all. Pedro Domingos, University of Washington describes his work toward this goal.
Text Analytics on Electronic Medical Record Data
This session Mark Pitts, Lifetime Healthcare describes the journey from data acquisition to text analytics on clinical, textual data and includes real examples of clinical data and the challenges involved.
Do's and Don'ts of Measuring Forecast Accuracy
Len Tashman, Foresight: The International Journal of Applied Forecasting describes pitfalls forecasters face when working to produce accurate forecasts and suggests how to replace them with more appropriate practices.
Simulation Approach for Aircraft Spare Engines and Engine Parts Planning
Jose Ramirez-Hernandez and Mei Zhang, American Airlines present a simulation-based method for planning the required spare-ownership levels for engine spares and parts.