Organizations are regularly faced with decisions that can significantly affect their operations. These decisions can be informed by data, models, preferences, and optimization methods to help organizations make decisions that better meet their needs.
- Should a utility company spend money now to replace aging pumping equipment and thereby save maintenance costs and service interruptions later, or wait for the equipment to fail and pay the associated costs at that time? How much will the future costs be?
- Should an insurance company settle a lawsuit against a manufacturer they insure for faulty products, or pay the costs to sample and investigate those products and thereby have a better chance of settling for a lower price?
- Should a fire department have a constant staffing level to be equally ready for calls no matter where or when they might come in, or should they alter their staffing by location and time of day and day of the year to better match the real-world frequencies of their actual calls?
- Should a city government invest in a new building climate monitoring and control system to improve the energy efficiency of government buildings, or will the savings be outweighed by increased complexity, staffing, and maintenance requirements?
These are just an example of the kinds of decisions that can be informed by collecting and analyzing existing data, building models of the processes that affect the decision, and using those models to produce high quality predictions of the outcomes, including uncertainty.