MONTE CARLO SIMULATION CHALLENGES Inputs • Scope • Time • Cost A project delivery plan also integrates: • Risks (including uncertainties) • • Resources (People, Equipment & Materials) Benefits Full integration means that changes in one parameter are reflected in other parameters. Outputs Figure 1 - The Monte Carlo Simulation Method. Last year, I organised a LinkedIn poll to clarify what project practitioners think about the Monte Carlo simulation method. The poll had a lot of attention, and many projects and risk consultants have shared their opinions. The following conclusions could be made based on these discussions, comments and the final results: • Monte Carlo Risk Simulation is the most recognised quantitative project risk analysis method; • There is no common acceptance of this method across project practitioners; • The opinion about Monte Carlo Simulation is mostly based on perception rather than knowledge of how this method works; • Many planners and risks consultants are not aware of missing functionalities in Risk Simulation tools. Monte Carlo Simulation method A Monte Carlo Simulation is a model used to predict the probability of different outcomes when the intervention of random variables is present. Monte Carlo simulations help to explain the impact of risks and uncertainties in prediction and forecasting models. To be useful a model has to be dynamic and represent the true relationships between inputs and outputs. A Monte Carlo Simulation is performed to identify: • Project risks that require maximum attention • • • • • Project targets that can be met with sufficient probabilities Contingency reserves that must be created to meet project targets Current probabilities of meeting project targets Resources required for the reliable achievement of project targets Project activities that require maximum attention Monte Carlo Simulation Process In project management Monte Carlo Simulation have to be applied the following way: 1. Integrated logically driven Project Delivery Plan developed and assessed; 2. People enter three estimates of initial data that are uncertain (optimistic, most probable and pessimistic) and define what probability distribution each uncertain parameter has; 3. Risk events are included in the project risk model with their probabilities and impacts; 4. Corresponding corrective actions added if targets achievements are endangered; 5. The software calculates the model and accompanying parameters over and over, each time using a different set of initial data in accordance with their probability distributions. The number of iterations is usually defined by the risk management software user. Usually, this number is measured in thousands of iterations. As the result, we get the distributions of possible outcome values. Simplicity Challenge Figure 2 - Monte Carol Simulation Model. Model Project Delivery Plan is used as a model for project planning and delivery. While the described process may look simple, the development of a dynamic model requires a deep understanding of project management processes, especially in schedule and risk management. Project specialists often don’t recognise this challenge. There are a few reasons why they accept the idea that the application of the scientific method in complex and complicated environments could be as simple as: “Prepare model and estimations, add risks and uncertainties, simulate, and report”: 00:0 5
6 Online Touch Home