To guide business planning and portfolio management for carbon-fund portfolio managers, estimate the probability of an Emission Reduction (ER) program succeeding in a specific developing country, with little or no data on similar projects in that country.
Causal Links developed a knowledge-based Bayesian network model through discussions with a team of experts and researchers to capture their knowledge about various factors that could affect the outcome of a project. Such factors included the political and economic climate of the country,stakeholder involvement, external risks, quality of the design, and complexity of the project.
The in-depth information collection enabled us to create an intelligent advisory tool to compute the risks to the project, based on the general underlying model and the specific context of the project.
Through a probabilistic model, the tool derived the probability of a particular program generating its projected ERs after discounting for program-specific risk.
A key feature of the ER delivery risk assessment tool is that it continues to learn from data. Over time its parameters can be adjusted based on the new evidence collected and lessons learned from implementation (i.e., the probabilistic influences among various factors on ER delivery).
The tool is used by carbon fund portfolio managers for purposes of allocating capital wisely, negotiating ER contracts, as well as for advising the developing countries about ways to improve the likelihood of success of the project.