Your company has developed a great new product. It seems like the “next big thing,” but will it be profitable? Nobody wants to be part of the next product-release fiasco. Remember New Coke, or the Yugo?

How can we estimate highly uncertain variables such as average profitability and riskiness of new products? More and more companies are turning to quantitative risk analysis to help them make the best decision under uncertain circumstances. Monte Carlo simulation is a powerful form of quantitative risk analysis that allows you to see many possible outcomes in a given situation and the probabilities of different outcomes occurring. There is add-in software for Microsoft Excel that adds Monte Carlo simulation functionality to spreadsheet models, making this technique accessible to any desktop user. By adding new native Excel functions to your spreadsheet, such software makes it possible to model uncertainty exactly the same way and with the same flexibility you would have building any Excel model. This kind of software also incorporates advanced sensitivity analysis features to identify drivers of risk, and include a variety of results graphs and charts for ease of interpretation.

For example, imagine a company called Pigco is thinking of marketing a new drug that will be used to make hippos healthier. Pigco builds a model that sets up all the variables involved in marketing the new product, such as market size, dose per animal, whether competitors will enter the market, sales, revenue, costs, and profits. Some of these input factors are uncertain. Instead of entering a best guess estimate for these values, we have entered probability distribution functions (such as Normal or Uniform) directly in those cells. These distribution functions (shown in green in our example model) simply represent the ranges of values that these uncertain factors could be. The Net Present Value of the company’s 5 year profits is the output cell for the simulation—in other words, the bottom line.