Monte Carlo in Practice

Techniques for Handling Increasing Uncertainty

By Access Analytic


Non-financial Information may be far more important than you think.

In fact, non-financial KPIs are often more important than financial information. Where financial KPIs are quantitative, non-financial KPIs can frequently be more qualitative and subjective.

However, they may well drive your financial KPIs, and can be critical for decision-making.

Deterministic vs Probabilistic Models

Standard ‘deterministic’ models typically deliver outcomes with single answer(s); based on limited input scenario(s) and estimated values and sensitivities.

However, a ‘probabilistic’ Monte Carlo model can deliver a range of answers that are based on estimated values, probable ranges, and statistical distributions for the various input variables.

In finance, they are often used to calculate the value of companies, to evaluate investments in projects at a business unit or corporate level, or to evaluate financial derivatives.

Monte Carlo in the Real World

In oil and resources exploration, their predictions of failures, cost overruns and schedule overruns are routinely better than human intuition or alternative ‘soft’ methods.

They can also be used to model project schedules, where simulations aggregate estimates for worst-case, best-case, and most likely durations for each task to determine outcomes for the overall project.

Monte Carlo methods simulate sources of uncertainty that affect value, and calculate a representative range of values. They are used to handle multiple sources of uncertainty, and typically, analysts will have an idea of the range of numbers expected but not the exact number.

Applying Monte Carlo to your Models

For simple Monte Carlo analysis, you can use Excel alone but it’s much easier and more powerful if you use add-ins such as ‘Crystal Ball’ or @Risk.

To utilise the Monte Carlo technique, you’d follow the steps below:

  1. Construct financial model as normal.
  2. Identify the variables impacted by uncertainty.
  3. Identify the expected range of values and distribution type, based on historical data or estimate range.
  4. Generate a large number of random values using selected distribution.
  5. Run multiple simulations, record the results and analyse them.

Find out more

To find out more, just contact us to discuss how these techniques can be applied to your financial models and/or obtain training for your staff in how to perform and apply Monte Carlo.