top of page


Risk Management and Decision making

The world is changing to unknown with great uncertainty and increased volatility

Climate changes, technological breakthrough, geopolitical tensions, economic downturns, are only few examples to describe unforecastable events that generate unpredictable volatility in the market and leave business unprepared. There is no real past experience to help the decision makers. In one-word businesses need to coexist with uncertainty.

The Oxford dictionary’s definition of uncertainty is the lack of knowledge or information about something, a doubt. Organizations and individuals must be prepared to react to a range of possible outcomes and be flexible enough to adapt to the changing circumstances.

Risk vs uncertainty

Risk is where a decision-maker knows that several different outcomes are possible, the probabilities of which are known, or can be estimated, usually due to past experience. But what to do in case of uncertainty? “The risk of infection”, “the risk of a recession”, Cybersecurity threats Natural disasters, Changes in customer preferences are only few concrete examples where past experience cannot help and can drive a business to disaster.

Risk Management and Decision making

As showed in chart 1, the traditional Risk management is the process of identifying, assessing, and controlling potential risks to an organization. It involves analysing the potential risks that could affect the organization, determining the likelihood of those risks occurring, and developing strategies to mitigate or eliminate them.

Risk management refers to decision-making situations under which all potential outcomes and their likelihood of occurrences are known to the decision-maker: regulatory compliance risks, financial risks, reputational risks, data privacy risks, operational risks to state some of them.

Chart 1 - Risk Matrix

Example of Risk management under uncertainty

In absence of past experience, it would be impossible to assess correctly the likelihood and the impact of the specific risk with the impossibility to target the strategy and consequently loosing potential opportunities. There will be many questions and no answers.

Will our new product launch be successful? Are we risking cyber security attach with which impact? Will we attain our forecast?

Risk management focuses on reducing the potential risks associated with a decision, while and in addition decision making under uncertainty focuses on making the best decision given the available information.

Uncertainty and Decision making

Chart 2 shows how uncertainty can be managed through decision-making processes. This involves gathering and analysing information, and making decisions based on the analysis. This process can help to reduce the uncertainty associated with a situation by providing more information to understand the events. Uncertainty can be analysed to quantify the appropriate decision for a company given its risk-appetite profile.

Chart 2 - Decision making under uncertainty

An operational approach

There are several techniques to analyse uncertainty and, in our practice, we follow a modelling and systemic approach.

The combination of uncertainty analysis, sensitivity, and Monte Carlo simulation can be used as a powerful tool for decision-making. By understanding the range of possible outcomes and the probability of each outcome occurring, it is possible to make more informed decisions. This reduces the risk of poor decision and increases the chances of making the right choices.

Sensitivity analysis is used to identify the most important parameters in a system, and to quantify the degree to which changes in those parameters affect the system's output. This is done by varying the parameters and observing the resulting changes in the system's output. The parameters that have the greatest effect on the system's output are said to be the most sensitive parameters.

Once the most sensitive parameters have been identified, Monte Carlo simulation can be used to simulate the system. This is done by randomly selecting values for the parameters and then running the system with those values. The results of the simulation can then be used to understand the system and its behaviour and, consequently, the path to choose according to business risk appetite.

A concrete example.

Company LJ, “luxury jewels” intends to expand the US market.

The expected sales and EBITDA for the yr1 are 15.5M and 2.8M € respectively. As the US is relatively a new market, LJ has decided to simulate some scenarios.

The Sales sensitivities

in yr 1, LJ sales projection is 15.2m € and it feels that this B scenario at would be the most probable and that can beat it. Therefore, LJ has worked out a sensitivity based on 4 scenarios:

A - conservative sales at 15m

B - most probable sales at 15.2m and

C, D - possible sales upside at 15.5m and 16.0m respectively.

On top of the above sensitivity LJ has assumed a range of probability associated to each scenario: .45, .25 and .05 for scenario B, C and D and A respectively.

Chart 3 shows the montecarlo process in action, a discrete distribution of possible sales and the associated probabilities based on 100.000 simulations.

The results, summarised in the chart’s boxplot, shows the expected sales value at 15.5m € and the first quartile at 15.20m €. LJ has a 75% probability to generate sales above 15.2m €.

Chart 3 – Montecarlo Analysis Sales Sensitivities

The Gross Margin sensitivity

LJ expects a gross margin of 54% and feels it highly probable, normally distributed with a limited variance of around 2%.

Chart 4 shows the montecarlo process in action, a normal distribution of possible sales and the associated probabilities supported by 100.000 simulations.

The results summarised in the chart’s boxplot, shows the expected Gross Margin value at 54% and the first quartile being at 53.6%.

Chart 4 – Montecarlo Analysis Gross Margin Sensitivities

The SG&A sensitivities

In yr 1 LJ has estimated 5.35m € SG&A expenses. It feels that B scenario is the most probable but at the same time LJ has developed 4 additional scenarios to consider over or under spending with the associated probabilities.

Chart 5 shows the Montecarlo process in action, a discrete distribution of possible spending and the associated probabilities supported by 100.000 simulations.

The results are summarised by the chart’s boxplot: the expected spending will be 5.4m € and the third quartile will be 5.55m €: LJ has a 75% probability to spend less than be 5.55m €.

Chart 5 – Montecarlo Analysis SG&A Sensitivities

All together - The expected EBITDA.

Time to put all together. We defined the EBITDA as Sales * Gross Margin – SG&A. In particular LJ thinks that in case of sales overdelivering the increase SG&A by 10% while if in case of soft sales LJ will be able to cut SG&A by 5%.

The boxplot summarizes the results of the previous simulations. The expected results will be 2.8M and the first quartile at 3.2M€. The minimum value will be 2.0M meaning that there is very high likely hood that the US venture will be not lossmaking.

Chart 6 – Montecarlo Analysis on EBITDA


Uncertainty, sensitivity, and Montecarlo simulation are all related concepts used to analyse and understand complex systems. Uncertainty is the lack of knowledge about the system, sensitivity is the degree to which the system is affected by changes in its inputs, and Montecarlo simulation is a method of using random numbers to simulate the system. By combining these three concepts, it is possible to gain a better understanding of complex systems and their behaviours.

In business, uncertainty, sensitivity, and Montecarlo simulation are often used to assess the risk of a particular venture. For example, a company may use sensitivity analysis to determine how market changes will affect the success of a new product or as in our example to evaluate the success of entering a new and unexplored market. Montecarlo simulation can in addition be used to assess the probability of the product being successful or not. By combining these three concepts, a company can gain a better understanding of the risk associated with a particular venture and make more informed decisions.


Mario is a seasoned finance executive, who served as CFO for fire & security, food, energy and clean-tech global companies. He has turn-around experience and managed to re-finance growing businesses.

Mario is the Managing Partner at TML Venture Ltd. and supports companies in finding tailor-made investment solutions. His industry focus is on renewable technology, energy and food companies.


Featured Posts
Recent Posts
bottom of page