# What is Sensitivity Analysis in Finance?

Despite the benefits that financial modeling brings to analysts and decision-makers, modeling is never 100% accurate. Even if you account for every possible variable, there’s still no way to predict the future with complete accuracy.

This is why financial institutions often use sensitivity analysis to “stress-test” their models and confirm (or debunk) their assumptions before presenting their findings to stakeholders. Executives are more likely to make better decisions for their companies when they can get a closer look at how their business might react to unlikely or unpredictable scenarios.

Let’s take a look at how sensitivity analysis is used in finance, its advantages and disadvantages, and how new innovations can help transform how analysts perform sensitivity analysis in the 21st century.

## What is sensitivity analysis?

Sensitivity analysis is a financial modeling tool that goes by several names—it’s also referred to as what-if analysis, simulation analysis, and data tables.

Financial professionals often use Excel or a similar spreadsheet-based solution to study the impact a specific set of independent variables (or inputs) has on a specific set of dependent variables (or outputs) in any given scenario.

The most well-known example of sensitivity analysis is performed annually by the Federal Reserve. The Comprehensive Capital Analysis and Review (CCAR) is used to assess whether the largest bank holding companies in the U.S. can weather worst-case market scenarios, such as sudden market crashes or high default rates for mortgages.

By taking historical data and using it to forecast future possibilities, sensitivity analysis helps modelers answer the question:

What would this model look like if these variables were to change?”

Sensitivity analysis is especially useful for analyzing complex “black box” scenarios. These situations often have independent and dependent variables with indeterminate relationships. Sensitivity analysis helps bring some much-needed clarity to these scenarios.

Of course, sensitivity analysis isn’t just useful on Wall Street. Analysts and scientists across a wide range of industries—including engineering, geography, physics, economics, and chemistry—perform their own sensitivity analyses as well.

## How does sensitivity analysis work?

When a financial professional performs sensitivity analysis on a financial model, they start by identifying all the independent variables that might impact outcomes.

Once all of these inputs have been identified, analysts change one independent variable at a time—keeping all other variables the same—to observe the impact that variable has on each output. They want to find out:

• How sensitive their financial models are to changes in variables
• How the variables impact each other and affect the outcomes

After answering these questions for one variable, the analyst moves on to the next one. This is called a one-at-a-time (OAT) sensitivity analysis, and it’s one of the most popular and reliable ways to determine the hidden relationships between variables.

In this way, sensitivity analysis helps stakeholders identify the inputs that have the biggest impact in different situations so that they can make smart decisions about how to best manage risk and best position themselves for growth opportunities.

## How sensitivity analysis is used in finance

Thanks to its ability to make predictions of the future, financial modelers use sensitivity analysis for many different purposes.

Because business leaders operate and make sweeping decisions with a huge amount of uncertainty, sensitivity analysis helps reduce the risks of a bad decision by offering insights into how a situation may play out. Leaders can then make decisions with more confidence, as they now have a better handle of the risks and issues involved with any one commitment.

If they wanted to change the entire nature of a business, for example, creating a what-if analysis would allow executives to see how the different aspects of their company would be affected by this change.

A company could also use sensitivity analysis to determine the return on investment (ROI) on a new advertising campaign. If they wanted to see the impact of a people-centered campaign versus a product-centered one, they could look at the results of past marketing efforts.

By comparing the results of campaigns that featured people prominently to those that did not, a marketing executive would be able to make their decision based on data rather than just speculation.

Sensitivity analysis can also be used to show where a process needs improvement or adjustment. In fact, analysts often use this method to audit existing financial models, making it especially helpful for risk analysis scenarios.

When it comes to complex projects with lots of stakeholders and many moving parts, assumptions tend to always be outdated. New information is constantly being considered.

The major advantage of sensitivity analysis is that it helps decision-makers stay on top of the ball and identify, in real-time, the biggest risks to their projects as well as the most optimal responses in any given situation. That way, they’re never surprised and they can react quickly no matter what happens.

Sensitivity analysis also helps analysts create more accurate forecasts by allowing them to study and compare the impact of different independent variables in greater depth.

But any type of analysis is only as good as the person running the numbers. The chosen inputs (assumptions, independent variables, probabilities, etc.) impact the entire model. If any of these assumptions are incorrect, the analyst risks compromising the integrity of the entire model.

And because the relationships between inputs and outputs is often framed as a one-to-one correlation, sensitivity analysis may actually lull less-experienced analysts into a misplaced sense of confidence…which usually leads to more incorrect assumptions.

Finally, sensitivity analysis requires real historical data. But as we all know, past performance is not a perfect indicator of future success. In many cases, you can expect to revise your model over and over again to account for new information that becomes available over time.

## The difference between sensitivity analysis and scenario analysis

Sensitivity analysis and scenario analysis are both tools that financial analysts frequently use in their work. Due to their similarities, it’s easy to confuse them.

Sensitivity analysis focuses on the relationships between independent and dependent variables. It helps analysts determine how sensitive dependent variables are to changes in a single independent variable.

Scenario analysis, on the other hand, looks at a specific scenario in very close detail. Analysts choose all of the variables that contribute to a given outcome and change them in different combinations and permutations. It tends to be a lot more complex.

Financial modelers will often use scenario analysis to examine macroeconomic events that bring great change to an industry or company, such as a shift or reversal in market trends or an unexpected policy announcement.

## Spark a financial modeling revolution

One of the biggest drawbacks of sensitivity analysis is how heavily it relies on the assumptions of an imperfect analyst, who then builds a financial model that business leaders will use to make crucial decisions that could reshape an entire company’s fortunes.

Frankly, those analysts have the weight of the world on their shoulders. It’s hard enough to build a financial model that you can run scenarios against. The last thing you want to deal with on top of that are typos from collaborators, multiple outdated spreadsheets lurking in recent emails, or having to create a PowerPoint that will probably be outdated before you reach the boardroom.

Synario drastically reduces the time it takes to get your financial model from your computer to the boardroom using our patented Multiverse Modeling™ technology—saving you countless hours and speeding up the decision-making process.

Even better, Synario’s presentation mode allows you to turn your results into an easy-to-understand presentation with a click of a button. What decision-maker wouldn’t enjoy that?