Surreal illustration of financial market uncertainty with a question mark over the landscape.

VaR or Not VaR: Why Value-at-Risk Models Are Facing an Uncertain Future

Kai Mendoza in Business & Economy June 2025 • 4 min read.

"Explore the economic obstacles challenging the reliability of Value-at-Risk (VaR) models and what it means for investors navigating today's volatile markets."

In the late 1960s, the Value-at-Risk (VaR) measure emerged as a response to a pressing question posed by JP Morgan's Chairman, Dennis Weatherstone: "How much can we lose on our trading portfolio by tomorrow's close?" This question sparked the development of VaR models by RiskMetrics Group, quickly becoming a standard tool for risk assessment in the financial industry.

VaR aims to measure the maximum potential change in the value of a portfolio over a specific time horizon, given a certain probability level. It provides a seemingly straightforward way to quantify risk, making it popular among investors, regulators, and financial institutions. However, the reliability and accuracy of VaR models are increasingly being questioned due to economic obstacles that limit their effectiveness.

One critical issue lies in the traditional approach to calculating VaR, which often relies on frequency-based price probabilities. This method determines the probability of price movements based on the number of trades at a specific price point over a given period. However, this approach overlooks the impact of large trade volumes and market dynamics, potentially leading to inaccurate risk assessments.

The Flaw in Frequency-Based Price Probability: Why Volume Matters

Surreal illustration of financial market uncertainty with a question mark over the landscape.

The conventional frequency-based approach to price probability assumes constant trade volumes, which is rarely the case in real-world markets. Large market transactions can significantly influence price movements, making the randomness of trade volumes a crucial factor in risk assessment. Ignoring this randomness can lead to an underestimation of potential losses and a false sense of security.

To address this limitation, a market-based approach to price probability considers the randomness of market trade values and volumes. This approach recognizes that the probability of a particular price movement depends not only on the frequency of trades but also on the size and impact of those trades.

Market-Based Probabilities: Reflect the impact of trade values and volumes on price movements.
Frequency-Based Probabilities: Assume constant trade volumes and may not accurately capture market dynamics.

By incorporating the randomness of trade volumes, market-based probabilities provide a more accurate picture of potential price fluctuations and a more reliable foundation for VaR assessments. This approach acknowledges that large trades can have a disproportionate impact on market prices, and therefore, their influence should be explicitly considered in risk management.

The Future of VaR: Adapting to Economic Complexity

As markets continue to evolve and become more complex, the limitations of traditional VaR models will become increasingly apparent. The accuracy of price probability predictions is likely to be constrained by the availability and reliability of data on market trade values and volumes. Furthermore, predicting market-based price volatility requires forecasting averages, volatilities, and correlations of trade values and volumes, which is a challenging task given the inherent uncertainty of economic activity.

About this Article -

This article was crafted using a human-AI hybrid and collaborative approach. AI assisted our team with initial drafting, research insights, identifying key questions, and image generation. Our human editors guided topic selection, defined the angle, structured the content, ensured factual accuracy and relevance, refined the tone, and conducted thorough editing to deliver helpful, high-quality information.See our About page for more information.

This article is based on research published under:

DOI-LINK: https://doi.org/10.48550/arXiv.2101.08559,

Title: To Var, Or Not To Var, That Is The Question

Subject: econ.gn q-fin.ec q-fin.gn q-fin.pm q-fin.pr q-fin.rm

Authors: Victor Olkhov

Published: 21-01-2021

Everything You Need To Know

What is Value-at-Risk (VaR) and why was it developed?

Value-at-Risk (VaR) is a measure designed to quantify the maximum potential loss of a portfolio over a specific time horizon, given a certain probability level. It was developed in the late 1960s in response to a question from JP Morgan's Chairman, Dennis Weatherstone: "How much can we lose on our trading portfolio by tomorrow's close?" VaR models, pioneered by RiskMetrics Group, became a standard risk assessment tool in the financial industry to answer this critical question.

How do frequency-based price probabilities work, and what are their limitations in calculating Value-at-Risk (VaR)?

Frequency-based price probabilities determine the probability of price movements based on the frequency of trades at specific price points over a period. The primary limitation is that this method assumes constant trade volumes, which is rarely true in real-world markets. It overlooks the impact of large trade volumes and market dynamics, potentially leading to inaccurate risk assessments and an underestimation of potential losses when calculating Value-at-Risk (VaR).

What is the key difference between frequency-based and market-based probabilities in the context of Value-at-Risk (VaR) calculations?

The fundamental difference lies in how they account for market dynamics. Frequency-based probabilities assume constant trade volumes, overlooking the impact of trade sizes. Market-based probabilities, however, consider the randomness of market trade values and volumes, acknowledging that the probability of a price movement depends not only on the frequency of trades but also on the size and impact of those trades. This makes market-based probabilities a more accurate reflection of potential price fluctuations in the calculation of Value-at-Risk (VaR).

Why is it crucial to incorporate the impact of trade volumes when assessing risk using Value-at-Risk (VaR) models?

Incorporating trade volumes is crucial because large market transactions can significantly influence price movements. Ignoring this randomness can lead to an underestimation of potential losses and a false sense of security. Acknowledging the influence of trade volumes, particularly in market-based probabilities, provides a more realistic and reliable foundation for Value-at-Risk (VaR) assessments, ensuring that risk management strategies are better equipped to handle market volatility.

What challenges does the future hold for Value-at-Risk (VaR) models, and what adaptations are needed?

As markets become more complex, traditional Value-at-Risk (VaR) models face increasing challenges. The accuracy of price probability predictions will likely be constrained by data availability and reliability concerning market trade values and volumes. Predicting market-based price volatility requires forecasting averages, volatilities, and correlations of trade values and volumes, a complex task given the inherent uncertainty of economic activity. Adapting to these challenges will require improved data analysis and more sophisticated models that can accurately reflect market dynamics and the impact of trade volumes on price movements.