Value at risk (VaR) is a measure of the risk of loss associated with an investment/ a portfolio/ a firm, etc. It takes into consideration the entire range of expected losses associated with the distribution of possible outcomes. VaR suffers a considerable weakness: it doesn’t produce consistent results across different return distributions. A more accurate measure that can overcome this shortcoming is known as the expected shortfall or (CVaR or C-VaR).

Conditional value at risk (CVaR) is a type of VaR that quantifies the amount of tail risk an investment portfolio is exposed to. CVaR is derived by taking a weighted average of the “extreme” losses in the tail of the distribution of possible returns, beyond the cutoff point of the standard VaR. It helps quantify the expected losses that would arise beyond that point.

VaR represents a worst-case loss (highest amount of loss to be sustained) in relation to a probability and a certain period of time. CVaR reflects the expected loss if that worst-case cutoff point is ever crossed.

VaR produces a single-figure estimation of loss as per the variables applied, while CVaR provides an added-up (discrete) figure, or an integral (cumulative) estimation of loss based on a continuous calculation of the probability-weighted average related to the tail in excess of the confidence level (e.g., 95%) using the same variables under VaR.