Online Value-At-Risk Computation

About this tool

This online tool aims to compute the Value-At-Risk according to the Historical approach.

It needs as input a CSV file containing the following information : Date, TradeID, P&L Vector.


How to compute your VaR ?


  • Upload your PnL Trades CSV file.
  • Select the trades for which you want to compute the VaR.
  • Provide the quantile value.
  • Provide the mode.
  • Provide the interpolation.
  • Click on the button Compute my VaR.

    • For further details about the measure computation or the configuration - please see the related section below.

     

    VaR Computation

    The application is expecting a csv file with the following header fields : AsOfDate | TradeID | PnL

    Trade Positions with PnL Vector
    		AsOfDateTradeIDPnL Vector
    No data
    Select a mode...
    Select an interpolation...
     

    More Information

    Value-At-Risk

    Value-At-Risk represents an investor's maximum potential loss on the value of a financial asset or portfolio of assets, which is expected to be achieved only with a given probability over a given time horizon.

    It is, in other words, the worst expected loss over a given time horizon for a given level of confidence.

    VaR can be seen as a quantile of the profit-and-loss distribution associated with holding an asset or a portfolio of assets over a given period.

    This tool is computing the VaR, according to the Historical approach.


    Parameters

    Mode

    The method used to compute the index of the quantile.

    Knowing q the quantile of a vector V, available options are :

  • simple : V.length * q
  • centered : V.length * q + 0.5
  • exc : (V.length + 1) * q
  • inc : (V.length - 1) * q

    • Interpolation

    If the quantile index is not an integer, the interpolation decides what value is returned.

    Knowing a quantile index k with i<k<j for the sorted vector V.

  • linear : value = V[ i ] + (V[ j ] - V[ i ]) * (k - i)
  • lower : value = V[ i ]
  • higher : value = V[ j ]
  • nearest : value = V[ i ] or value = V[ j ] depending on which is closest to k