PLA Test Requirements

If the HPL uses market data in a different manner to RTPL to calculate risk parameters that are essential to the valuation engine, these differences must be reflected in the PLA test and as a result in the calculation of HPL and RTPL. In this regard, HPL and RTPL are allowed to use the same market data only as a basis, but must use their respective methods (which can differ) to calculate the respective valuation engine parameters. This would be the case, for example, where market data are transformed as part of the valuation process used to calculate RTPL. In that instance, banks may align market data between RTPL and HPL pre-transformation but not post- transformation. 12.33 Banks are not permitted to align HPL input data for risk factors with input data used in RTPL. Adjustments to RTPL or HPL to address residual operational noise are not permitted. Residual operational noise arises from computing HPL and RTPL in two different systems at two different points in time. It may originate from transitioning large portions of data across systems, and potential data aggregations may result in minor reconciliation gaps below tolerance levels for intervention; or from small differences in static/reference data and configuration. PLA test metrics 12.34 The PLA requirements are based on two test metrics: (1) the Spearman correlation metric to assess the correlation between RTPL and HPL; and (2) the Kolmogorov-Smirnov (KS) test metric to assess similarity of the distributions of RTPL and HPL. 12.35 To calculate each test metric for a trading desk, the bank must use the time series of the most recent 250 trading days of observations of RTPL and HPL. Process for determining the Spearman correlation metric 12.36 For a time series of HPL, banks must produce a corresponding time series of ranks based on the size of the P&L (R HPL ). That is, the lowest value in the HPL time series receives a rank of 1, the next lowest value receives a rank of 2 and so on. 12.37 Similarly, for a time series of RTPL, banks m0ust produce a corresponding time series of ranks based on size (R RTPL ). 12.38 Banks must calculate the Spearman correlation coefficient of the two time series of rank values of R RTPL and R HPL based on size using the following formula, where σ RHPL and σ RRTPL are the standard deviations of R RTPL and R HPL . Process for determining Kolmogorov-Smirnov test metrics 12.39 The bank must calculate the empirical cumulative distribution function of RTPL. For any value of RTPL, the empirical cumulative distribution is the product of 0.004 and the number of RTPL observations that are less than or equal to the specified RTPL. 12.40 The bank must calculate the empirical cumulative distribution function of HPL. For any value of HPL, the empirical cumulative distribution is the product of 0.004 and number of HPL observations that are less than or equal to the specified HPL. 12.41 The KS test metric is the largest absolute difference observed between these two empirical cumulative distribution functions at any P&L value. PLA test metrics evaluation 12.42 Based on the outcome of the metrics, a trading desk is allocated to a PLA test red zone, an amber zone or a green zone as set out in Table 2. (1) A trading desk is in the PLA test green zone if both (a) the correlation metric is above 0.80; and (b) the KS distributional test metric is below 0.09 (p-value = 0.264). (2) A trading desk is in the PLA test red zone if the correlation metric is less than 0.7 or if the KS distributional test metric is above 0.12 (p-value = 0.055). (3) A trading desk is in the PLA amber zone if it is allocated neither to the green zone nor to the red zone. PLA test thresholds Table 2 Zone Spearman correlation KS test Amber zone thresholds 0.80 0.09 (p-value = 0.264) Red zone thresholds 0.70 0.12 (p-value = 0.055)