BY EMILY HOLLIS
What is back-testing and what benefits does implementation of such a model serve a credit union? Read on to discover some of the ways in which comparing actual data with past projections can be and cannot be of value for your CU.
Back-testing a model compares the projections of a past report against the actual figures produced during that same time horizon.Back-testing is a way to check the sufficiency of the data, the setup and the assumptions used to produce an analytical report.
Comparing actual data with a past projection can help identify and measure discrepancies. That way, any that are found can be properly explained or corrected.From an interestrate risk perspective, back-testing is only possible in some cases.It’s also important to note that the assumptions in an ALM model are necessary to isolate interestrate risk. Therefore, they can’t be perfectly replicated in actuality.The only way this replication could be achieved is if all projected rates in the modeled scenarios were to be realized.
An ALM model typically stresses the balance sheet in parallel rate shocks.In reality, yield curves would never move in such a way,nor would they move immediately up 300 basis points, the most focused scenario.Thus, an institution couldn’t use such shocked IRR results as a perfect basis for measuring future volatility.