Panel data modeling of bank deposits

Studying the dynamics of deposits is important for three reasons: first, it serves as an important component of liquidity stress testing; second, it is crucial to asset-liability management exercises and the allocation between liquid and illiquid assets; third, it is the support for a Liquidity at Risk methodology. Current models are based on $$\textit{AR}(1)$$ AR ( 1 ) processes that often underestimate liquidity risk. Thus, a bank relying on those models may face failure in an event of crisis. We propose an alternative approach for modeling deposits, using panel data and a momentum term. The model enables the simulation of a variety of deposit trajectories, including episodes of financial distress, showing much higher drawdowns and realistic liquidity at risk estimates, as well as density plots that present a wide range of possible values, corresponding to booms and financial crises. Therefore, this methodology is more suitable for liquidity management at banks, as well as for conducting liquidity stress tests.