On the Construction of a Leading Indicator Based on News Headlines for Predicting Greek Deposit Outflows

Abstract

Employing data in a monthly frequency, with a sample period spanning from 2002 to 2018, the purpose of this study is twofold. First, we construct a novel leading indicator based on news headlines drawn from Bloomberg, and second, examine whether this leading indicator able to capture agents’ sentiment affects Greek bank deposit flows’ trajectory. Employing alternative econometric methodologies, we find that this index proxies for depositors’ crisis sentiment and the higher this index becomes, the higher the depositors’ negative sentiment becomes, leading them to withdraw their bank deposits. Overall, in this work, we show that the last decade’s advances in internet technology, which permit us to have direct access to a vast amount of information such as news headlines, offers the possibility of forecasting critical measures in the economy’s banking system, such as the number of bank deposits, which are of crucial importance. Monetary poly authorities or macroprudential regulators could adapt our model to assess the resilience of a bank or the whole banking sector.

Bank deposits and textual sentiment: When an European Central Bank president's speech is not just a speech

“…Apart from all the previous studies, there is also extensive literature supporting that depositors' actions are not determined neither by “sunspots” nor by fundamentals but by other reasons such as economic sentiment, depositors' networks, and personal beliefs and attitudes (Anastasiou & Drakos, 2020; Anastasiou & Petralias, 2021; Brown et al., 2020; Iyer & Puri, 2012; Martinez‐Peria & Schmukler, 2001; Nys et al., 2015; Oliveira et al., 2014; Osili & Paulson, 2014).…”

Short-term prediction of bank deposit flows: do textual features matter?

“…Even though there is an extended background theory on the determinants of bank deposits (Martinez-Peria and Schmukler, 2001;Hondroyiannis, 2004;Finger and Hesse, 2009;Oliveira et al, 2014;Nys et al, 2015;Anastasiou and Katsafados, 2020;Anastasiou and Drakos, 2021a;Anastasiou and Drakos, 2021b) the literature on forecasting deposit flows is still sparse. Especially, as far as we know, the only studies that conduct a forecasting exercise for bank deposits are these of Piscopo (2010), Petropoulos et al, (2018), and Anastasiou and Petralias (2021). In more detail, Piscopo (2010) developed a functional data model with ARIMA terms for forecasting the evolution of Italian bank deposits.…”

“…Petropoulos et al, (2018) developed a Markov-regime switching autoregressive model to forecast Greek private sector bank deposits. Finally, Anastasiou and Petralias (2021), after constructing a novel leading indicator based on Bloomberg news headlines, examined its forecasting ability on Greek bank deposit flows employing a Markov Regime Switching Regression model.…”