As part of the Eurosystem’s annual banknote production planning, the national central banks draw up forecasts estimating the volumes of national-issued banknotes in circulation for the three years ahead. As at the end of 2021, more than 80 per cent of euro banknotes in circulation (cumulated...

We find that the salience distortions of past fundamental information significantly predict future analyst forecast errors in both Chinese and U.S. markets. Fundamental salience is more potent in distorting long-term beliefs. Predictable forecast errors are more pronounced in firms with opaque...

This paper analyzes the inflation forecast errors over the period 2021Q1-2022Q3 using forecasts of core and headline inflation from the International Monetary Fund World Economic Outlook for a large group of advanced and emerging market economies. The findings reveal evidence of forecast bias...

Managing inflation is vital for a stable economy, but forecasting remains challenging. ML methods, like neural networks, have shown promise in forecasting inflation and other macroeconomic variables. In this paper, I propose DPCNet, a deep multi-task learning model, to jointly forecast inflation...

Not all errors from models predicting asset returns are equal in terms of impact on the efficiency of the algorithm: a small error could trigger poor investment decisions while a significant error has no financial consequences. This economic asymmetry, critical for assessing the performance of...

Using a large sample of listed firms in Japan, where management earnings forecasts are effectively mandated, we show that managers of firms covered by analysts are more likely to be accurate in terms of their initial and last forecasts and their forecast revisions during the fiscal year are more...

With the advent of Big Data and machine learning/AI technologies, actuaries can now develop advanced models in a data-rich environment to achieve better forecasting performance and provide added value in many applications. Traditionally, economic forecasting for actuarial applications is...

This project focuses on using predictive modeling techniques to combat money laundering and improve Anti-Money Laundering (AML) compliance efforts. The IBM Synthetic Financial Data Money Laundering dataset is used to explore the effectiveness of different machine learning algorithms in...

Euro area labour market variables are published with a considerable lag, longer than in the case of real GDP. We develop a suite of models to provide a more timely estimate (nowcast) of euro area quarterly employment growth based on a broad range of monthly indicators. The suite includes a batch...

In this project we try to predict bad loans with Machine Learning models. We approach the problem as a Supervised Classification problem. We conduct a preprocessing step, and deal with imbalance. As a first step we apply various Machine Learning models and identify the best ones. With the...