EY EAT follows and analyses macroeconomic conditions on the ongoing basis, always staying up to date with current developments. We cover a broad range of economies, focusing on Europe and a broader EMEIA region. Together with multi-year experience and very strong quantitative skills, this allows us to draw unique insights and prepare realistic forecasts, which are consistent with economic theory and the current state of knowledge.
We adapt the class of models used – from econometrics to machine learning — to the research question. For example, econometric techniques can help us to quantify the impact of macroeconomic factors on the business and identify key drivers of performance. Through the use of machine learning and data visualization techniques, we can identify patterns and trends in the data that can inform more accurate forecasting.
In addition to understanding the changes that are happening in the economy as a whole, it is also important to understand how these changes are affecting specific businesses and their customers. This requires analyzing industry-specific data, customer behavior, and other factors that may influence demand for a particular product or service. Therefore, next to economic variables, we include other important industry-specific factors in the analysis.
We produce our in-house macroeconomic forecasts using a large-scale model of the global economy, developed from the Oxford Economics Global Economic Model. When the Client needs a macroeconomic forecast which is more tailored to their needs or wants to build their own model, we use advanced econometric techniques such as (Bayesian) Vector Autoregressions (VARs) or Structural Equation Models.
The impact of macroeconomic variables on the client’s business is assessed using a wide range of econometric methods, depending on the specifics of the business studied and data availability. Other than macroeconometric methods mentioned above, we use panel data methods and GARCH models, for example. In specific cases the analysis may be supported by non-econometric methods such as Computable General Equilibrium (CGE) models or data science techniques.
We can provide a very detailed description of data, codes and manuals so that the delivered models can be used and/or further developed by the Client’s analytical teams.