We live in unpredictable times, whether this relates to the global economy and business, the climate or geopolitics. Anticipating the risks is important to humanity’s future resilience. This involves making sense of increasingly complex information aided with new tools. In this series we look at the work of researchers as they strive to make better predictions.
Economies are dynamic systems where relationships between variables shift over time. Despite uncertainty, governments and businesses must assume certain pathways for economic conditions, in order to make meaningful plans, with respect to labour or investment. This is why the work of the Institute of Applied Economics (CREA) at HEC Lausanne is so important.
Why economic forecasts matter
“For decision makers they need to anticipate what will happen in the future in terms of economic growth, inflation and interest rates. This is why accurate forecasting is vital,” explains Mathieu Grobéty, economist and director of CREA Institute.
He adds: “Yet the global economic situation is increasingly unpredictable, especially with the current U.S. administration. Geopolitical tensions, this includes what’s happening in Ukraine and Europe, also have a large effect on economic forecasting.”
This is where scenario-based forecasting helps. These are based on varying positive or negative assumptions, in order to characterise uncertainty. These assumptions are transparent, allowing economists and the public to understand how forecasts are constructed and how outcomes might shift if economic conditions improve or deteriorate.
Accuracy in volatility
“It’s also important to calculate the variance or volatility we see in our forecasts since this is another way of characterising levels of uncertainty. This is where density forecasts are used, since they quantify uncertainty and capture the probability that a variable will evolve within a certain range. Density forecasts can be deployed to evaluate short-term risks,” details Grobéty.
Accuracy is always a challenge with forecasting, the aim is neither underpredict or overpredict on average, for instance when it comes to evaluating inflation rates. Another challenge is making sense of huge tranches of data. This is where factor analysis is used. This condenses many variables into a few, so that the data is easier to work with.
“It is essential that we identify economic shocks and build scenarios around them, whether they arise from supply side disruptions or unexpected shifts in monetary policy. Beyond this, producing unbiased forecasts and making efficient use of all available information is always a demanding task. Our objective is to ensure that our projections are as accurate and robust as possible,” states the director of CREA.
CREA forecasting models
CREA always evaluates the performance of its forecasting models, comparing them to other benchmarks and those from a consensus of economic experts. It has a series of indicators including the prediction of GDP growth in Switzerland. It also has a Business Cycle Index, which analyses the state of each canton’s economy.
“The Swiss economy depends on a lot of factors including the labour market, consumer demand, the effective exchange rate, GDP, industrial production and exports. These factors can go in multiple directions at the same time. We try to aggregate all this information in our indexes,” he explains. The Institute regularly publishes analysises in major Swiss media outlets, contributing to public debate and affirming its position as a reference for economic analysis and forecasting
The CREA Institute is now developing a new forecasting methodology, which will be available towards the end of the year. This could provide an even more accurate picture of the Swiss economy.
“As an economist and academic it’s really important to make even more accurate forecasts that are rigorous, replicable quantitative models that minimise any biases. We are always trying to make things better!” concludes Grobéty.
