Arthur Turrell, Nikoleta Anesti and Silvia Miranda-Agrippino.
As the American playwright Arthur Miller wrote, “A good newspaper, I suppose, is a nation talking to itself.” Using text analysis and machine learning, we decided to put this to test – to find out whether newspaper copy could tell us about the national economy, and in particular, whether it can help us predict GDP growth.
Estimates of GDP growth are published with a considerable lag – even in some major economies we still only have partial data on what GDP growth was in Q1 2018. So ‘nowcasting’ GDP using more timely indicators of economic activity is an important way of assessing the strength of the world economy in real time. Good indicators are timely, correlated with measures of world activity and should outperform simple benchmarks. Unlike other global indicators such as business surveys or trade data, metals prices are available minute by minute. They also tend to move closely with world GDP. This post assesses how well they perform at nowcasting world GDP.