FRANKFURT, June 26 (Reuters) – A recent paper published by the European Central Bank (ECB) reveals that analyzing qualitative commentary in PMI releases using ChatGPT can significantly enhance GDP forecasting. The ECB has been exploring artificial intelligence tools in recent years, including web-scraping price data and employing large language models for data classification. This latest study highlights that even small amounts of text from PMI releases can offer valuable insights into economic trends, improving real-time activity assessments. “The study uniquely focuses on the narrative, tone, and anecdotes found in PMI news releases,” the working paper explains. Economists utilized ChatGPT to generate sentiment scores based on these narratives, integrating them into current-quarter growth forecasts. The authors noted, “Adding PMI text scores to GDP nowcast benchmarks significantly improves forecast accuracy.” Remarkably, they found that just two pages of text could enhance benchmarks that are otherwise difficult to surpass.
— news from Reuters
— News Original —
ECB economists improve GDP forecasting with ChatGPT
FRANKFURT, June 26 (Reuters) – A ChatGPT analysis of qualitative commentary in PMI releases can significantly improve GDP forecasting, a paper published by the European Central Bank of Thursday showed.
The ECB has been working with artificial intelligence in recent years, partly to improve its forecasting ability by web-scraping price data and using large language models for data classification.
Sign up here.
However, this new study found that even relatively little text associated with PMI releases can provide meaningful guidance on economic developments, improving its ability to assess activity in real time.
“What makes this study unique is its focus on the narrative, tone, and anecdotes reported in PMI news releases,” the working paper argued.
Economists used ChatGPT to generate activity sentiment scores based on the narratives and anecdotes of PMI news releases, then integrated these scores into forecasts of growth in the current quarter, or nowcasts.
“The main compelling result is that the enhancement of the PMI text scores to the two GDP nowcast benchmarks significantly improves the accuracy of GDP nowcasts,” the authors argued.
“Only two pages of text rather than for example millions of newspapers articles can be sufficient to enhance existing hard-to-beat benchmarks,” they added.