Recursive deep learning framework for forecasting the decadal world economic outlook

TL;DR

A deep learning framework to forecast the GDP growth rate of the world economy over a decade is developed and it is revealed that most of the developed countries would experience economic growth slowdown, stagnation and even recession within five years (2020-2024).

Abstract

The gross domestic product (GDP) is the most widely used indicator in macroeconomics and the main tool for measuring a country's economic output. Due to the diversity and complexity of the world economy, a wide range of models have been used, but there are challenges in making decadal GDP forecasts given unexpected changes such as emergence of catastrophic world events including pandemics and wars. Deep learning models are well suited for modelling temporal sequences and time series forecasting. In this paper, we develop a deep learning framework to forecast the GDP growth rate of the world economy over a decade. We use the Penn World Table as the data source featuring 13 countries prior to the COVID-19 pandemic, such as Australia, China, India, and the United States. We present a recursive deep learning framework to predict the GDP growth rate in the next ten years. We test prominent deep learning models and compare their results with traditional econometric models for selected developed and developing countries. Our decadal forecasts reveal that that most of the developed countries would experience economic growth slowdown, stagnation and even recession within five years (2020-2024). Furthermore, our model forecasts show that only China, France, and India would experience stable GDP growth.

Figures (37)

• Figure 1: RNN structure showing information from input $x$ to output $y$ via the state and hidden layers $h$.
• Figure 2: LSTM network with memory cell for handling long-term dependencies.
• Figure 3: BD-LSTM model showing the forward direction LSTM cells $F\ cells$ and backward direction LSTM cells $B\ cells$.
• Figure 4: ED-LSTM architecture showing the Encoder and the Decoder modules.
• Figure 5: Deep learning-based framework for predicting decadal GDP growth rate using the direct and the recursive strategy. The model only predicts the GDP growth rate in the direct strategy using data from 1980-2010, and model testing is done for data from 2011-2019. In the recursive strategy, the model first predicts the features (economic indicators) for the decade ahead (2020-2030), which are then used to predict the decadal GDP growth rate (2020-2030).