Forecasting Four Business Cycle Phases Using Machine Learning - A Case Study of US and EuroZone

Aug 3, 2026

Upload by Liam

Understanding the business cycle is essential for enhancing economic stability, shaping business planning, and informing investment decisions amid recurring expansion and contraction patterns. Economic analysis remains difficult because numerous intertwined factors—macroeconomic indicators, political choices, and global events—affect the economy’s current state and future direction. This study evaluates three machine learning approaches to classify four phases: expansion, slowdown, recession, and recovery in the United States and EuroZone, with Multinomial Logistic Regression delivering the strongest results.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages9

Reading Time23 min

AccessFree to download

Introduction

Business cycle phases used in this study

Challenges of forecasting the business cycle

Institutional definitions and prior modeling approaches

arXiv :2405 . 17170v2 [ cs .LG] 14 Jun 2024 Forecasting Four Business Cycle Phases Using Machine Learning: A Case Study of US and EuroZone Elvys Linhares Pontes, Mohamed Benjannet, and Raymond Yung Trading Central Labs, Trading Central, Paris, France {elvys.linharespontes,[mohamed.benjannet}@tradingcentral.com](mohamed.benjannet}@tradingcentral.com) Abstract Understanding the business cycle is crucial for building economic stability, guiding business planning, and informing investment decisions. The business cycle refers to the recurring pattern of expansion and contraction in economic activity over time. Economic analysis is inherently complex, incorporating a myriad of factors (such as macroeconomic indicators, political decisions) . This complexity makes it challenging to fully account for all variables when determining the current state of the economy and predicting its future trajectory in the upcoming months. The objective of this study is to investigate the capacity of machine learning models in automatically analyzing the state of the economic, with the goal of forecasting business phases (expansion, slowdown, recession and recovery) in the United States and the EuroZone. We compared three different machine learning approaches to classify the phases of the business cycle, and among them, the Multinomial Logistic Regression (MLR) achieved the best results. Specifically, MLR got the best results by achieving the accuracy of 65.25%(Top1) and 84.74%(Top2) for the EuroZone and 75%(Top1) and 92 . 14%(Top2) for the United States. These results demonstrate the potential of machine learning techniques to predict business cycles accurately, which can aid in making informed decisions in the fields of economics and finance. Keywords: Business cycle classification, Machine learning, Macroeconomics 1. Introduction The economy is a multifaceted and dynamic system characterized by complexity, uncertainty, and interdependence. Understanding the economy requires delving into a complex web of interconnected systems, behaviors, and variables that influence the production, distribution, and consumption of goods and services within a society or across the globe. Business cycles represent fluctuations in the overall economic activity of a country. These cycles involve periods of expansion, where economic activities across various sectors simultaneously grow, followed by periods of contraction, where economic activities similarly decline1 . The study and prediction of the business cycle is crucial for promoting economic stability, guiding business planning, and informing investment decisions. By understanding the various phases of the business cycle, policymakers can design effective policies to stabilize the economy during downturns. Similarly, investors and businesses can use this knowledge to make decisions about where to allocate capital and how to adjust their strategies. A business cycle is characterized by fluctuations in Gross Domestic Product (GDP) around its longterm natural growth rate, elucidating the alternating phases of expansion and contraction in economic activity that an economy undergoes overtime. The delineation of these phases in the business cycle framework lacks global consensus, with 1 [https://www.investopedia.com/terms/b/](https://www.investopedia.com/terms/b/)[ ](https://www.investopedia.com/terms/b/)businesscycle .asp varying perspectives proposing two, four2 , or six phases3 . In this study, we have chosen to adopt a business cycle model consisting of four phases: expansion, slowdown, recession, and recovery. Expansion is characterised by an economic growth and an increasing in output, employment, and income. Slowdown is the phase following expansion where economic activity start to decline. Recession is characterised by declining economic activity, decreasing output, employment, and income. Finally, recovery is the end of recession phase and the beginning of economic recovery with incr

FAQs

What four business cycle phases does this study aim to forecast?

The study uses a four-phase model: expansion, slowdown, recession, and recovery.

Why is forecasting the business cycle considered challenging?

Business cycles are theoretical models influenced by many interacting variables, making it difficult to account for all factors when estimating the economy’s current state and predicting its future trajectory.

Which machine learning method performs best in classifying phases, and how is its performance reported?

Multinomial Logistic Regression (MLR) achieves the best results, reporting accuracy of 65.25% (Top1) and 84.74% (Top2) for the EuroZone, and 75% (Top1) and 92.14% (Top2) for the United States.

Aug 3, 2026

Upload by Liam