By April 2026, it is projected that there is a probability of ***** percent that the United States will fall into another economic recession. This reflects a significant decrease from the projection of the preceding month.

United States Recession Probability data was reported at 14.120 % in Oct 2019. This records a decrease from the previous number of 14.505 % for Sep 2019. United States Recession Probability data is updated monthly, averaging 7.668 % from Jan 1960 (Median) to Oct 2019, with 718 observations. The data reached an all-time high of 95.405 % in Dec 1981 and a record low of 0.080 % in Sep 1983. United States Recession Probability data remains active status in CEIC and is reported by Federal Reserve Bank of New York. The data is categorized under Global Database’s United States – Table US.S021: Recession Probability.

The Long Depression was, by a large margin, the longest-lasting recession in U.S. history. It began in the U.S. with the Panic of 1873, and lasted for over five years. This depression was the largest in a series of recessions at the turn of the 20th century, which proved to be a period of overall stagnation as the U.S. financial markets failed to keep pace with industrialization and changes in monetary policy. Great Depression The Great Depression, however, is widely considered to have been the most severe recession in U.S. history. Following the Wall Street Crash in 1929, the country's economy collapsed, wages fell and a quarter of the workforce was unemployed. It would take almost four years for recovery to begin. Additionally, U.S. expansion and integration in international markets allowed the depression to become a global event, which became a major catalyst in the build up to the Second World War. Decreasing severity When comparing recessions before and after the Great Depression, they have generally become shorter and less frequent over time. Only three recessions in the latter period have lasted more than one year. Additionally, while there were 12 recessions between 1880 and 1920, there were only six recessions between 1980 and 2020. The most severe recession in recent years was the financial crisis of 2007 (known as the Great Recession), where irresponsible lending policies and lack of government regulation allowed for a property bubble to develop and become detached from the economy over time, this eventually became untenable and the bubble burst. Although the causes of both the Great Depression and Great Recession were similar in many aspects, economists have been able to use historical evidence to try and predict, prevent, or limit the impact of future recessions.

While conditional forecasting has become prevalent both in the academic literature and in practice (e.g., bank stress testing, scenario forecasting), its applications typically focus on continuous variables. In this article, we merge elements from the literature on the construction and implementation of conditional forecasts with the literature on forecasting binary variables. We use the Qual-VAR, whose joint VAR-probit structure allows us to form conditional forecasts of the latent variable which can then be used to form probabilistic forecasts of the binary variable. We apply the model to forecasting recessions in real-time and investigate the role of monetary and oil shocks on the likelihood of two U.S. recessions.

Milton Friedman’s plucking model of business cycles hypothesizes that deeper recessions forecast larger booms while stronger booms do not necessarily forecast deeper recessions. This paper tests the plucking model using Maddison Project growth data for 169 countries across several centuries. We find 56.9% of the per capita GDP growth magnitude in the last year of a downturn forecasts the per capita GDP growth magnitude of the subsequent first recovery year while only 16.2% of the last boom year per capita GDP growth magnitude forecasts the per capita GDP growth magnitude of the first year in the subsequent downturn, suggesting that the plucking model holds up relatively well. Combining our finding that first post-recession boom year per capita GDP growth rate is typically is 0.7% higher than later boom years suggests that recoveries generally exhibit “reverse square root” shapes.

Probability of Recession: United States data was reported at 0.995 % in Mar 2025. This records a decrease from the previous number of 1.031 % for Feb 2025. Probability of Recession: United States data is updated monthly, averaging 1.564 % from Jan 1980 (Median) to Mar 2025, with 543 observations. The data reached an all-time high of 87.972 % in May 2020 and a record low of 0.021 % in Jan 1980. Probability of Recession: United States data remains active status in CEIC and is reported by CEIC Data. The data is categorized under World Trend Plus’s CEIC Leading Indicator – Table US.S002: Probability of Recession.

United States Recession Prob: Yield Curve: 3 Month Treasury Yield data was reported at 2.250 % in Oct 2018. This records an increase from the previous number of 2.130 % for Sep 2018. United States Recession Prob: Yield Curve: 3 Month Treasury Yield data is updated monthly, averaging 4.620 % from Jan 1959 (Median) to Oct 2018, with 718 observations. The data reached an all-time high of 16.300 % in May 1981 and a record low of 0.010 % in Dec 2011. United States Recession Prob: Yield Curve: 3 Month Treasury Yield data remains active status in CEIC and is reported by Federal Reserve Bank of New York. The data is categorized under Global Database’s United States – Table US.S021: Recession Probability.

This analysis presents a rigorous exploration of financial data, incorporating a diverse range of statistical features. By providing a robust foundation, it facilitates advanced research and innovative modeling techniques within the field of finance.

LON:ETX Stock: Are We Headed for a Recession?

Financial data:

• Historical daily stock prices (open, high, low, close, volume)

• Fundamental data (e.g., market capitalization, price to earnings P/E ratio, dividend yield, earnings per share EPS, price to earnings growth, debt-to-equity ratio, price-to-book ratio, current ratio, free cash flow, projected earnings growth, return on equity, dividend payout ratio, price to sales ratio, credit rating)

• Technical indicators (e.g., moving averages, RSI, MACD, average directional index, aroon oscillator, stochastic oscillator, on-balance volume, accumulation/distribution A/D line, parabolic SAR indicator, bollinger bands indicators, fibonacci, williams percent range, commodity channel index)

Machine learning features:

• Feature engineering based on financial data and technical indicators

• Sentiment analysis data from social media and news articles

• Macroeconomic data (e.g., GDP, unemployment rate, interest rates, consumer spending, building permits, consumer confidence, inflation, producer price index, money supply, home sales, retail sales, bond yields)

Potential Applications:

• Stock price prediction

• Portfolio optimization

• Algorithmic trading

• Market sentiment analysis

• Risk management

Use Cases:

• Researchers investigating the effectiveness of machine learning in stock market prediction

• Analysts developing quantitative trading Buy/Sell strategies

• Individuals interested in building their own stock market prediction models

• Students learning about machine learning and financial applications

Additional Notes:

• The dataset may include different levels of granularity (e.g., daily, hourly)

• Data cleaning and preprocessing are essential before model training

• Regular updates are recommended to maintain the accuracy and relevance of the data

United States NBER: Recorded Recession data was reported at 0.000 Unit in Oct 2018. This stayed constant from the previous number of 0.000 Unit for Sep 2018. United States NBER: Recorded Recession data is updated monthly, averaging 0.000 Unit from Jan 1959 (Median) to Oct 2018, with 718 observations. The data reached an all-time high of 1.000 Unit in Jun 2009 and a record low of 0.000 Unit in Oct 2018. United States NBER: Recorded Recession data remains active status in CEIC and is reported by Federal Reserve Bank of New York. The data is categorized under Global Database’s United States – Table US.S021: Recession Probability. An interpretation of US Business Cycle Expansions and Contractions data provided by The National Bureau of Economic Research (NBER). A value of 1 is a recessionary period, while a value of 0 is an expansionary period.

Graph and download economic data for Real-time Sahm Rule Recession Indicator (SAHMREALTIME) from Dec 1959 to Jun 2025 about recession indicators, academic data, and USA.

United States NBER-Based Recession Indicators from the Peak Through the Trough data was reported at 0.000 Unit in 14 May 2025. This stayed constant from the previous number of 0.000 Unit for 13 May 2025. United States NBER-Based Recession Indicators from the Peak Through the Trough data is updated daily, averaging 0.000 Unit from Dec 1854 (Median) to 14 May 2025, with 62256 observations. The data reached an all-time high of 1.000 Unit in 15 Apr 2020 and a record low of 0.000 Unit in 14 May 2025. United States NBER-Based Recession Indicators from the Peak Through the Trough data remains active status in CEIC and is reported by Federal Reserve Bank of St. Louis. The data is categorized under Global Database’s United States – Table US.S: NBER-Based Recession Indicators.

This paper proposes a model to predict recessions that accounts for non-linearity and a structural break when the spread between long- and short-term interest rates is the leading indicator. Estimation and model selection procedures allow us to estimate and identify time-varying non-linearity in a VAR. The structural break threshold VAR (SBTVAR) predicts better the timing of recessions than models with constant threshold or with only a break. Using real-time data, the SBTVAR with spread as leading indicator is able to anticipate correctly the timing of the 2001 recession.

Inspired by:

Modeling and predicting U.S. recessions using machine learning techniques

As variáveis do FRED-MD como preditivas e a USREC como alvo (período de 1979-2019)

Diversos Modelos: probit, logit, LDA, árvores Naive-Bayes Algumas variáveis tiveram que ser transformadas em mensais (interpolação cúbica)

128 varibles. Grupos: Output and Income Labor Market Consumption and Orders Orders and Inventories Money and Credit Interest Rates and Exchange Rates Prices Stock Market

According to Cognitive Market Research, the global AI Sensor Market with Recession Market size is USD 2.8 billion in 2024 and will expand at a compound annual growth rate (CAGR) of 38.6% from 2024 to 2031. Market Dynamics of AI Sensor Market with Recession Market

Key Drivers for AI Sensor Market with Recession Market

Advancements in AI and Machine Learning: Rapid advances in artificial intelligence and machine learning are boosting the use of Al sensors. Algorithms are getting increasingly sophisticated and capable of handling complicated data from sensors, enabling real-time decision-making and predictive analytics. These developments allow Al sensors to detect patterns, anomalies, and trends in data streams, making them useful in applications such as picture recognition, natural language processing, and predictive maintenance. For instance, in manufacturing, Al sensors may detect faults in real time, improving quality control and lowering waste. Al sensors also improve the capability of autonomous systems and robots. They can perceive their surroundings, adjust to changing circumstances, and make sound decisions. This is especially crucial in industries like agriculture, where autonomous drones equipped with Al sensors can check crop health, detect pest infestations, and optimize pesticide use. Security and Surveillance applications

Key Restraints for AI Sensor Market with Recession Market

Capital Spending Delays in Price-Sensitive Sectors: Businesses in a variety of sectors, including retail, consumer electronics, and the automobile industry, frequently postpone or abandon capital-intensive initiatives and technological advancements during recessions. This has a direct impact on the use of AI sensors in consumer electronics, smart factories, and new goods, momentarily reducing market expansion.

Semiconductor shortages and supply chain disruptions: Complex semiconductor components are necessary for AI sensors, and supply chain bottlenecks are frequently made worse by global economic downturns. Delays in shipping, reduced manufacturing capacity, and geopolitical unrest can all affect sensor production and lengthen lead times, making it more difficult for industries to deploy sensors on time.

Key Trends for AI Sensor Market with Recession Market

Transition to Low-Cost Advanced AI Sensors: Industries are turning to edge AI sensors that analyze data locally in order to deal with financial restrictions. This eliminates the need for expensive cloud infrastructure and latency problems. Due to their simplicity of deployment and reduced total cost of ownership, small, energy-efficient sensors with on-chip AI are becoming more and more popular. Growing Utilization in Energy Efficiency and Predictive Maintenance: Operational efficiency is a top priority for financially stressed organizations, and AI sensors are essential for energy optimization and predictive maintenance. Industrial equipment with sensors built in can anticipate malfunctions, prolong the life of machinery, and use less electricity, all of which can result in quantifiable cost savings during recessions. Introduction of the AI Sensor Market with Recession Market

Al sensors are also improving the capabilities of autonomous systems and robots. They can perceive their surroundings, adjust to changing conditions, and make sound decisions. This is especially crucial in industries like agriculture, where autonomous drones equipped with Al sensors can check crop health, detect pest infestations, and optimize pesticide use. Also, increased demand for life-saving healthcare equipment and self-driving capabilities in new electric vehicles are expected to fuel growth. The global shift towards digitization is expected to boost growth even further.

This analysis presents a rigorous exploration of financial data, incorporating a diverse range of statistical features. By providing a robust foundation, it facilitates advanced research and innovative modeling techniques within the field of finance.

DTRTU Stock: Are We Headed for a Recession?

Financial data:

• Historical daily stock prices (open, high, low, close, volume)

• Fundamental data (e.g., market capitalization, price to earnings P/E ratio, dividend yield, earnings per share EPS, price to earnings growth, debt-to-equity ratio, price-to-book ratio, current ratio, free cash flow, projected earnings growth, return on equity, dividend payout ratio, price to sales ratio, credit rating)

• Technical indicators (e.g., moving averages, RSI, MACD, average directional index, aroon oscillator, stochastic oscillator, on-balance volume, accumulation/distribution A/D line, parabolic SAR indicator, bollinger bands indicators, fibonacci, williams percent range, commodity channel index)

Machine learning features:

• Feature engineering based on financial data and technical indicators

• Sentiment analysis data from social media and news articles

• Macroeconomic data (e.g., GDP, unemployment rate, interest rates, consumer spending, building permits, consumer confidence, inflation, producer price index, money supply, home sales, retail sales, bond yields)

Potential Applications:

• Stock price prediction

• Portfolio optimization

• Algorithmic trading

• Market sentiment analysis

• Risk management

Use Cases:

• Researchers investigating the effectiveness of machine learning in stock market prediction

• Analysts developing quantitative trading Buy/Sell strategies

• Individuals interested in building their own stock market prediction models

• Students learning about machine learning and financial applications

Additional Notes:

• The dataset may include different levels of granularity (e.g., daily, hourly)

• Data cleaning and preprocessing are essential before model training

• Regular updates are recommended to maintain the accuracy and relevance of the data

This repository hosts the supplementary materials associated with the paper:
> Delforge, D., Muñoz-Carpena, R., Van Camp, M. Vanclooster, M. (2020), A parsimonious empirical approach to streamflow recession analysis and forecasting (accepted at Water Resources Research - 29-01-2020).

This data set contains streamflow and recession data, a python code file and a Jupyter notebook illustrating how to apply the EDM-Simplex method to forecast the recession, and the outputs of the global sensitivity analysis. All files are documented in the readme.md Markdown files.

Streamflow data were obtained from the Aqualim portal (http://aqualim.environnement.wallonie.be/) of the "Service Public de Wallonie" and shared with their kind permission. This work is part of a Ph.D. supported by a FRIA grant from the Fund for Scientific Research (FSR-FNRS, Belgium). The authors acknowledge University of Florida Research Computing for providing computational resources and support that have contributed to the research results stored in this repository. URL: http://researchcomputing.ufl.edu.

United States FRB Recession Risk data was reported at 0.178 % in Apr 2025. This records a decrease from the previous number of 0.192 % for Mar 2025. United States FRB Recession Risk data is updated monthly, averaging 0.193 % from Jan 1973 (Median) to Apr 2025, with 628 observations. The data reached an all-time high of 1.000 % in Oct 2008 and a record low of 0.022 % in Jul 2003. United States FRB Recession Risk data remains active status in CEIC and is reported by Federal Reserve Board. The data is categorized under Global Database’s United States – Table US.S090: FRB Recession Risk.

This analysis presents a rigorous exploration of financial data, incorporating a diverse range of statistical features. By providing a robust foundation, it facilitates advanced research and innovative modeling techniques within the field of finance.

TA:TSX Stock: Are We Headed for a Recession?

Financial data:

• Historical daily stock prices (open, high, low, close, volume)

• Fundamental data (e.g., market capitalization, price to earnings P/E ratio, dividend yield, earnings per share EPS, price to earnings growth, debt-to-equity ratio, price-to-book ratio, current ratio, free cash flow, projected earnings growth, return on equity, dividend payout ratio, price to sales ratio, credit rating)

• Technical indicators (e.g., moving averages, RSI, MACD, average directional index, aroon oscillator, stochastic oscillator, on-balance volume, accumulation/distribution A/D line, parabolic SAR indicator, bollinger bands indicators, fibonacci, williams percent range, commodity channel index)

Machine learning features:

• Feature engineering based on financial data and technical indicators

• Sentiment analysis data from social media and news articles

• Macroeconomic data (e.g., GDP, unemployment rate, interest rates, consumer spending, building permits, consumer confidence, inflation, producer price index, money supply, home sales, retail sales, bond yields)

Potential Applications:

• Stock price prediction

• Portfolio optimization

• Algorithmic trading

• Market sentiment analysis

• Risk management

Use Cases:

• Researchers investigating the effectiveness of machine learning in stock market prediction

• Analysts developing quantitative trading Buy/Sell strategies

• Individuals interested in building their own stock market prediction models

• Students learning about machine learning and financial applications

Additional Notes:

• The dataset may include different levels of granularity (e.g., daily, hourly)

• Data cleaning and preprocessing are essential before model training

• Regular updates are recommended to maintain the accuracy and relevance of the data

Details of the Data and Code for this paper are in readme_cv.pdf.

Abstract Rudebusch and Williams (2009, RW) predict recessions in the United States utilising a probit model with the lagged yield spread as a real-time predictor. Mindful of the importance of recent yield curve movements, we update their analysis and evaluate quarterly forecasts from their probit model up to the end of 2023. We also analyse lagged financial conditions as an alternative real-time predictor. We find that both the yield spread and financial conditions perform relatively well at the longer horizons considered by the experts in the Survey of Professional Forecasters.

This paper analyzes the performance of the monthly economic policy uncertainty (EPU) index in predicting recessionary regimes of the (quarterly) U.S. GDP. In this regard, the authors apply a mixed-frequency Markov-switching vector autoregressive (MF-MSVAR) model, and compare its in-sample and out-of-sample forecasting performances to those of a Markov-switching vector autoregressive model (MS-VAR, where the EPU is averaged over the months to produce quarterly values) and a Markov-switching autoregressive (MS-AR) model. The results show that the MF-MS-VAR fits the different recession regimes, and provides out-of-sample forecasts of recession probabilities which are more accurate than those derived from the MS-VAR and MS-AR models. The results highlight the importance of using high-frequency values of the EPU, and not averaging them to obtain quarterly values, when forecasting recessionary regimes for the U.S. economy.