Bad news in the Great Depression,the Great Recession,and other U.S. recessions: A comparative study

In economic recessions consumption usually drops in tandem with other aggregate quantities as output or employment. Following the permanent income hypothesis, these drops can be rationalized by the idea that consumers have pessimistic views about their long-run income. Using a standard signal-extraction model, we show that this pessimism can be due either to a persistent fall of aggregate productivity before and during the recession (signaling a future decline of income), or to other negative information unrelated to contemporaneous fundamentals, which we label “bad news”. We classify U.S. recessions (from 1919 to 2015) according to a (bad) news index reflecting this negative information. We find that both the Great Depression and the Great Recession score highest in this index. The index is such that we can rule out that this is due merely to the length or the depth of these recessions. Instead, these two recessions are similar in that both were aggravated by a wave of pessimism about future income which cannot be related to contemporaneous fundamentals.     

The non‐linear dynamics of output and unemployment in the U.S.

This paper studies the joint dynamics of U.S. output and unemployment rate in a non‐linear VAR model. The non‐linearity is introduced through a feedback variable that endogenously augments the output lags of the VAR in recessionary phases. Sufficient conditions for the ergodicity of the model, potentially applying to a larger class of threshold models, are provided. The linear specification is rejected in favour of our threshold VAR. However, in the estimation the feedback is found to be statistically significant only on unemployment, while it transmits to output through its cross‐correlation. This feedback effect from recessions generates important asymmetries in the propagation of shocks, a possible key to interpret the divergence in the measures of persistence in the literature. The regime‐dependent persistence also explains the finding that the feedback from recession exerts a positive effect on the long‐run growth rate of the economy, an empirical validation of the Schumpeterian macroeconomic theories. Copyright © 2001 John Wiley & Sons, Ltd.     

Residential investment and recession predictability

We assess the importance of residential investment for the prediction of economic recessions for an unbalanced panel of 12 OECD countries over the period 1960Q1–2014Q4. Our approach is to estimate various probit models with different leading indicators and evaluate their relative prediction accuracies using the area under the receiver operating characteristic curve as our forecasting performance metric. We document that residential investment contains information that is useful for predicting recessions both in-sample and out-of-sample. This result is robust to adding typical leading indicators, such as the term spread, stock prices, consumer confidence surveys and oil prices. It is shown that residential investment is particularly useful for the prediction of recessions for countries with high home-ownership rates. Finally, in a separate exercise for the US, we show that the predictive ability of residential investment is — in a broad sense — robust to employing real-time data.     

Forecasting U.S. money growth using economic uncertainty measures and regularisation techniques

This paper examines the out-of-sample forecasting properties of six different economic uncertainty variables for the growth of the real M2 and real M4 Divisia money series for the U.S. using monthly data. The core contention is that information on economic uncertainty improves the forecasting accuracy. We estimate vector autoregressive models using the iterated rolling-window forecasting scheme, in combination with modern regularisation techniques from the field of machine learning. Applying the Hansen-Lunde-Nason model confidence set approach under two different loss functions reveals strong evidence that uncertainty variables that are related to financial markets, the state of the macroeconomy or economic policy provide additional informational content when forecasting monetary dynamics. The use of regularisation techniques improves the forecast accuracy substantially.     

J.M.KEYNES: AN EMPEROR WITHOUT CLOTHES (ONE NON-ECONOMIST'S VIEW OF ANOTHER)

Central bank policy causes economic dislocation and recession. Keynes's work assumes away much of what is important in economic analysis. As a result, Keynesian conclusions on how to deal with recessions are wrong.     

Predicting ordinary and severe recessions with a three-state Markov-switching dynamic factor model: An application to the German business cycle

We estimate a Markow-switching dynamic factor model with three states based on six leading business cycle indicators for Germany, preselected from a broader set using the elastic net soft-thresholding rule. The three states represent expansions, normal recessions and severe recessions. We show that a two-state model is not sensitive enough to detect relatively mild recessions reliably when the Great Recession of 2008/2009 is included in the sample. Adding a third state helps to distinguish normal and severe recessions clearly, so that the model identifies all business cycle turning points in our sample reliably. In a real-time exercise, the model detects recessions in a timely manner. Combining the estimated factor and the recession probabilities with a simple GDP forecasting model yields an accurate nowcast for the steepest decline in GDP in 2009Q1, and a correct prediction of the timing of the Great Recession and its recovery one quarter in advance.     

On the real-time predictive content of financial condition indices for growth

We provide evidence on the real-time predictive content of the National Financial Conditions Index (NFCI), for conditional quantiles of U.S. real GDP growth. Our work is distinct from the literature in two specific ways. First, we construct (unofficial) real-time vintages of the NFCI. This allows us to conduct out-of-sample analysis without introducing the kind of look-ahead biases that are naturally introduced when using a single current vintage. We then develop methods for conducting asymptotic inference on tests of equal tick loss between nested quantile regression models when the data are subject to revision. We conclude by evaluating the real-time predictive content of NFCI vintages for quantiles of real GDP growth. While our results largely reinforce the literature, we find gains to using real-time vintages leading up to recessions—precisely when policymakers need such a monitoring device.     

The effect of seasonal adjustment on the properties of business cycle regimes

We study the impact of seasonal adjustment on the properties of business cycle expansion and recession regimes using analytical, simulation and empirical methods. Analytically, we show that the X‐11 adjustment filter both reduces the magnitude of change at turning points and reduces the depth of recessions, with specific effects depending on the length of the recession. A Monte Carlo analysis using Markov‐switching models confirms these properties, with particularly undesirable effects in delaying the recognition of the end of a recession. However, seasonal adjustment can help to clarify the true regime when this is well underway. These results continue to hold when a seasonally non‐stationary process with regime‐dependent mean is misspecified as one with deterministic seasonal effects. The empirical findings, based on four coincident US business cycle indicators, reinforce the analytical and simulation results by showing that seasonal adjustment leads to the identification of longer and shallower recessions than obtained using unadjusted data. Copyright © 2008 John Wiley & Sons, Ltd.     

Global recessions as a cascade phenomenon with interacting agents

This paper examines global recessions as a cascade phenomenon. In other words, how recessions arising within one or more countries might percolate across a network of connected economies. An agent based model is set up in which the agents are Western economies. A country has a probability of entering recession in any given year and one of emerging from it the next. In addition, the agents have a threshold propensity, which varies across time, to import a recession from the agents most closely connected to them. The agents are connected on a network, and an agent’s neighbours at any time are either in (state 1) or out (state 0) of recession. If the weighted sum exceeds the threshold, the agent also goes into recession. Annual real GDP growth for 17 Western countries 1871–2006 is used as the data set. The model is able to replicate three key features of the statistical distribution of recessions: the distribution of the number of countries in recession in any given year, the duration of recessions within the individual countries, and the distribution of ‘wait time’ between recessions i.e. the number of years between them. The network structure is important for the interacting agents to replicate the stylised facts. The country-specific probabilities of entering and emerging from recession by themselves give results which are by no means as well matched to the actual data. We are grateful to an anonymous referee for some extremely helpful comments.     

Bankruptcy Prediction: Evidence from Korean Listed Companies during the IMF Crisis

This paper empirically studies the predictive model of business failure using the sample of listed companies that went bankrupt during the period from 1997 to 1998 when deep recession driven by the IMF crisis started in Korea. Logit maximum likelihood estimator is employed as the statistical technique. The model demonstrated decent prediction accuracy and robustness. The type I accuracy is 80.4 per cent and the Type II accuracy is 73.9 per cent. The accuracy remains almost at the same level when the model is applied to an independent holdout sample. In addition to building a bankruptcy prediction model this paper finds that most of firms that went bankrupt during the Korean economic crisis from 1997 to 1998 had shown signs of financial distress long before the crisis. Bankruptcy probabilities of the sample are consistently high during the period from 1991 to 1996. The evidence of this paper can be seen as complementary to the perspective that traces Asian economic crisis to the vulnerabilities of corporate governance of Asian countries.     

Machine Learning Classification Model Comparison

Machine learning models are boosting Artificial Intelligence applications in many domains, such as automotive, finance and health care. This is mainly due to their advantage, in terms of predictive accuracy, with respect to classic statistical models. However, machine learning models are much less explainable: less transparent, less interpretable. This paper proposes to improve machine learning models, by proposing a model selection methodology, based on Lorenz Zonoids, which allows to compare them in terms of predictive accuracy significant gains, leading to a selected model which maintains accuracy while improving explainability. We illustrate our proposal by means of simulated datasets and of a real credit scoring problem. The analysis of the former shows that the proposal improves alternative methods, based on the AUROC. The analysis of the latter shows that the proposal leads to models made up of two/three relevant variables that measure the profitability and the financial leverage of the companies asking for credit.     

Structural break threshold VARs for predicting US recessions using the spread

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. Copyright © 2006 John Wiley & Sons, Ltd.     

Predicting bank insolvencies using machine learning techniques

Proactively monitoring and assessing the economic health of financial institutions has always been the cornerstone of supervisory authorities. In this work, we employ a series of modeling techniques to predict bank insolvencies on a sample of US-based financial institutions. Our empirical results indicate that the method of Random Forests (RF) has a superior out-of-sample and out-of-time predictive performance, with Neural Networks also performing almost equally well as RF in out-of-time samples. These conclusions are drawn not only by comparison with broadly used bank failure models, such as Logistic, but also by comparison with other advanced machine learning techniques. Furthermore, our results illustrate that in the CAMELS evaluation framework, metrics related to earnings and capital constitute the factors with higher marginal contribution to the prediction of bank failures. Finally, we assess the generalization of our model by providing a case study to a sample of major European banks.     

Deep learning for modeling the collection rate for third-party buyers

This study evaluates a wide range of machine learning techniques such as deep learning, boosting, and support vector regression to predict the collection rate of more than 65,000 defaulted consumer credits from the telecommunications sector that were bought by a German third-party company. Weighted performance measures were defined based on the value of exposure at default for comparing collection rate models. The approach proposed in this paper is useful for a third-party company in managing the risk of a portfolio of defaulted credit that it purchases. The main finding is that one of the machine learning models we investigate, the deep learning model, performs significantly better out-of-sample than all other methods that can be used by an acquirer of defaulted credits based on weighted-performance measures. By using unweighted performance measures, deep learning and boosting perform similarly. Moreover, we find that using a training set with a larger proportion of the dataset does not improve prediction accuracy significantly when deep learning is used. The general conclusion is that deep learning is a potentially performance-enhancing tool for credit risk management.     

Predictive analysis and modelling football results using machine learning approach for English Premier League

The introduction of artificial intelligence has given us the ability to build predictive systems with unprecedented accuracy. Machine learning is being used in virtually all areas in one way or another, due to its extreme effectiveness. One such area where predictive systems have gained a lot of popularity is the prediction of football match results. This paper demonstrates our work on the building of a generalized predictive model for predicting the results of the English Premier League. Using feature engineering and exploratory data analysis, we create a feature set for determining the most important factors for predicting the results of a football match, and consequently create a highly accurate predictive system using machine learning. We demonstrate the strong dependence of our models’ performances on important features. Our best model using gradient boosting achieved a performance of 0.2156 on the ranked probability score (RPS) metric for game weeks 6 to 38 for the English Premier League aggregated over two seasons (2014–2015 and 2015–2016), whereas the betting organizations that we consider (Bet365 and Pinnacle Sports) obtained an RPS value of 0.2012 for the same period. Since a lower RPS value represents a higher predictive accuracy, our model was not able to outperform the bookmaker’s predictions, despite obtaining promising results.     

Towards a real-time prediction of waiting times in emergency departments: A comparative analysis of machine learning techniques

Emergency Departments (EDs) can better manage activities and resources and anticipate overcrowding through accurate estimations of waiting times. However, the complex nature of EDs imposes a challenge on waiting time prediction. In this paper, we test various machine learning techniques, using predictive analytics, applied to two large datasets from real EDs. We evaluate the predictive ability of Lasso, Random Forest, Support Vector Regression, Artificial Neural Network, and the Ensemble Method, using different error metrics and computational times. To improve the prediction accuracy, new queue-based variables, that capture the current state of the ED, are defined as additional predictors. The results show that the Ensemble Method is the most effective at predicting waiting times. In terms of both accuracy and computational efficiency, Random Forest is a reasonable trade-off. The results have significant practical implications for EDs and hospitals, suggesting that a real-time performance monitoring system that supports operational decision-making is possible.     

How to “improve” prediction using behavior modification

Many internet platforms that collect behavioral big data use it to predict user behavior for internal purposes and for their business customers (e.g., advertisers, insurers, security forces, governments, political consulting firms) who utilize the predictions for personalization, targeting, and other decision-making. Improving predictive accuracy is therefore extremely valuable. Data science researchers design algorithms, models, and approaches to improve prediction. Prediction is also improved with larger and richer data. Beyond improving algorithms and data, platforms can stealthily achieve better prediction accuracy by pushing users’ behaviors towards their predicted values, using behavior modification techniques, thereby demonstrating more certain predictions. Such apparent “improved” prediction can result from employing reinforcement learning algorithms that combine prediction and behavior modification. This strategy is absent from the machine learning and statistics literature. Investigating its properties requires integrating causal with predictive notation. To this end, we incorporate Pearl’s causal $do(.)$ operator into the predictive vocabulary. We then decompose the expected prediction error given behavior modification and identify the components impacting predictive power. Our derivation elucidates implications of such behavior modification to data scientists, platforms, their customers, and the humans whose behavior is manipulated. Behavior modification can make users’ behavior more predictable and even more homogeneous; yet this apparent predictability might not generalize when business customers use predictions in practice. Outcomes pushed towards their predictions can be at odds with customers’ intentions, and harmful to manipulated users.     

Why a pandemic recession boosts asset prices

Economic recessions are traditionally associated with asset price declines, and recoveries with asset price booms. Standard asset pricing models make sense of this: during a recession, dividends are low and the marginal value of income is high, causing low asset prices. Here, I develop a simple model which shows that this is not true during a recession caused by consumption restrictions, such as those seen during the 2020 pandemic: the restrictions drive the marginal value of income down, and thereby drive asset prices up, to an extent that tends to overwhelm the effect of low dividends. This result holds even if investors misperceive the economic forces at work.     

Does recession drive convergence in firms’ productivity? Evidence from Spanish manufacturing firms

This paper provides evidence on the effect of recessions and expansions on the productivity growth rate of productivity leaders and followers. We use data of a representative sample of the Spanish manufacturing sector for the period 1991 and 2005. These data allow us to estimate firm level productivity for a relatively long period of time and provide us with firm level perception of the business cycle. We find that productivity tends to converge in recessions because, in these periods, the productivity growth of followers is higher than the productivity growth of leaders. This fact is consistent with theoretical models of managerial incentives and competition. A recession can be seen as an exogenous increase in competition that reduces demand and poses a threat of liquidation. This threat is higher for followers and is high enough to create asymmetric incentives to become more productive. We test the robustness of our results to sample selection and different productivity measure.     

The macroeconomic effects of uncertainty shocks: The role of the financial channel

This paper studies the macroeconomic effects of uncertainty shocks with an emphasis on the interaction between elevated uncertainty and credit market conditions when the economy is in different regimes (recessions vs. non-recessions). We use a smooth-transition factor-augmented vector autoregression (ST-FAVAR) and a large monthly panel of U.S. macroeconomic and financial indicators in our estimation. Our findings are twofold. First, while an unanticipated increase in uncertainty has adverse effects on the real economy and financial markets, the effects are quantitatively larger during recessions. Second, the financial channel is important in the transmission of uncertainty shocks, with a greater role during recessions and in the short run.