Jährlich veröffentlicht das Statistische Bundesamt Statistiken über die Besteuerung von Rentnerinnen und Rentnern, wegen langer Abgabe- und Einspruchsfristen für Einkommensteuererklärungen allerdings erst etwa 3,5 Jahre nach Ablauf des betref- fenden Statistikjahres. Jedoch liegt ein Teil...

This study evaluates näive and advanced prediction models when applied to style rotation strategies on the Johannesburg Stock Exchange ('JSE'). We apply 1- and 3-month style momentum as näive predictors against three tree-based machine learning ('ML') algorithms (advanced predictors),...

This study evaluates naïve and advanced prediction models when applied to style rotation strategies on the Johannesburg Stock Exchange (‘JSE’). We apply 1- and 3-month style momentum as naïve predictors against three tree-based machine learning (‘ML’) algorithms (advanced predictors),...

Jährlich veröffentlicht das Statistische Bundesamt Statistiken über die Besteuerung von Rentnerinnen und Rentnern, wegen langer Abgabe- und Einspruchsfristen für Einkommensteuererklärungen allerdings erst etwa 3,5 Jahre nach Ablauf des betref- fenden Statistikjahres. Jedoch liegt ein Teil...

We develop a novel sentiment measure derived from survey data to empirically vali date the Minsky-Kindleberger view on financial crises. Using survey data from multiple countries, we decompose beliefs into components explained by public information that are orthogonal to optimal machine beliefs,...

Purpose - This study aims to forecast the stock market behavior of BRICS nations (Brazil, Russia, India, China and South Africa) using advanced machine learning models. The focus is on identifying market trends, predicting future index prices and analyzing returns. Design/methodology/approach -...

The Financial Lobster Bias describes how SMEs, driven by distorted liquidity perceptions, engage in aggressive expansion until financial breakdown occurs. Using data from 10,412 Spanish SMEs (2000-2024), this study shows that liquidity misperception-measured through two versions of the Liquidity...

Theories of limited attention predict that investors rely on typical patterns to navigate high-dimensional firm characteristics, making atypical firms hard to process. To quantify this difficulty, we propose a data-driven measure of firm atypicality using an autoencoder (ATYP). The model learns...

The magnitude and scope of the application of artificial intelligence (AI) and information-based computing methods to green and sustainable power generation systems have been significantly expanded to include research, initial development, implementation, and deployment. Over the past five...

We present improved out-of-sample predictability of future fund flows using state-of-the-art machine learning methods. Nonlinear machine learning models significantly outperform linear models in terms of out-of-sample R-squared. Using interpretable ML methods, we identify past flows and the...

We consider parametric portfolio policies of any complexity using deep neural networks to optimize investor utility. Risk aversion acts as an economic regularization mechanism, with higher risk aversion constraining model complexity. Empirically, Deep Parametric Portfolio Policies (DPPP)...

This paper explores the application of machine learning (ML) techniques to nowcast the monthly year-over-year growth rate of both total and non-primary GDP in Peru. Using a comprehensive dataset that includes over 170 domestic and international predictors, we assess the predictive performance of...

Die Nutzung von Scannerdaten in der Verbraucherpreisstatistik hat viele Vorteile, bringt allerdings auch einige Herausforderungen mit sich. Eine der Herausforderungen ist die Klassifizierung der Artikel nach dem vom Verbraucherpreisindex verwendeten Klassifikationssystem COICOP. Aufgrund der...

Auch die amtliche Statistik nutzt Methoden der Künstlichen Intelligenz (KI) und ihres Teilbereichs Maschinelles Lernen (ML). Dies wirft verschiedene ethische Fragestellungen auf, die im ersten Teil des Artikels ("Identifikation") mithilfe von Vorarbeiten aus anderen Staaten und von...

Künstliche Intelligenz (KI) hat mit ihrem Teilgebiet Maschinelles Lernen (ML) Einzug gehalten in die Verwaltung im Allgemeinen sowie in die amtliche Statistik in Deutschland im Speziellen. Welche ethischen Fragen sind jedoch beim Einsatz von KI/ML in der Produktion amtlicher Statistiken zu...

Inequality is a dynamic phenomenon, and the relative and absolute positions of individuals are subject to frequent shocks. It is important to know if preventive interventions mitigate adverse inequality effects of labor market shocks. We consider individuals up to three months before the...

We study how the effects of exports on earnings vary across individual workers, depending on a wide range of worker, firm, and job characteristics. To this end, we combine a generalized random forest with an instrumental variable strategy. Analyzing Germany's exports to China and Eastern Europe,...

We examine predictive machine learning studies from 50 top business and economic journals published between 2010 and 2023. We investigate their transparency regarding the predictive performance of machine learning models compared to less complex traditional statistical models that require fewer...

Können Methoden der Künstlichen Intelligenz helfen, Baustellenaktivitäten in Nordrhein-Westfalen zu erfassen und somit mehr Informationen über das dortige Baugeschehen zu erhalten? Der Artikel untersucht ob es möglich ist, einen Datensatz zu erstellen, um einen Algorithmus zu trainieren,...

In this study, the authors propose an advanced strategy to analyze thermal images for breast cancer detection employing machine learning techniques. By focusing on critical features that capture geometric and structural information in thermal images, the aim is to elevate the precision and...

Accurate macroeconomic forecasts are essential for effective policy decisions, yet their precision depends on the accuracy of the underlying assumptions. This paper examines the extent to which assumption errors affect forecast accuracy, introducing the average squared assumption error (ASAE) as...

We introduce a novel, non-parametric approach for estimating house price indices that capture heterogeneous price developments independently of strict functional form assumptions. Utilizing the potential outcomes framework, our approach employs causal forests to effectively address changes in...

This study presents an exploratory analysis of the key factors contributing to fatal and severe crashes on German motorways. We employ Poisson and Negative Binomial regression models, combined with Lasso regularization and stability selection, to explore model specifications incorporating...

Im Projekt t+20 des Statistischen Bundesamtes wurden Methoden untersucht, um Konjunkturindikatoren für das Verarbeitende Gewerbe beschleunigt bereitzustellen. Der Einsatz mikrodatenbasierter Modelle, darunter Imputationsmethoden und Maschinelles Lernen, sowie eines makrodatenbasierten...

Sustainability has become a crucial factor in the financial sector, making the assessment of a company's sustainability performance essential for informed decision-making. Recognizing the media's power to shape public perception of corporate sustainability issues, this study examines the use of...

In sub-Saharan Africa, child fostering-a widespread practice in which a child moves out of the household of her biological parents-can have significant implications for a child's overall well-being. Using longitudinal data from South Africa that includes individual tracking, we employ double...

This research examines the proposition that enhancing sustainable innovation can be particularly effective when the focus is on strategy, machine learning, and digitalization. The study specifically targets the complex interactions among strategic alignment (SA), sustainability-oriented...

For many economic questions, the empirical results are not interesting unless they are strong. For these questions, theorizing before the results are known is not always optimal. Instead, the optimal sequencing of theory and empirics trades off a "Darwinian Learning" effect from theorizing first...

Accounting fraud poses significant financial and reputational risks for organizations. Traditional detection methods - such as manual audits and red-flag indicators - struggle to keep pace with the growing volume and complexity of financial data. In contrast, artificial intelligence...

We propose a novel empirical structural inflation model that captures non-linear shock transmission using a Bayesian machine learning framework that combines VARs with non-linear structural factor models. Unlike traditional linear models, our approach allows for non-linear effects at all impulse...

The exchange of information is an essential means for being able to conduct negotiations and to derive situational decisions. In electronic negotiations, information is transferred in the form of requests, offers, questions and clarifications consisting of communication and decisions. Taken...

Based on the work by Buettner (2017) showing a personality-based recommender system for electronic markets using social media data, we extend the work by proposing a novel deep learning-based engine to predict the user’s personality just based on electroencephalographic brain data. As...

Artificial intelligence (AI) systems create value but can pose substantial risks, particularly due to their black-box nature and potential bias towards certain individuals. In response, recent legal initiatives require organizations to ensure their AI systems conform to overarching principles...

In this study, we examine the Federal Reserve's communication strategies during the COVID-19 pandemic, comparing them with communication during previous periods of economic stress. Using specialized dictionaries tailored to COVID-19, unconventional monetary policy (UMP), and financial stability,...

We predict earnings for forecast horizons of up to five years by using the entire set of Compustat financial statement data as input and providing it to state-of-the-art machine learning models capable of approximating arbitrary functional forms. Our approach improves prediction one year ahead...

Agricultural and environmental economists are in the fortunate position that a lot of what is happening on the ground is observable from space. Most agricultural production happens in the open and one can see from space when and where innovations are adopted, crop yields change, or forests are...

En este estudio, se aborda el desaliento laboral en México desde una perspectiva de modelación matemática. Se consideran dos condiciones de empleabilidad: desocupado y desalentado, y se caracteriza la clasificación de estos grupos utilizando modelos de aprendizaje automático y variables...

This paper examines the prediction of IPO withdrawal using machine learning methods (lasso and random forest) and conventional regression (logit). The dataset comprises 2444 US first‐time IPOs from 1997 to 2014. Results show that random forest outperforms both logit and lasso in in‐sample...