|
on Big Data |
| By: | Leib, Margarita (Tilburg University); Köbis, Nils (Max Planck Institute for Human Development); Rilke, Rainer Michael (WHU Vallendar); Hagens, Marloes (Erasmus University Rotterdam); Irlenbusch, Bernd (University of Cologne) |
| Abstract: | Artificial Intelligence (AI) increasingly becomes an indispensable advisor. New ethical concerns arise if AI persuades people to behave dishonestly. In an experiment, we study how AI advice (generated by a Natural-Language-processing algorithm) affects (dis)honesty, compare it to equivalent human advice, and test whether transparency about advice source matters. We find that dishonesty-promoting advice increases dishonesty, whereas honesty-promoting advice does not increase honesty. This is the case for both AI and human advice. Algorithmic transparency, a commonly proposed policy to mitigate AI risks, does not affect behaviour. The findings mark the first steps towards managing AI advice responsibly. |
| Keywords: | Artificial Intelligence, machine behaviour, behavioural ethics, advice |
| JEL: | C91 D90 D91 |
| Date: | 2023–07 |
| URL: | http://d.repec.org/n?u=RePEc:iza:izadps:dp16293&r=big |
| By: | Aspremont Alexandre; Ben Arous Simon; Bricongne Jean-Charles; Lietti Benjamin; Meunier Baptiste |
| Abstract: | The Covid crisis has demonstrated the need for alternative data, in real-time and with global coverage. This paper exploits daily infrared images from satellites to track economic activity in advanced and emerging countries. We first develop a framework to read, clean and exploit satellite images. We construct an algorithm based on the laws of physics and machine learning to detect the heat produced by cement plants in activity. This allows to monitor in real-time if a cement plant is functioning. Using this information on more than 500 plants, we construct a satellite-based index tracking activity. Using this satellite index outperforms benchmark models and alternative indicators for nowcasting the activity in the cement industry and in the construction sector. Exploring the granularity of daily and plant-level data, using neural networks yields significantly more accurate predictions. Overall, combining satellite images and machine learning allows to track industrial activity accurately. |
| Keywords: | Data Science, Big Data, Satellite Data, Machine Learning, Nowcasting, Cement, Construction, Industry, Economic Activity, Neural Network |
| JEL: | C51 C81 E23 E37 |
| Date: | 2023 |
| URL: | http://d.repec.org/n?u=RePEc:bfr:banfra:916&r=big |
| By: | Menzie D. Chinn; Baptiste Meunier; Sebastian Stumpner |
| Abstract: | We nowcast world trade using machine learning, distinguishing between tree-based methods (random forest, gradient boosting) and their regression-based counterparts (macroeconomic random forest, gradient linear boosting). While much less used in the literature, the latter are found to outperform not only the tree-based techniques, but also more “traditional” linear and non-linear techniques (OLS, Markov-switching, quantile regression). They do so significantly and consistently across different horizons and real-time datasets. To further improve performances when forecasting with machine learning, we propose a flexible three-step approach composed of (step 1) pre-selection, (step 2) factor extraction and (step 3) machine learning regression. We find that both pre-selection and factor extraction significantly improve the accuracy of machine-learning-based predictions. This three-step approach also outperforms workhorse benchmarks, such as a PCA-OLS model, an elastic net, or a dynamic factor model. Finally, on top of high accuracy, the approach is flexible and can be extended seamlessly beyond world trade. |
| JEL: | C53 C57 E37 |
| Date: | 2023–06 |
| URL: | http://d.repec.org/n?u=RePEc:nbr:nberwo:31419&r=big |
| By: | Sohum Thakkar (QC Ware Corp); Skander Kazdaghli (QC Ware Corp); Natansh Mathur (QC Ware Corp; IRIF - Universit\'e Paris Cit\'e and CNRS); Iordanis Kerenidis (QC Ware Corp; IRIF - Universit\'e Paris Cit\'e and CNRS); Andr\'e J. Ferreira-Martins (Ita\'u Unibanco); Samurai Brito (Ita\'u Unibanco) |
| Abstract: | Quantum algorithms have the potential to enhance machine learning across a variety of domains and applications. In this work, we show how quantum machine learning can be used to improve financial forecasting. First, we use classical and quantum Determinantal Point Processes to enhance Random Forest models for churn prediction, improving precision by almost 6%. Second, we design quantum neural network architectures with orthogonal and compound layers for credit risk assessment, which match classical performance with significantly fewer parameters. Our results demonstrate that leveraging quantum ideas can effectively enhance the performance of machine learning, both today as quantum-inspired classical ML solutions, and even more in the future, with the advent of better quantum hardware. |
| Date: | 2023–05 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2306.12965&r=big |
| By: | Chinn Menzie; Meunier Baptiste; Stumpner Sebastian |
| Abstract: | We nowcast world trade using machine learning, distinguishing between tree-based methods (random forest, gradient boosting) and their regression-based counterparts (macroeconomic random forest, linear gradient boosting). While much less used in the literature, the latter are found to outperform not only the tree-based techniques, but also more “traditional” linear and non-linear techniques (OLS, Markov-switching, quantile regression). They do so significantly and consistently across different horizons and real-time datasets. To further improve performance when forecasting with machine learning, we propose a flexible three-step approach composed of (step 1) pre-selection, (step 2) factor extraction and (step 3) machine learning regression. We find that both pre-selection and factor extraction significantly improve the accuracy of machine-learning-based predictions. This three-step approach also outperforms workhorse benchmarks, such as a PCA-OLS model, an elastic net, or a dynamic factor model. Finally, on top of high accuracy, the approach is flexible and can be extended seamlessly beyond world trade. |
| Keywords: | Forecasting, Big Data, Large Dataset, Factor Model, Pre-Selection |
| JEL: | C53 C55 E37 |
| Date: | 2023 |
| URL: | http://d.repec.org/n?u=RePEc:bfr:banfra:917&r=big |
| By: | Georgios Palaiokrassas; Sandro Scherrers; Iason Ofeidis; Leandros Tassiulas |
| Abstract: | Since the inception of permissionless blockchains with Bitcoin in 2008, it became apparent that their most well-suited use case is related to making the financial system and its advantages available to everyone seamlessly without depending on any trusted intermediaries. Smart contracts across chains provide an ecosystem of decentralized finance (DeFi), where users can interact with lending pools, Automated Market Maker (AMM) exchanges, stablecoins, derivatives, etc. with a cumulative locked value which had exceeded 160B USD. While DeFi comes with high rewards, it also carries plenty of risks. Many financial crimes have occurred over the years making the early detection of malicious activity an issue of high priority. The proposed framework introduces an effective method for extracting a set of features from different chains, including the largest one, Ethereum and it is evaluated over an extensive dataset we gathered with the transactions of the most widely used DeFi protocols (23 in total, including Aave, Compound, Curve, Lido, and Yearn) based on a novel dataset in collaboration with Covalent. Different Machine Learning methods were employed, such as XGBoost and a Neural Network for identifying fraud accounts detection interacting with DeFi and we demonstrate that the introduction of novel DeFi-related features, significantly improves the evaluation results, where Accuracy, Precision, Recall, F1-score and F2-score where utilized. |
| Date: | 2023–05 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2306.07972&r=big |
| By: | Christophe Carugati |
| Abstract: | This working paper examines how competition in foundation models (FMs) works. |
| Date: | 2023–07 |
| URL: | http://d.repec.org/n?u=RePEc:bre:wpaper:node_9258&r=big |
| By: | Kunz, Pascal Christoph; Jussupow, Ekaterina; Spohrer, Kai; Heinzl, Armin |
| Date: | 2022–05–11 |
| URL: | http://d.repec.org/n?u=RePEc:dar:wpaper:138573&r=big |
| By: | Anderie, Lutz; Hönig, Michaela |
| Abstract: | Das Metaverse ist eine neue Art von Plattform, die eine intuitive und natürliche Benutzererfahrung bietet. Es nutzt intelligente Technologien wie KI, Machine Learning und Datenanalyse, um Benutzer mit Content, Diensten und Erlebnissen zu verbinden. Das Metaverse ist eine vollständig immersive, dreidimensionale digitale Umgebung, die aus vielen vernetzten Plattformen besteht und ein realitätsnahes Erlebnis bietet. Dazu gehört eine immersive 3-D-Umgebung - beispielsweise in Virtual- oder Augmented Reality (VR/AR) - mit einer hohen visuellen Qualität und realistischen Geräuschen. |
| Keywords: | Metaversum, Internet, Blockchain |
| Date: | 2023 |
| URL: | http://d.repec.org/n?u=RePEc:zbw:fhfwps:27&r=big |
| By: | Nikhil Agarwal; Alex Moehring; Pranav Rajpurkar; Tobias Salz |
| Abstract: | While Artificial Intelligence (AI) algorithms have achieved performance levels comparable to human experts on various predictive tasks, human experts can still access valuable contextual information not yet incorporated into AI predictions. Humans assisted by AI predictions could outperform both human-alone or AI-alone. We conduct an experiment with professional radiologists that varies the availability of AI assistance and contextual information to study the effectiveness of human-AI collaboration and to investigate how to optimize it. Our findings reveal that (i) providing AI predictions does not uniformly increase diagnostic quality, and (ii) providing contextual information does increase quality. Radiologists do not fully capitalize on the potential gains from AI assistance because of large deviations from the benchmark Bayesian model with correct belief updating. The observed errors in belief updating can be explained by radiologists’ partially underweighting the AI’s information relative to their own and not accounting for the correlation between their own information and AI predictions. In light of these biases, we design a collaborative system between radiologists and AI. Our results demonstrate that, unless the documented mistakes can be corrected, the optimal solution involves assigning cases either to humans or to AI, but rarely to a human assisted by AI. |
| JEL: | C50 C90 D47 D83 |
| Date: | 2023–07 |
| URL: | http://d.repec.org/n?u=RePEc:nbr:nberwo:31422&r=big |
| By: | Ariel Neufeld; Julian Sester |
| Abstract: | In this paper we demonstrate both theoretically as well as numerically that neural networks can detect model-free static arbitrage opportunities whenever the market admits some. Due to the use of neural networks, our method can be applied to financial markets with a high number of traded securities and ensures almost immediate execution of the corresponding trading strategies. To demonstrate its tractability, effectiveness, and robustness we provide examples using real financial data. From a technical point of view, we prove that a single neural network can approximately solve a class of convex semi-infinite programs, which is the key result in order to derive our theoretical results that neural networks can detect model-free static arbitrage strategies whenever the financial market admits such opportunities. |
| Date: | 2023–06 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2306.16422&r=big |
| By: | Marco Morucci; Vittorio Orlandi; Harsh Parikh; Sudeepa Roy; Cynthia Rudin; Alexander Volfovsky |
| Abstract: | Experimental and observational studies often lack validity due to untestable assumptions. We propose a double machine learning approach to combine experimental and observational studies, allowing practitioners to test for assumption violations and estimate treatment effects consistently. Our framework tests for violations of external validity and ignorability under milder assumptions. When only one assumption is violated, we provide semi-parametrically efficient treatment effect estimators. However, our no-free-lunch theorem highlights the necessity of accurately identifying the violated assumption for consistent treatment effect estimation. We demonstrate the applicability of our approach in three real-world case studies, highlighting its relevance for practical settings. |
| Date: | 2023–07 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2307.01449&r=big |
| By: | Yue Tian; Guanjun Liu |
| Abstract: | How to obtain informative representations of transactions and then perform the identification of fraudulent transactions is a crucial part of ensuring financial security. Recent studies apply Graph Neural Networks (GNNs) to the transaction fraud detection problem. Nevertheless, they encounter challenges in effectively learning spatial-temporal information due to structural limitations. Moreover, few prior GNN-based detectors have recognized the significance of incorporating global information, which encompasses similar behavioral patterns and offers valuable insights for discriminative representation learning. Therefore, we propose a novel heterogeneous graph neural network called Spatial-Temporal-Aware Graph Transformer (STA-GT) for transaction fraud detection problems. Specifically, we design a temporal encoding strategy to capture temporal dependencies and incorporate it into the graph neural network framework, enhancing spatial-temporal information modeling and improving expressive ability. Furthermore, we introduce a transformer module to learn local and global information. Pairwise node-node interactions overcome the limitation of the GNN structure and build up the interactions with the target node and long-distance ones. Experimental results on two financial datasets compared to general GNN models and GNN-based fraud detectors demonstrate that our proposed method STA-GT is effective on the transaction fraud detection task. |
| Date: | 2023–07 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2307.05121&r=big |
| By: | Yannick Limmer; Blanka Horvath |
| Abstract: | The availability of deep hedging has opened new horizons for solving hedging problems under a large variety of realistic market conditions. At the same time, any model - be it a traditional stochastic model or a market generator - is at best an approximation of market reality, prone to model-misspecification and estimation errors. This raises the question, how to furnish a modelling setup with tools that can address the risk of discrepancy between anticipated distribution and market reality, in an automated way. Automated robustification is currently attracting increased attention in numerous investment problems, but it is a delicate task due to its imminent implications on risk management. Hence, it is beyond doubt that more activity can be anticipated on this topic to converge towards a consensus on best practices. This paper presents a natural extension of the original deep hedging framework to address uncertainty in the data generating process via an adversarial approach inspired by GANs to automate robustification in our hedging objective. This is achieved through an interplay of three modular components: (i) a (deep) hedging engine, (ii) a data-generating process (that is model agnostic permitting a large variety of classical models as well as machine learning-based market generators), and (iii) a notion of distance on model space to measure deviations between our market prognosis and reality. We do not restrict the ambiguity set to a region around a reference model, but instead penalize deviations from the anticipated distribution. Our suggested choice for each component is motivated by model agnosticism, allowing a seamless transition between settings. Since all individual components are already used in practice, we believe that our framework is easily adaptable to existing functional settings. |
| Date: | 2023–07 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2307.02310&r=big |
| By: | Wójcik-Czerniawska, Agnieszka |
| Abstract: | In terms of the economy, agriculture plays a significant role. In agriculture, automation has become a major concern and a hot topic around the world. Food and employment demand are rising as a result of a rapidly expanding population. Using the new methods, billions of people were able to meet their dietary needs while also gaining employment opportunities. Farming has undergone an enormous change thanks to artificial intelligence. Crop yields have been protected by this technology from a variety of threats, including climate change, population growth, labour shortages, and concerns about global food security. Weeding, spraying, and irrigation are just a few of the many uses for artificial intelligence in agriculture that this paper examines in detail, with the help of sensors and other tools built into machine and drones. Water, pesticide, herbicide, and soil fertility use, as well as labour use, are all reduced thanks to these new technologies, which boost output while also improving product quality. Robots and drones are being used for weeding in agriculture, and this paper compiles the findings of numerous researchers to give readers an overview of the current state of automation in agriculture. Soil water sensing techniques and two automated weeding methods are discussed. It is discussed in this paper how drones can be used for spraying and crop monitoring, as well as the various methods they can employ. |
| Keywords: | Production Economics, Research and Development/Tech Change/Emerging Technologies |
| Date: | 2022–09–23 |
| URL: | http://d.repec.org/n?u=RePEc:ags:haaewp:337138&r=big |
| By: | Wójcik-Czerniawska, Agnieszka |
| Abstract: | In terms of the economy, agriculture plays a significant role. In agriculture, automation has become a major concern and a hot topic around the world. Food and employment demand are rising as a result of a rapidly expanding population. Using the new methods, billions of people were able to meet their dietary needs while also gaining employment opportunities. Farming has undergone an enormous change thanks to artificial intelligence. Crop yields have been protected by this technology from a variety of threats, including climate change, population growth, labour shortages, and concerns about global food security. Weeding, spraying, and irrigation are just a few of the many uses for artificial intelligence in agriculture that this paper examines in detail, with the help of sensors and other tools built into machine and drones. Water, pesticide, herbicide, and soil fertility use, as well as labour use, are all reduced thanks to these new technologies, which boost output while also improving product quality. Robots and drones are being used for weeding in agriculture, and this paper compiles the findings of numerous researchers to give readers an overview of the current state of automation in agriculture. Soil water sensing techniques and two automated weeding methods are discussed. It is discussed in this paper how drones can be used for spraying and crop monitoring, as well as the various methods they can employ. |
| Keywords: | Production Economics, Research and Development/Tech Change/Emerging Technologies |
| Date: | 2022–09–23 |
| URL: | http://d.repec.org/n?u=RePEc:ags:haaepa:337138&r=big |
| By: | Miguel Faria-e-Castro; Fernando Leibovici |
| Abstract: | We explore the ability of Large Language Models (LLMs) to produce conditional inflation forecasts during the 2019-2023 period. We use a leading LLM (Google AI's PaLM) to produce distributions of conditional forecasts at different horizons and compare these forecasts to those of a leading source, the Survey of Professional Forecasters (SPF). We find that LLM forecasts generate lower mean-squared errors overall in most years, and at almost all horizons. LLM forecasts exhibit slower reversion to the 2% inflation anchor. We argue that this method of generating forecasts is inexpensive and can be applied to other time series. |
| Keywords: | inflation forecasts; large language models; artificial intelligence |
| JEL: | E31 E37 C45 C53 |
| Date: | 2023–07–14 |
| URL: | http://d.repec.org/n?u=RePEc:fip:fedlwp:96478&r=big |
| By: | Gaël Le Mens; Balász Kovács; Michael T. Hannan; Guillem Pros |
| Abstract: | Recently, the world’s attention has been captivated by Large Language Models (LLMs) thanks to OpenAI’s Chat-GPT, which rapidly proliferated as an app powered by GPT-3 and now its successor, GPT-4. If these LLMs produce human-like text, the semantic spaces they construct likely align with those used by humans for interpreting and generating language. This suggests that social scientists could use these LLMs to construct measures of semantic similarity that match human judgment. In this article, we provide an empirical test of this intuition. We use GPT-4 to construct a new measure of typicality– the similarity of a text document to a concept or category. We evaluate its performance against other model-based typicality measures in terms of their correspondence with human typicality ratings. We conduct this comparative analysis in two domains: the typicality of books in literary genres (using an existing dataset of book descriptions) and the typicality of tweets authored by US Congress members in the Democratic and Republican parties (using a novel dataset). The GPT-4 Typicality measure not only meets or exceeds the current state-of-the-art but accomplishes this without any model training. This is a breakthrough because the previous state-of-the-art measure required fine-tuning a model (a BERT text classifier) on hundreds of thousands of text documents to achieve its performance. Our comparative analysis emphasizes the need for systematic empirical validation of measures based on LLMs: several measures based on other recent LLMs achieve at best a moderate correspondence with human judgments. |
| Keywords: | categories, concepts, deep learning, typicality, GPT, chatGPT, BERT, Similarity |
| JEL: | C18 C52 |
| Date: | 2023–06 |
| URL: | http://d.repec.org/n?u=RePEc:bge:wpaper:1394&r=big |
| By: | Pawel Baranowski; Hamza Bennani (LEMNA - Laboratoire d'économie et de management de Nantes Atlantique - ONIRIS - École nationale vétérinaire, agroalimentaire et de l'alimentation Nantes-Atlantique - IMT Atlantique - IMT Atlantique - IMT - Institut Mines-Télécom [Paris] - Nantes Univ - IAE Nantes - Nantes Université - Institut d'Administration des Entreprises - Nantes - Nantes Université - pôle Sociétés - Nantes Univ - Nantes Université - IUML - FR 3473 Institut universitaire Mer et Littoral - UM - Le Mans Université - UA - Université d'Angers - UBS - Université de Bretagne Sud - IFREMER - Institut Français de Recherche pour l'Exploitation de la Mer - CNRS - Centre National de la Recherche Scientifique - Nantes Université - pôle Sciences et technologie - Nantes Univ - Nantes Université - Nantes Univ - ECN - École Centrale de Nantes - Nantes Univ - Nantes Université); Wirginia Doryń |
| Abstract: | Using textual analysis and high-frequency financial data, this letter emphasizes the informativeness of the different communication phases of the ECB press conference, the Introductory Statement and the Questions & Answers, for market participants. Our results show that, while the tone of the Introductory Statement brings valuable information to stock market participants, the Questions & Answers were mostly informative after the Global Financial Crisis. Moreover, the announcement of unconventional measures triggers stronger reaction from market participants, particularly during the Questions & Answers. |
| Keywords: | central bank communication, financial markets, textual analysis |
| Date: | 2023–03 |
| URL: | http://d.repec.org/n?u=RePEc:hal:journl:hal-04145785&r=big |
| By: | Stefano Piasenti (HU Berlin); Marica Valente (University of Innsbruck); Roel van Veldhuizen (Lund University); Gregor Pfeifer (University of Sydney) |
| Abstract: | How do men and women differ in their persistence after experiencing failure in a competitive environment? We tackle this question by combining a large online experiment (N=2, 086) with machine learning. We find that when losing is unequivocally due to merit, both men and women exhibit a significant decrease in subsequent tournament entry. However, when the prior tournament is unfair, i.e., a loss is no longer necessarily based on merit, women are more discouraged than men. These results suggest that transparent meritocratic criteria may play a key role in preventing women from falling behind after experiencing a loss. |
| Keywords: | competitiveness; gender; fairness; machine learning; online experiment; |
| JEL: | C90 D91 J16 C14 |
| Date: | 2023–07–14 |
| URL: | http://d.repec.org/n?u=RePEc:rco:dpaper:410&r=big |
| By: | Lenza, Michele; Moutachaker, Inès; Paredes, Joan |
| Abstract: | Density forecasts of euro area inflation are a fundamental input for a medium-term oriented central bank, such as the European Central Bank (ECB). We show that a quantile regression forest, capturing a general non-linear relationship between euro area (headline and core) inflation and a large set of determinants, is competitive with state-of-the-art linear benchmarks and judgemental survey forecasts. The median forecasts of the quantile regression forest are very collinear with the ECB point inflation forecasts, displaying similar deviations from “linearity”. Given that the ECB modelling toolbox is overwhelmingly linear, this finding suggests that the expert judgement embedded in the ECB forecast may be characterized by some mild non-linearity. JEL Classification: C52, C53, E31, E37 |
| Keywords: | Inflation, Non-linearity, Quantile Regression Forest |
| Date: | 2023–07 |
| URL: | http://d.repec.org/n?u=RePEc:ecb:ecbwps:20232830&r=big |
| By: | Kampanelis, Sotiris; Elizalde, Aldo; Ioannides, Yannis M. |
| Abstract: | This paper examines the long-term economic impacts of the adoption of local knowledge during European colonisation. We use the case of Australia, where Aboriginal knowledge of the landscape was integral to colonial exploration and settlement. To quantify the effects of this knowledge, we construct a newly digitised and georeferenced dataset of trade routes created by Aboriginal people based on oral traditions, known as Songlines. Our results indicate that Aboriginal trade routes are strongly associated with current economic activity as measured by nighttime satellite imagery. We attribute this association to path dependence and agglomeration effects that emanate from the transport infrastructure built by Europeans roughly along these routes, which have agglomerated economic activity. Finally, by exploiting exogenous variation in optimal travel routes, we provide evidence that our results are not entirely determined by the inherent characteristics of Australian topography, but rather by Aboriginal knowledge. |
| Keywords: | Aboriginal trade routes, Songlines, colonialism, agglomeration, Australia |
| JEL: | N77 O10 R12 Z10 Z13 |
| Date: | 2023 |
| URL: | http://d.repec.org/n?u=RePEc:zbw:qucehw:202307&r=big |