|
on Computational Economics |
| By: | Challoumis, Constantinos |
| Abstract: | While some may view artificial intelligence as a contemporary phenomenon, its roots sink deep into the annals of human ingenuity. Central to the understanding of this domain is the distinction between artificial intelligence (AI) and machine learning (ML). AI manifests as a complex branch of computer science that endeavors to emulate human cognitive functions, thereby enabling machines to perform tasks typically requiring human intelligence, such as understanding language, recognizing patterns, and making decisions. On the other hand, machine learning is a subset of AI, focusing primarily on the development of algorithms that allow computers to learn from and make predictions based on data. As data accumulates, these algorithms enhance their performance autonomously—without explicit programming, symbolizing a fundamental shift in our interaction with technology. |
| Keywords: | AI revolution, monetary landscape, job opportunities |
| JEL: | F00 H0 Z0 |
| Date: | 2024–11–15 |
| URL: | https://d.repec.org/n?u=RePEc:pra:mprapa:122734 |
| By: | Abramson, Corey; Li, Zhuofan |
| Abstract: | Ethnography (social scientific methods that illuminate how people understand, navigate and shape the real world contexts in which they live their lives) and machine learning (computational techniques that use big data and statistical learning models to perform quantifiable tasks) are each core to contemporary social science. Yet these tools have remained largely separate in practice. This chapter draws on a growing body of scholarship that argues that ethnography and machine learning can be usefully combined, particularly for large comparative studies. Specifically, this paper (a) explains the value (and challenges) of using machine learning alongside qualitative field research for certain types of projects, (b) discusses recent methodological trends to this effect, (c) provides examples that illustrate workflow drawn from several large projects, and (d) concludes with a roadmap for enabling productive coevolution of field methods and machine learning. Keywords ethnography, computational social science, qualitative methods, machine learning, natural language processing, large language models, computational ethnography, digital ethnography, big data, research methods, mixed-methods |
| Date: | 2024–12–09 |
| URL: | https://d.repec.org/n?u=RePEc:osf:osfxxx:jvpbw |
| By: | Katsafados, Apostolos G.; Leledakis, George N.; Panagiotou, Nikolaos P.; Pyrgiotakis, Emmanouil G. |
| Abstract: | We combine machine learning algorithms (ML) with textual analysis techniques to forecast bank stock returns. Our textual features are derived from press releases of the Federal Open Market Committee (FOMC). We show that ML models produce more accurate out-of-sample predictions than OLS regressions, and that textual features can be more informative inputs than traditional financial variables. However, we achieve the highest predictive accuracy by training ML models on a combination of both financial variables and textual data. Importantly, portfolios constructed using the predictions of our best performing ML model consistently outperform their benchmarks. Our findings add to the scarce literature on bank return predictability and have important implications for investors. |
| Keywords: | Bank stock prediction; Trading strategies; Machine learning; Press conferences; Natural language processing; Banks |
| JEL: | C53 C88 G00 G11 G12 G14 G17 G21 |
| Date: | 2024–10 |
| URL: | https://d.repec.org/n?u=RePEc:pra:mprapa:122899 |
| By: | Dyakonova, Ludmila; Konstantinov, Alexey |
| Abstract: | The article studies approaches to improving the forecasting quality of machine learning models in finance. An overview of studies devoted to the application of machine learning models and artificial intelligence in the banking sector is given, both from the point of view of risk management and considering in more detail the applied methods of credit scoring and fraud detection. Aspects of applying explainable artificial intelligence (XAI) methods in financial organizations are considered. To identify the most effective machine learning models, the authors conducted experiments to compare 8 classification models used in the financial sector. The gradient boosting model CatboostClassifier was chosen as the base model. A comparison was carried out for the results obtained on the CatboostClassifier model with the characteristics of the other models: IsolationForest, feature ranking model using Recursive Feature Elimination (RFE), XAI Shapley values method, positive class weight increase models wrapper model. All models were applied to 5 open financial data sets. 1 dataset contains transaction data of credit card transactions, 3 datasets contain data on retail lending, and 1 dataset contains data on consumer lending. Our calculations revealed slight improvement for the models IsolationForest and wrapper model in comparison with the base CatboostClassifier model in terms of ROC_AUC for loan defaults data. |
| Keywords: | financial risks, credit scoring, fraud detection, machine learning, explainable artificial intelligence methods, Catboost, SHAP |
| JEL: | C63 |
| Date: | 2024–12–10 |
| URL: | https://d.repec.org/n?u=RePEc:pra:mprapa:122941 |
| By: | Jairo Flores (Banco Central de Reserva del Perú); Bruno Gonzaga (Banco Central de Reserva del Perú); Walter Ruelas-Huanca (Banco Central de Reserva del Perú); Juan Tang (Banco Central de Reserva del Perú) |
| Abstract: | 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 12 ML models, including Lasso, Ridge, Elastic Net, Support Vector Regression, Random Forest, XGBoost, and Neural Networks. The study compares these ML approaches against the traditional Dynamic Factor Model (DFM), which serves as the benchmark for nowcasting in economic research. We treat specific configurations, such as the feature matrix rotations and the dimensionality reduction technique, as hyperparameters that are optimized iteratively by the Tree-Structured Parzen Estimator. Our results show that ML models outperformed DFM in nowcasting total GDP, and that they achieve similar performance to this benchmark in nowcasting non-primary GDP. Furthermore, the bottom-up approach appears to be the most effective practice for nowcasting economic activity, as aggregating sectoral predictions improves the precision of ML methods. The findings indicate that ML models offer a viable and competitive alternative to traditional nowcasting methods. |
| Keywords: | GDP, Machine Learning, nowcasting |
| JEL: | C14 C32 E32 E52 |
| Date: | 2024–12 |
| URL: | https://d.repec.org/n?u=RePEc:rbp:wpaper:2024-019 |
| By: | Abbate Nicolás Francisco; Gasparini Leonardo; Ronchetti Franco; Quiroga Facundo |
| Abstract: | In this study, we examine the potential of using high-resolution satellite imagery and machine learning techniques to create income maps with a high level of geographic detail. We trained a convolutional neural network with satellite images from the Metropolitan Area of Buenos Aires (Argentina) and 2010 census data to estimate per capita income at a 50x50 meter resolution for 2013, 2018, and 2022. This outperformed the resolution and frequency of available census information. Based on the EfficientnetV2 architecture, the model achieved high accuracy in predicting household incomes ($R^2=0.878$), surpassing the spatial resolution and model performance of other methods used in the existing literature. This approach presents new opportunities for the generation of highly disaggregated data, enabling the assessment of public policies at a local scale, providing tools for better targeting of social programs, and reducing the information gap in areas where data is not collected. |
| JEL: | C81 C45 |
| Date: | 2024–11 |
| URL: | https://d.repec.org/n?u=RePEc:aep:anales:4701 |
| By: | Caravaggio, Nicola; Resce, Giuliano; Idola Francesca, Spanò |
| Abstract: | This paper investigates determinants of local tax policy, with a particular focus on personal income tax rates in Italian municipalities. By employing seven Machine Learning (ML) algorithms, we assess and predict tax rate decisions, identifying Random Forest as the most accurate model. Results underscore the critical influence of demographic dynamics, fiscal health, socioeconomic conditions, and institutional quality on tax policy formulation. The findings not only showcase the power of ML in enhancing predictive precision in public finance but also provide actionable insights for policymakers and stakeholders, enabling more informed decision-making and the mitigation of fiscal uncertainties. |
| Keywords: | Local taxation, Machine learning, Municipalities. |
| JEL: | C53 H24 H71 |
| Date: | 2024–09–24 |
| URL: | https://d.repec.org/n?u=RePEc:mol:ecsdps:esdp24098 |
| By: | Li, Chao; Keeley, Alexander Ryota; Takeda, Shutaro; Seki, Daikichi; Managi, Shunsuke |
| Abstract: | We create a large language model with high accuracy to investigate the relatedness between 12 environmental, social, and governance (ESG) topics and more than 2 million news reports. The text match pre-trained transformer (TMPT) with 138, 843, 049 parameters is built to probe whether and how much a news record is connected to a specific topic of interest. The TMPT, based on the transformer structure and a pre-trained model, is an artificial intelligence model trained by more than 200, 000 academic papers. The cross-validation result reveals that the TMPT’s accuracy is 85.73%, which is excellent in zero-shot learning tasks. In addition, combined with sentiment analysis, our research monitors news attitudes and tones towards specific ESG topics daily from September 2021 to September 2023. The results indicate that the media is increasing discussion on social topics, while the news regarding environmental issues is reduced. Moreover, towards almost all topics, the attitudes are gradually becoming positive. Our research highlights the temporal shifts in public perception regarding 12 key ESG issues: ESG has been incrementally accepted by the public. These insights are invaluable for policymakers, corporate leaders, and communities as they navigate sustainable decision-making. |
| Keywords: | ESG; News; Natural Language Processing; Pre-trained Transformer; Data Mining; Machine Learning |
| JEL: | G0 H0 M1 |
| Date: | 2024–11 |
| URL: | https://d.repec.org/n?u=RePEc:pra:mprapa:122757 |
| By: | Hota, Ashish |
| Abstract: | This paper explores the evolution of AI-driven pricing strategies in the automotive and financial services sectors, focusing on dynamic and deal-based pricing models that adapt in real time to shifts in consumer behavior, supply chain limitations, and market fluctuations. We examine how advanced machine learning techniques, including deep learning and reinforcement learning, enable predictive and adaptive pricing solutions that drive customer loyalty, revenue optimization, and transparency. Explainable AI also features prominently, offering transparency to consumers and regulators alike. |
| Date: | 2024–11–25 |
| URL: | https://d.repec.org/n?u=RePEc:osf:osfxxx:emgpv |
| By: | Chaohua Dong; Jiti Gao; Bin Peng; Yayi Yan |
| Abstract: | In this paper, we consider estimation and inference for the unknown parameters and function involved in a class of generalized hierarchical models. Such models are of great interest in the literature of neural networks (such as Bauer and Kohler, 2019). We propose a rectified linear unit (ReLU) based deep neural network (DNN) approach, and contribute to the design of DNN by i) providing more transparency for practical implementation, ii) defining different types of sparsity, iii) showing the differentiability, iv) pointing out the set of effective parameters, and v) offering a new variant of rectified linear activation function (ReLU), etc. Asymptotic properties are established accordingly, and a feasible procedure for the purpose of inference is also proposed. We conduct extensive numerical studies to examine the finite-sample performance of the estimation methods, and we also evaluate the empirical relevance and applicability of the proposed models and estimation methods to real data. |
| Keywords: | Estimation Theory; Deep Neural Network; Hierarchical Model; ReLU |
| JEL: | C14 C45 G12 |
| Date: | 2024 |
| URL: | https://d.repec.org/n?u=RePEc:msh:ebswps:2024-7 |
| By: | Kamlakshya, Tikhnadhi (Citizens Bank) |
| Abstract: | Artificial Intelligence (AI) is revolutionizing eligibility verification processes in Health and Human Services (HHS) agencies, offering significant improvements in efficiency and accuracy. This study examines the role of AI in streamlining operations, enhancing fraud detection, and optimizing resource allocation within HHS eligibility verification systems. By leveraging machine learning algorithms, AI can rapidly analyze vast datasets, cross-reference information with existing databases, and identify patterns that may indicate eligibility or potential fraud. The implementation of AI not only accelerates the decision-making process but also reduces human error, particularly in complex cases. Moreover, AI's ability to flag discrepancies for human review allows agencies to focus their resources on high-risk cases, potentially preventing fraudulent claims and ensuring that services reach those truly in need. This research highlights the transformative potential of AI in HHS eligibility verification and its natural progression towards more sophisticated fraud detection mechanisms, ultimately improving the integrity and effectiveness of social service programs. Keywords: Artificial Intelligence (AI), Government Public Sector, Health and Human Services (HHS), Salesforce, Apex, AWS, Fraud Detection. |
| Date: | 2024–12–02 |
| URL: | https://d.repec.org/n?u=RePEc:osf:osfxxx:x8e9v |
| By: | Bruno Deffains (Université Paris Panthéon Sorbonne; CRED); Frédéric Marty (Université Côte d'Azur, France; GREDEG CNRS) |
| Abstract: | The implementation of generative artificial intelligence in legal services offers undeniable efficiency gains, but also raises fundamental issues for law firms. These challenges can be categorised along a broad continuum, ranging from changes in business lines to changes in the competitive environment and the internal organisation of law firms. This paper considers the risks that law firms face in terms of both the quality of the services they provide and perceived competition, both horizontally and vertically, considering possible relationships of dependency on suppliers of large language models and cloud infrastructures. |
| Keywords: | generative artificial intelligence, legal services, accountability, competition, vertical relationships |
| JEL: | L42 L86 |
| Date: | 2025–01 |
| URL: | https://d.repec.org/n?u=RePEc:gre:wpaper:2025-01 |
| By: | Hota, Ashish |
| Abstract: | The integration of behavioral data analysis and machine learning (ML) within unified systems has become increasingly vital for enhanced decision-making and system optimization across various industries, including healthcare, marketing, and finance. Behavioral data—comprising user actions, preferences, and interactions—provides valuable insights into emerging trends, enabling adaptive and intelligent system functionalities. Coupling this with ML allows systems to continuously learn and improve their performance. This paper presents a comprehensive approach to integrating behavioral data analysis and ML within unified systems, covering key methodologies, technical challenges, applications, and a roadmap for future developments. Additionally, the article includes technical facts, tables, diagrams, and comparisons to aid in understanding the technical aspects and advantages of this integration. |
| Date: | 2024–12–16 |
| URL: | https://d.repec.org/n?u=RePEc:osf:osfxxx:rjpxs |
| By: | Polachek, Solomon (Binghamton University, New York); Romano, Kenneth (Binghamton University, New York); Tonguc, Ozlem (State University of New York) |
| Abstract: | Do large language models (LLMs)—such as ChatGPT 3.5, ChatGPT 4.0, and Google's Gemini 1.0 Pro—simulate human behavior in the context of the Prisoner's Dilemma (PD) game with varying stake sizes? This paper investigates this question, examining how LLMs navigate scenarios where self-interested behavior of all players results in less preferred outcomes, offering insights into how LLMs might "perceive" human decision-making. Through a replication of Yamagishi et al. (2016) "Study 2, " we analyze LLM responses to different payoff stakes and the influence of stake order on cooperation rates. LLMs demonstrate sensitivity to these factors, and some LLMs mirror human behavior only under very specific circumstances, implying the need for cautious application of LLMs in behavioral research. |
| Keywords: | Prisoner's Dilemma, cooperation, payoff stakes, artificial intelligence |
| JEL: | D01 C72 C90 |
| Date: | 2024–12 |
| URL: | https://d.repec.org/n?u=RePEc:iza:izadps:dp17521 |
| By: | Cova, Joshua; Schmitz, Luuk |
| Abstract: | The emergence of generative AI models is rapidly changing the social sciences. Much has now been written on the ethics and epistemological considerations of using these tools. Meanwhile, AI-powered research increasingly makes its way to preprint servers. However, we see a gap between ethics and practice: while many researchers would like to use these tools, few if any guides on how to do so exist. This paper fills this gap by providing users with a hands-on application written in accessible language. The paper deals with what we consider the most likely and advanced use case for AI in the social sciences: text annotation and classification. Our application guides readers through setting up a text classification pipeline and evaluating the results. The most important considerations concern reproducibility and transparency, open-source versus closed-source models, as well as the difference between classifier and generative models. The take-home message is this: these models provide unprecedented scale to augment research, but the community must take seriousely open-source and locally deployable models in the interest of open science principles. Our code to reproduce the example can be accessed via Github. |
| Date: | 2024–12–20 |
| URL: | https://d.repec.org/n?u=RePEc:osf:osfxxx:r3qng |
| By: | Nuttapol Lertmethaphat; Nuarpear Lekfuangfu; Pucktada Treeratpituk |
| Abstract: | In recent decades, the Beveridge curve, which demonstrates a relationship between unemployment and vacancies, has emerged as a central organizing framework for understanding of labour markets – both for academic as well as central banks. The absence of consistent of the data in Thailand is a fundamental drawback in the utilisation of this important indicator. Data from online job platforms presents an alternative opportunity. However, the first and necessary step is to develop a process that can structure and standardise such data. In this paper, we develop an algorithm that standardise the high-frequency data from job websites, which consists of manually written job titles from major online job posting websites in Thailand (in Thai and English languages) into the International Standard Classification of Occupations codes (ISCO-2008), up to 4-digit level. With Natural Language Processing and machine learning techniques, our methodology automates the process to efficiently deal with the volume and velocity nature of the data. Our approach not only carves a new path for comprehending labour market trends, but also enhances the capacity for monitoring labour market behaviours with higher precision and timeliness. Most of all, it offers a pivotal shift towards leveraging real-time, rich online job postings. |
| Keywords: | Labour market; Beveridge Curve; Online job platform; Machine Learning; Natural Language Processing; Text Classification; Thailand |
| JEL: | J2 J3 E24 N35 |
| Date: | 2025–01 |
| URL: | https://d.repec.org/n?u=RePEc:pui:dpaper:228 |
| By: | Vogel, Justus; Cordier, Johannes; Filipovic, Miodrag |
| Abstract: | Intensive care units (ICUs) operate with fixed capacities and face uncertainty such as demand variability, leading to demand-driven, early discharges to free up beds. These discharges can increase readmission rates, negatively impacting patient outcomes and aggravating ICU bottleneck congestion. This study investigates how ICU discharge timing affects readmission risk, with the goal of developing policies that minimize ICU readmissions, managing demand variability and bed capacity. To define a binary treatment, we randomly assign hypothetical discharge days to patients, comparing these with actual discharge days to form intervention and control groups. We apply two causal machine learning techniques (generalized random forest, modified causal forest). Assuming unconfoundedness, we leverage observed patient data as sufficient covariates. For scenarios where unconfoundedness might fail, we discuss an IV approach with different instruments. We further develop decision policies based on individualized average treatment effects (IATEs) to minimize individual patients' readmission risk. We find that for 72% of our sample (roughly 12, 000 cases), admission at point in time 𝑡 as compared to 𝑡+1 increases their readmission risk. Vice versa, 28% of cases profit from an earlier discharge in terms of readmission risk. To develop decision policies, we rank patients according to their IATE, and compare IATE rankings for instances, when demand exceeds the available capacity. Finally, we outline how we will assess the potential reduction in readmissions and saved bed capacities under optimal policies in a simulation, offering actionable insights for ICU management. We aim to provide a novel approach and blueprint for similar operations research and management science applications in data-rich environments. |
| Keywords: | Causal Machine Learning, Intensive Care Unit Management, Hospital Operations, Policy Learning |
| JEL: | I10 C44 |
| Date: | 2025 |
| URL: | https://d.repec.org/n?u=RePEc:zbw:hsgmed:202501 |
| By: | Chevalier, Arnaud (Royal Holloway, University of London); Orzech, Jakub (University of London); Stankov, Petar (University of London) |
| Abstract: | Grading and providing feedback are two of the most time-consuming activities in education. We developed a randomised controlled trial (RCT) to test whether they could be performed by generative artificial intelligence (Gen-AI). We randomly allocated undergraduate students to feedback provided either by a human instructor, ChatGPT 3.5, or ChatGPT 4. Our results show that: (i) Students treated with the freely accessible ChatGPT 3.5 received lower grades in subsequent assessments than their peers in the control group who always received human feedback; (ii) No such penalty was observed for ChatGPT 4. Separately, we tested the capacity of Gen-AI to grade student work. Gen-AI grades and ranks were significantly different than human-generated grades. Overall, while the newest LLM helps learning as well as a human, its ability to grade student work is still inferior. |
| Keywords: | feeback, grading, Artificial Intelligence, learning with Gen-AI |
| JEL: | A22 C93 I23 I24 |
| Date: | 2024–12 |
| URL: | https://d.repec.org/n?u=RePEc:iza:izadps:dp17511 |
| By: | Niousha Bagheri; Milad Ghasri; Michael Barlow |
| Abstract: | This paper introduces a framework for capturing stochasticity of choice probabilities in neural networks, derived from and fully consistent with the Random Utility Maximization (RUM) theory, referred to as RUM-NN. Neural network models show remarkable performance compared with statistical models; however, they are often criticized for their lack of transparency and interoperability. The proposed RUM-NN is introduced in both linear and nonlinear structures. The linear RUM-NN retains the interpretability and identifiability of traditional econometric discrete choice models while using neural network-based estimation techniques. The nonlinear RUM-NN extends the model's flexibility and predictive capabilities to capture nonlinear relationships between variables within utility functions. Additionally, the RUM-NN allows for the implementation of various parametric distributions for unobserved error components in the utility function and captures correlations among error terms. The performance of RUM-NN in parameter recovery and prediction accuracy is rigorously evaluated using synthetic datasets through Monte Carlo experiments. Additionally, RUM-NN is evaluated on the Swissmetro and the London Passenger Mode Choice (LPMC) datasets with different sets of distribution assumptions for the error component. The results demonstrate that RUM-NN under a linear utility structure and IID Gumbel error terms can replicate the performance of the Multinomial Logit (MNL) model, but relaxing those constraints leads to superior performance for both Swissmetro and LPMC datasets. By introducing a novel estimation approach aligned with statistical theories, this study empowers econometricians to harness the advantages of neural network models. |
| Date: | 2025–01 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2501.05221 |
| By: | Flavio Calvino; Luca Fontanelli |
| Abstract: | In this work we characterise French firms using artificial intelligence (AI) and explore the link between AI use and productivity. We distinguish AI users that source AI from external providers (AI buyers) from those developing their own AI systems (AI developers). AI buyers tend to be larger than other firms, but this relation is explained by ICT-related variables. Conversely, AI developers are larger and younger beyond ICT. Other digital technologies, digital skills and infrastructure play a key role for AI use, with AI developers leveraging more specialised ICT human capital than AI buyers. Overall, AI users tend to be more productive, however this is related to the self-selection of more productive and digital-intensive firms into AI use. This is not the case for AI developers, for which the positive link between AI use and productivity remains evident beyond selection. |
| Keywords: | technology diffusion, artificial intelligence, digitalisation, productivity |
| JEL: | D20 J24 O14 O33 |
| Date: | 2024 |
| URL: | https://d.repec.org/n?u=RePEc:ces:ceswps:_11466 |
| By: | Domenico Delli Gatti; Roberta Terranova; Enrico Maria Turco |
| Abstract: | Can standard measures of industrial policy such as R&D subsidies or financial support for machine replacement be effective tools to reverse the current pattern of increasing market power and declining business dynamism? To answer this question we explore the effects of various industrial policy instruments in a macroeconomic agent-based model calibrated to reproduce the decline in US business dynamism over the last half-century. Our results indicate that R&D subsidies alone are insufficient to address the underlying causes of declining dynamism. They become effective, however, when combined in a policy mix with knowledge diffusion policies, particularly those favoring advanced technology adoption by small firms. In this case, industrial policy fosters growth by closing the productivity gap between leaders and laggards, and thereby curbing market power. These findings suggests a two-pronged approach to the design of industrial policy, integrating firm-level subsidies with knowledge diffusion measures and therefore ensuring that innovation and competition policies advance together. |
| Keywords: | macroeconomic dynamics, innovation, knowledge diffusion, market power, industrial policy, agent-based model |
| JEL: | C63 E32 L10 L52 O31 O33 |
| Date: | 2024 |
| URL: | https://d.repec.org/n?u=RePEc:ces:ceswps:_11544 |
| By: | Adil Rengim Cetingoz; Charles-Albert Lehalle |
| Abstract: | Simulation methods have always been instrumental in finance, and data-driven methods with minimal model specification, commonly referred to as generative models, have attracted increasing attention, especially after the success of deep learning in a broad range of fields. However, the adoption of these models in financial applications has not kept pace with the growing interest, probably due to the unique complexities and challenges of financial markets. This paper aims to contribute to a deeper understanding of the limitations of generative models, particularly in portfolio and risk management. To this end, we begin by presenting theoretical results on the importance of initial sample size, and point out the potential pitfalls of generating far more data than originally available. We then highlight the inseparable nature of model development and the desired use case by touching on a paradox: generic generative models inherently care less about what is important for constructing portfolios (in particular the long-short ones). Based on these findings, we propose a pipeline for the generation of multivariate returns that meets conventional evaluation standards on a large universe of US equities while being compliant with stylized facts observed in asset returns and turning around the pitfalls we previously identified. Moreover, we insist on the need for more delicate evaluation methods, and suggest, through an example of mean-reversion strategies, a method designed to identify poor models for a given application based on regurgitative training, i.e. retraining the model using the data it has itself generated, which is commonly referred to in statistics as identifiability. |
| Date: | 2025–01 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2501.03993 |
| By: | Buskens, Vincent (Utrecht University); Corten, Rense; Przepiorka, Wojtek (Utrecht University) |
| Abstract: | Behavioral experiments are rarely used as an empirical strategy in computational social science, where empirical studies typically focus on analyzing large-scale digital trace data. We argue that behavioral experiments have a role in computational social science, in particular in combination with agent-based modeling – a key theoretical strategy in computational social science. We highlight three ways in which behavioral experiments can contribute to theory building in computational social science: by testing macro-level predictions from agent-based models, by evaluating behavioral assumptions on which these models are based, and by calibrating agent-based models. We illustrate these points through three examples from our work concerned with the emergence of conventions. |
| Date: | 2024–12–20 |
| URL: | https://d.repec.org/n?u=RePEc:osf:osfxxx:9vm5t |
| By: | Paul Ghelasi; Florian Ziel |
| Abstract: | Power prices can be forecasted using data-driven models or fundamental models. Data-driven models learn from historical patterns, while fundamental models simulate electricity markets. Traditionally, fundamental models have been too computationally demanding to allow for intrinsic parameter estimation or frequent updates, which are essential for short-term forecasting. In this paper, we propose a novel data-driven fundamental model that combines the strengths of both approaches. We estimate the parameters of a fully fundamental merit order model using historical data, similar to how data-driven models work. This removes the need for fixed technical parameters or expert assumptions, allowing most parameters to be calibrated directly to observations. The model is efficient enough for quick parameter estimation and forecast generation. We apply it to forecast German day-ahead electricity prices and demonstrate that it outperforms both classical fundamental and purely data-driven models. The hybrid model effectively captures price volatility and sequential price clusters, which are becoming increasingly important with the expansion of renewable energy sources. It also provides valuable insights, such as fuel switches, marginal power plant contributions, estimated parameters, dispatched plants, and power generation. |
| Date: | 2025–01 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2501.02963 |
| By: | Angela C. Lyons (University of Illinois Urbana-Champaign); Josephine Kass-Hanna (IESEG School of Management, Univ. Lille); Deepika Pingali (University of Illinois Urbana-Champaign); Aiman Soliman (University of Illinois Urbana-Champaign); David Zhu (University of Illinois Urbana-Champaign); Yifang Zhang (University of Illinois Urbana-Champaign); Alejandro Montoya Castano (Colombian Directorate of Taxes and Customs (DIAN), Bogotá) |
| Abstract: | This study integrates geospatial analysis with machine learning to understand the interplay and spatial dependencies among various indicators of food insecurity. Combining household survey data and novel geospatial data on Syrian refugees in Lebanon, we explore why certain food security measures are effective in specific contexts while others are not. Our findings indicate that geolocational indicators significantly influence food insecurity, often overshadowing traditional factors like household socio-demographics and living conditions. This suggests a shift in focus from labor-intensive socioeconomic surveys to readily accessible geospatial data. The study also highlights the variability of food insecurity across different locations and subpopulations, challenging the effectiveness of individual measures like FCS, HDDS, and rCSI in capturing localized needs. By disaggregating the dimensions of food insecurity and understanding their distribution, humanitarian and development organizations can better tailor strategies, directing resources to areas where refugees face the most severe food challenges. From a policy perspective, our insights call for a refined approach that improves the predictive power of food insecurity models, aiding organizations in efficiently targeting interventions. |
| Date: | 2024–09–20 |
| URL: | https://d.repec.org/n?u=RePEc:erg:wpaper:1729 |
| By: | Bryzgalova, Svetlana; Huang, Jiantao; Julliard, Christian |
| Abstract: | We propose a novel framework for analyzing linear asset pricing models: simple, robust, and applicable to high-dimensional problems. For a (potentially misspecified) stand-alone model, it provides reliable price of risk estimates for both tradable and nontradable factors, and detects those weakly identified. For competing factors and (possibly nonnested) models, the method automatically selects the best specification—if a dominant one exists—or provides a Bayesian model averaging–stochastic discount factor (BMA-SDF), if there is no clear winner. We analyze 2.25 quadrillion models generated by a large set of factors and find that the BMA-SDF outperforms existing models in- and out-of-sample. |
| JEL: | C11 C52 G12 C50 |
| Date: | 2023–02–28 |
| URL: | https://d.repec.org/n?u=RePEc:ehl:lserod:126151 |