|
on Big Data |
| By: | John D. Huber; Laura Mayoral |
| Abstract: | We develop a novel methodology that uses machine learning to produce accurate estimates of consumption per capita and poverty in 10x10km cells in sub-Saharan Africa over time. Using the new data, we revisit two prominent papers that examine the effect of institutions on economic development, both of which use “nightlights” as a proxy for development. The conclusions from these papers are reversed when we substitute the new consumption data for nightlights. We argue that the different conclusions about institutions are due to a previously unrecognized problem that is endemic when nightlights are used as a proxy for spatial economic well-being: nightlights suffer from nonclassical measurement error. This error will typically lead to biased estimates in standard statistical models that use nightlights as a spatially disaggregated measure of economic development. The bias can be either positive or negative, and it can appear when nightlights are used as either a dependent or an independent variable. Our research therefore underscores an important limitation in the use of nightlights, which has become the standard measure of spatial economic well-being for studies focusing on developing parts of the world. It also demonstrates how machine learning models can generate a useful alternative to nightlights, with important implications for the conclusions we draw from the analyses in which such data are employed. |
| Keywords: | economic develpment, poverty, institutions, nightlights, nonclassical measurement error, machine learning |
| JEL: | C01 P46 P48 |
| Date: | 2024–02 |
| URL: | http://d.repec.org/n?u=RePEc:bge:wpaper:1433&r=big |
| By: | Victor Chernozhukov; Christian Hansen; Nathan Kallus; Martin Spindler; Vasilis Syrgkanis |
| Abstract: | An introduction to the emerging fusion of machine learning and causal inference. The book presents ideas from classical structural equation models (SEMs) and their modern AI equivalent, directed acyclical graphs (DAGs) and structural causal models (SCMs), and covers Double/Debiased Machine Learning methods to do inference in such models using modern predictive tools. |
| Date: | 2024–03 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2403.02467&r=big |
| By: | Ziyuan Ma; Conor Ryan; Jim Buckley; Muslim Chochlov |
| Abstract: | Sentiment analysis can be used for stock market prediction. However, existing research has not studied the impact of a user's financial background on sentiment-based forecasting of the stock market using artificial neural networks. In this work, a novel combination of neural networks is used for the assessment of sentiment-based stock market prediction, based on the financial background of the population that generated the sentiment. The state-of-the-art language processing model Bidirectional Encoder Representations from Transformers (BERT) is used to classify the sentiment and a Long-Short Term Memory (LSTM) model is used for time-series based stock market prediction. For evaluation, the Weibo social networking platform is used as a sentiment data collection source. Weibo users (and their comments respectively) are divided into Authorized Financial Advisor (AFA) and Unauthorized Financial Advisor (UFA) groups according to their background information, as collected by Weibo. The Hong Kong Hang Seng index is used to extract historical stock market change data. The results indicate that stock market prediction learned from the AFA group users is 39.67% more precise than that learned from the UFA group users and shows the highest accuracy (87%) when compared to existing approaches. |
| Date: | 2024–02 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2403.00772&r=big |
| By: | Pierre Brugiere; Gabriel Turinici |
| Abstract: | The transformer models have been extensively used with good results in a wide area of machine learning applications including Large Language Models and image generation. Here, we inquire on the applicability of this approach to financial time series. We first describe the dataset construction for two prototypical situations: a mean reverting synthetic Ornstein-Uhlenbeck process on one hand and real S&P500 data on the other hand. Then, we present in detail the proposed Transformer architecture and finally we discuss some encouraging results. For the synthetic data we predict rather accurately the next move, and for the S&P500 we get some interesting results related to quadratic variation and volatility prediction. |
| Date: | 2024–03 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2403.02523&r=big |
| By: | Hanshuang Tong; Jun Li; Ning Wu; Ming Gong; Dongmei Zhang; Qi Zhang |
| Abstract: | Recent advancements in large language models (LLMs) have opened new pathways for many domains. However, the full potential of LLMs in financial investments remains largely untapped. There are two main challenges for typical deep learning-based methods for quantitative finance. First, they struggle to fuse textual and numerical information flexibly for stock movement prediction. Second, traditional methods lack clarity and interpretability, which impedes their application in scenarios where the justification for predictions is essential. To solve the above challenges, we propose Ploutos, a novel financial LLM framework that consists of PloutosGen and PloutosGPT. The PloutosGen contains multiple primary experts that can analyze different modal data, such as text and numbers, and provide quantitative strategies from different perspectives. Then PloutosGPT combines their insights and predictions and generates interpretable rationales. To generate accurate and faithful rationales, the training strategy of PloutosGPT leverage rearview-mirror prompting mechanism to guide GPT-4 to generate rationales, and a dynamic token weighting mechanism to finetune LLM by increasing key tokens weight. Extensive experiments show our framework outperforms the state-of-the-art methods on both prediction accuracy and interpretability. |
| Date: | 2024–02 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2403.00782&r=big |
| By: | Richard Schnorrenberger; Aishameriane Schmidt; Guilherme Valle Moura |
| Abstract: | We investigate the predictive ability of machine learning methods to produce weekly inflation nowcasts using high-frequency macro-financial indicators and a survey of professional forecasters. Within an unrestricted mixed-frequency ML framework, we provide clear guidelines to improve inflation nowcasts upon forecasts made by specialists. First, we find that variable selection performed via the LASSO is fundamental for crafting an effective ML model for inflation nowcasting. Second, we underscore the relevance of timely data on price indicators and SPF expectations to better discipline our model-based nowcasts, especially during the inflationary surge following the COVID-19 crisis. Third, we show that predictive accuracy substantially increases when the model specification is free of ragged edges and guided by the real-time data release of price indicators. Finally, incorporating the most recent high-frequency signal is already sufficient for real-time updates of the nowcast, eliminating the need to account for lagged high-frequency information. |
| Keywords: | inflation nowcasting; machine learning; mixed-frequency data; survey of professional forecasters; |
| JEL: | E31 E37 C53 C55 |
| Date: | 2024–03 |
| URL: | http://d.repec.org/n?u=RePEc:dnb:dnbwpp:806&r=big |
| By: | Giraldo, Carlos (Latin American Reserve Fund); Giraldo, Iader (Latin American Reserve Fund); Gomez-Gonzalez, Jose E. (City University of New York – Lehman College); Uribe, Jorge M. (Universitat Oberta de Catalunya) |
| Abstract: | This study utilizes weekly datasets on loan growth in Colombia to develop a daily indicator of credit expansion using a two-step machine learning approach. Initially, employing Random Forests (RF), missing data in the raw credit indicator is filled using high frequency indicators like spreads, interest rates, and stock market returns. Subsequently, Quantile Random Forest identifies periods of excessive credit creation, particularly focusing on growth quantiles above 95%, indicative of potential financial instability. Unlike previous studies, this research combines machine learning with mixed frequency analysis to create a versatile early warning instrument for identifying instances of excessive credit growth in emerging market economies. This methodology, with its ability to handle nonlinear relationships and accommodate diverse scenarios, offers significant value to central bankers and macroprudential authorities in safeguarding financial stability. |
| Keywords: | Credit growth; Machine learning methodology; Excessive credit creation; Financial stability |
| JEL: | C45 E44 G21 |
| Date: | 2024–03–10 |
| URL: | http://d.repec.org/n?u=RePEc:col:000566:021077&r=big |
| By: | Bryan Kelly; Boris Kuznetsov; Semyon Malamud; Teng Andrea Xu |
| Abstract: | We open up the black box behind Deep Learning for portfolio optimization and prove that a sufficiently wide and arbitrarily deep neural network (DNN) trained to maximize the Sharpe ratio of the Stochastic Discount Factor (SDF) is equivalent to a large factor model (LFM): A linear factor pricing model that uses many non-linear characteristics. The nature of these characteristics depends on the architecture of the DNN in an explicit, tractable fashion. This makes it possible to derive end-to-end trained DNN-based SDFs in closed form for the first time. We evaluate LFMs empirically and show how various architectural choices impact SDF performance. We document the virtue of depth complexity: With enough data, the out-of-sample performance of DNN-SDF is increasing in the NN depth, saturating at huge depths of around 100 hidden layers. |
| Date: | 2024–01 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2402.06635&r=big |
| By: | Qishuo Cheng; Le Yang; Jiajian Zheng; Miao Tian; Duan Xin |
| Abstract: | Portfolio management issues have been extensively studied in the field of artificial intelligence in recent years, but existing deep learning-based quantitative trading methods have some areas where they could be improved. First of all, the prediction mode of stocks is singular; often, only one trading expert is trained by a model, and the trading decision is solely based on the prediction results of the model. Secondly, the data source used by the model is relatively simple, and only considers the data of the stock itself, ignoring the impact of the whole market risk on the stock. In this paper, the DQN algorithm is introduced into asset management portfolios in a novel and straightforward way, and the performance greatly exceeds the benchmark, which fully proves the effectiveness of the DRL algorithm in portfolio management. This also inspires us to consider the complexity of financial problems, and the use of algorithms should be fully combined with the problems to adapt. Finally, in this paper, the strategy is implemented by selecting the assets and actions with the largest Q value. Since different assets are trained separately as environments, there may be a phenomenon of Q value drift among different assets (different assets have different Q value distribution areas), which may easily lead to incorrect asset selection. Consider adding constraints so that the Q values of different assets share a Q value distribution to improve results. |
| Date: | 2024–02 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2402.15994&r=big |
| By: | Vikranth Lokeshwar Dhandapani; Shashi Jain |
| Abstract: | In this paper, we present an artificial neural network framework for portfolio compression of a large portfolio of European options with varying maturities (target portfolio) by a significantly smaller portfolio of European options with shorter or same maturity (compressed portfolio), which also represents a self-replicating static hedge portfolio of the target portfolio. For the proposed machine learning architecture, which is consummately interpretable by choice of design, we also define the algorithm to learn model parameters by providing a parameter initialisation technique and leveraging the optimisation methodology proposed in Lokeshwar and Jain (2024), which was initially introduced to price Bermudan options. We demonstrate the convergence of errors and the iterative evolution of neural network parameters over the course of optimization process, using selected target portfolio samples for illustration. We demonstrate through numerical examples that the Exposure distributions and Exposure profiles (Expected Exposure and Potential Future Exposure) of the target portfolio and compressed portfolio align closely across future risk horizons under risk-neutral and real-world scenarios. Additionally, we benchmark the target portfolio's Financial Greeks (Delta, Gamma, and Vega) against the compressed portfolio at future time horizons across different market scenarios generated by Monte-Carlo simulations. Finally, we compare the regulatory capital requirement under the standardised approach for counterparty credit risk of the target portfolio against the compressed portfolio and highlight that the capital requirement for the compact portfolio substantially reduces. |
| Date: | 2024–02 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2402.17941&r=big |
| By: | Daniele Ballinari |
| Abstract: | Machine learning methods, particularly the double machine learning (DML) estimator (Chernozhukov et al., 2018), are increasingly popular for the estimation of the average treatment effect (ATE). However, datasets often exhibit unbalanced treatment assignments where only a few observations are treated, leading to unstable propensity score estimations. We propose a simple extension of the DML estimator which undersamples data for propensity score modeling and calibrates scores to match the original distribution. The paper provides theoretical results showing that the estimator retains the DML estimator's asymptotic properties. A simulation study illustrates the finite sample performance of the estimator. |
| Date: | 2024–03 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2403.01585&r=big |
| By: | Pengfei Zhao; Haoren Zhu; Wilfred Siu Hung NG; Dik Lun Lee |
| Abstract: | Volatility, as a measure of uncertainty, plays a crucial role in numerous financial activities such as risk management. The Econometrics and Machine Learning communities have developed two distinct approaches for financial volatility forecasting: the stochastic approach and the neural network (NN) approach. Despite their individual strengths, these methodologies have conventionally evolved in separate research trajectories with little interaction between them. This study endeavors to bridge this gap by establishing an equivalence relationship between models of the GARCH family and their corresponding NN counterparts. With the equivalence relationship established, we introduce an innovative approach, named GARCH-NN, for constructing NN-based volatility models. It obtains the NN counterparts of GARCH models and integrates them as components into an established NN architecture, thereby seamlessly infusing volatility stylized facts (SFs) inherent in the GARCH models into the neural network. We develop the GARCH-LSTM model to showcase the power of the GARCH-NN approach. Experiment results validate that amalgamating the NN counterparts of the GARCH family models into established NN models leads to enhanced outcomes compared to employing the stochastic and NN models in isolation. |
| Date: | 2024–01 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2402.06642&r=big |
| By: | ZHANG Meilian; YIN Ting; USUI Emiko; OSHIO Takashi; ZHANG Yi |
| Abstract: | Overemployment and underemployment being widely existing phenomena, much less is known about their determinants for older workers. We innovatively employ machine learning methods to determine the important factors driving overemployment and underemployment among older workers in Japan. Those with better economic conditions, worse health, less family support, and unfavorable job characteristics are more likely to report overemployment, whereas increasing age, less disposable income, shorter current work hours, holding a job with a temporary nature, and low job and pay satisfaction are predictive to underemployment. Cluster analysis further shows that reasons for having work hour mismatches can be highly heterogeneous within both overemployed and underemployed groups. Subgroup analyses suggest room for pro-work policies among 65+ workers facing financial stress and lacking family support, female workers with unstable jobs and low spousal income, and salaried workers working insufficient hours. |
| Date: | 2024–03 |
| URL: | http://d.repec.org/n?u=RePEc:eti:dpaper:24034&r=big |
| By: | Wentao Zhang; Lingxuan Zhao; Haochong Xia; Shuo Sun; Jiaze Sun; Molei Qin; Xinyi Li; Yuqing Zhao; Yilei Zhao; Xinyu Cai; Longtao Zheng; Xinrun Wang; Bo An |
| Abstract: | Financial trading is a crucial component of the markets, informed by a multimodal information landscape encompassing news, prices, and Kline charts, and encompasses diverse tasks such as quantitative trading and high-frequency trading with various assets. While advanced AI techniques like deep learning and reinforcement learning are extensively utilized in finance, their application in financial trading tasks often faces challenges due to inadequate handling of multimodal data and limited generalizability across various tasks. To address these challenges, we present FinAgent, a multimodal foundational agent with tool augmentation for financial trading. FinAgent's market intelligence module processes a diverse range of data-numerical, textual, and visual-to accurately analyze the financial market. Its unique dual-level reflection module not only enables rapid adaptation to market dynamics but also incorporates a diversified memory retrieval system, enhancing the agent's ability to learn from historical data and improve decision-making processes. The agent's emphasis on reasoning for actions fosters trust in its financial decisions. Moreover, FinAgent integrates established trading strategies and expert insights, ensuring that its trading approaches are both data-driven and rooted in sound financial principles. With comprehensive experiments on 6 financial datasets, including stocks and Crypto, FinAgent significantly outperforms 9 state-of-the-art baselines in terms of 6 financial metrics with over 36% average improvement on profit. Specifically, a 92.27% return (a 84.39% relative improvement) is achieved on one dataset. Notably, FinAgent is the first advanced multimodal foundation agent designed for financial trading tasks. |
| Date: | 2024–02 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2402.18485&r=big |
| By: | Ruoyu Sun (Xi'an Jiaotong-Liverpool University, School of Mathematics and Physics, Department of Financial and Actuarial Mathematics); Angelos Stefanidis (Xi'an Jiaotong-Liverpool University Entrepreneur College); Zhengyong Jiang (Xi'an Jiaotong-Liverpool University Entrepreneur College); Jionglong Su (Xi'an Jiaotong-Liverpool University Entrepreneur College) |
| Abstract: | As a model-free algorithm, deep reinforcement learning (DRL) agent learns and makes decisions by interacting with the environment in an unsupervised way. In recent years, DRL algorithms have been widely applied by scholars for portfolio optimization in consecutive trading periods, since the DRL agent can dynamically adapt to market changes and does not rely on the specification of the joint dynamics across the assets. However, typical DRL agents for portfolio optimization cannot learn a policy that is aware of the dynamic correlation between portfolio asset returns. Since the dynamic correlations among portfolio assets are crucial in optimizing the portfolio, the lack of such knowledge makes it difficult for the DRL agent to maximize the return per unit of risk, especially when the target market permits short selling (i.e., the US stock market). In this research, we propose a hybrid portfolio optimization model combining the DRL agent and the Black-Litterman (BL) model to enable the DRL agent to learn the dynamic correlation between the portfolio asset returns and implement an efficacious long/short strategy based on the correlation. Essentially, the DRL agent is trained to learn the policy to apply the BL model to determine the target portfolio weights. To test our DRL agent, we construct the portfolio based on all the Dow Jones Industrial Average constitute stocks. Empirical results of the experiments conducted on real-world United States stock market data demonstrate that our DRL agent significantly outperforms various comparison portfolio choice strategies and alternative DRL frameworks by at least 42% in terms of accumulated return. In terms of the return per unit of risk, our DRL agent significantly outperforms various comparative portfolio choice strategies and alternative strategies based on other machine learning frameworks. |
| Date: | 2024–02 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2402.16609&r=big |
| By: | Antonis Papapantoleon; Jasper Rou |
| Abstract: | We develop a novel deep learning approach for pricing European options in diffusion models, that can efficiently handle high-dimensional problems resulting from Markovian approximations of rough volatility models. The option pricing partial differential equation is reformulated as an energy minimization problem, which is approximated in a time-stepping fashion by deep artificial neural networks. The proposed scheme respects the asymptotic behavior of option prices for large levels of moneyness, and adheres to a priori known bounds for option prices. The accuracy and efficiency of the proposed method is assessed in a series of numerical examples, with particular focus in the lifted Heston model. |
| Date: | 2024–03 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2403.00746&r=big |
| By: | Adele Ravagnani; Fabrizio Lillo; Paola Deriu; Piero Mazzarisi; Francesca Medda; Antonio Russo |
| Abstract: | Identification of market abuse is an extremely complicated activity that requires the analysis of large and complex datasets. We propose an unsupervised machine learning method for contextual anomaly detection, which allows to support market surveillance aimed at identifying potential insider trading activities. This method lies in the reconstruction-based paradigm and employs principal component analysis and autoencoders as dimensionality reduction techniques. The only input of this method is the trading position of each investor active on the asset for which we have a price sensitive event (PSE). After determining reconstruction errors related to the trading profiles, several conditions are imposed in order to identify investors whose behavior could be suspicious of insider trading related to the PSE. As a case study, we apply our method to investor resolved data of Italian stocks around takeover bids. |
| Date: | 2024–03 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2403.00707&r=big |
| By: | Yilun Wang; Shengjie Guo |
| Abstract: | In recent years, the dynamic factor model has emerged as a dominant tool in economics and finance, particularly for investment strategies. This model offers improved handling of complex, nonlinear, and noisy market conditions compared to traditional static factor models. The advancement of machine learning, especially in dealing with nonlinear data, has further enhanced asset pricing methodologies. This paper introduces a groundbreaking dynamic factor model named RVRAE. This model is a probabilistic approach that addresses the temporal dependencies and noise in market data. RVRAE ingeniously combines the principles of dynamic factor modeling with the variational recurrent autoencoder (VRAE) from deep learning. A key feature of RVRAE is its use of a prior-posterior learning method. This method fine-tunes the model's learning process by seeking an optimal posterior factor model informed by future data. Notably, RVRAE is adept at risk modeling in volatile stock markets, estimating variances from latent space distributions while also predicting returns. Our empirical tests with real stock market data underscore RVRAE's superior performance compared to various established baseline methods. |
| Date: | 2024–03 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2403.02500&r=big |
| By: | Yiyan Huang; Cheuk Hang Leung; Siyi Wang; Yijun Li; Qi Wu |
| Abstract: | The growing demand for personalized decision-making has led to a surge of interest in estimating the Conditional Average Treatment Effect (CATE). The intersection of machine learning and causal inference has yielded various effective CATE estimators. However, deploying these estimators in practice is often hindered by the absence of counterfactual labels, making it challenging to select the desirable CATE estimator using conventional model selection procedures like cross-validation. Existing approaches for CATE estimator selection, such as plug-in and pseudo-outcome metrics, face two inherent challenges. Firstly, they are required to determine the metric form and the underlying machine learning models for fitting nuisance parameters or plug-in learners. Secondly, they lack a specific focus on selecting a robust estimator. To address these challenges, this paper introduces a novel approach, the Distributionally Robust Metric (DRM), for CATE estimator selection. The proposed DRM not only eliminates the need to fit additional models but also excels at selecting a robust CATE estimator. Experimental studies demonstrate the efficacy of the DRM method, showcasing its consistent effectiveness in identifying superior estimators while mitigating the risk of selecting inferior ones. |
| Date: | 2024–02 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2402.18392&r=big |
| By: | Jiajian Zheng; Duan Xin; Qishuo Cheng; Miao Tian; Le Yang |
| Abstract: | The stock market is a crucial component of the financial market, playing a vital role in wealth accumulation for investors, financing costs for listed companies, and the stable development of the national macroeconomy. Significant fluctuations in the stock market can damage the interests of stock investors and cause an imbalance in the industrial structure, which can interfere with the macro level development of the national economy. The prediction of stock price trends is a popular research topic in academia. Predicting the three trends of stock pricesrising, sideways, and falling can assist investors in making informed decisions about buying, holding, or selling stocks. Establishing an effective forecasting model for predicting these trends is of substantial practical importance. This paper evaluates the predictive performance of random forest models combined with artificial intelligence on a test set of four stocks using optimal parameters. The evaluation considers both predictive accuracy and time efficiency. |
| Date: | 2024–02 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2402.17194&r=big |
| By: | Sylvain Barthélémy; Virginie Gautier; Fabien Rondeau (CREM - Centre de recherche en économie et management - UNICAEN - Université de Caen Normandie - NU - Normandie Université - UR - Université de Rennes - CNRS - Centre National de la Recherche Scientifique) |
| Abstract: | Currency crises, recurrent events in the economic history of developing, emerging, and developed countries, have disastrous economic consequences. This paper proposes an early warning system for currency crises using sophisticated recurrent neural networks, such as long short‐term memory (LSTM) and gated recurrent unit (GRU). These models were initially used in language processing, where they performed well. Such models are increasingly being used in forecasting financial asset prices, including exchange rates, but they have not yet been applied to the prediction of currency crises. As for all recurrent neural networks, they allow for taking into account nonlinear interactions between variables and the influence of past data in a dynamic form. For a set of 68 countries including developed, emerging, and developing economies over the period of 1995–2020, LSTM and GRU outperformed our benchmark models. LSTM and GRU correctly sent continuous signals within a 2‐year warning window to alert for 91% of the crises. For the LSTM, false signals represent only 14% of the emitted signals compared with 23% for logistic regression, making it an efficient early warning system for policymakers. |
| Keywords: | currency crises, early warning system, gated recurrent unit, long short-term memory, neural network |
| Date: | 2024 |
| URL: | http://d.repec.org/n?u=RePEc:hal:journl:hal-04470367&r=big |
| By: | Vikranth Lokeshwar Dhandapani; Shashi Jain |
| Abstract: | This paper presents a Monte-Carlo-based artificial neural network framework for pricing Bermudan options, offering several notable advantages. These advantages encompass the efficient static hedging of the target Bermudan option and the effective generation of exposure profiles for risk management. We also introduce a novel optimisation algorithm designed to expedite the convergence of the neural network framework proposed by Lokeshwar et al. (2022) supported by a comprehensive error convergence analysis. We conduct an extensive comparative analysis of the Present Value (PV) distribution under Markovian and no-arbitrage assumptions. We compare the proposed neural network model in conjunction with the approach initially introduced by Longstaff and Schwartz (2001) and benchmark it against the COS model, the pricing model pioneered by Fang and Oosterlee (2009), across all Bermudan exercise time points. Additionally, we evaluate exposure profiles, including Expected Exposure and Potential Future Exposure, generated by our proposed model and the Longstaff-Schwartz model, comparing them against the COS model. We also derive exposure profiles at finer non-standard grid points or risk horizons using the proposed approach, juxtaposed with the Longstaff Schwartz method with linear interpolation and benchmark against the COS method. In addition, we explore the effectiveness of various interpolation schemes within the context of the Longstaff-Schwartz method for generating exposures at finer grid horizons. |
| Date: | 2024–02 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2402.15936&r=big |
| By: | Chu Myaet Thwal; Ye Lin Tun; Kitae Kim; Seong-Bae Park; Choong Seon Hong |
| Abstract: | Recent innovations in transformers have shown their superior performance in natural language processing (NLP) and computer vision (CV). The ability to capture long-range dependencies and interactions in sequential data has also triggered a great interest in time series modeling, leading to the widespread use of transformers in many time series applications. However, being the most common and crucial application, the adaptation of transformers to time series forecasting has remained limited, with both promising and inconsistent results. In contrast to the challenges in NLP and CV, time series problems not only add the complexity of order or temporal dependence among input sequences but also consider trend, level, and seasonality information that much of this data is valuable for decision making. The conventional training scheme has shown deficiencies regarding model overfitting, data scarcity, and privacy issues when working with transformers for a forecasting task. In this work, we propose attentive federated transformers for time series stock forecasting with better performance while preserving the privacy of participating enterprises. Empirical results on various stock data from the Yahoo! Finance website indicate the superiority of our proposed scheme in dealing with the above challenges and data heterogeneity in federated learning. |
| Date: | 2024–01 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2402.06638&r=big |
| By: | Mi Zhou; Vibhanshu Abhishek; Timothy Derdenger; Jaymo Kim; Kannan Srinivasan |
| Abstract: | This study analyzed images generated by three popular generative artificial intelligence (AI) tools - Midjourney, Stable Diffusion, and DALLE 2 - representing various occupations to investigate potential bias in AI generators. Our analysis revealed two overarching areas of concern in these AI generators, including (1) systematic gender and racial biases, and (2) subtle biases in facial expressions and appearances. Firstly, we found that all three AI generators exhibited bias against women and African Americans. Moreover, we found that the evident gender and racial biases uncovered in our analysis were even more pronounced than the status quo when compared to labor force statistics or Google images, intensifying the harmful biases we are actively striving to rectify in our society. Secondly, our study uncovered more nuanced prejudices in the portrayal of emotions and appearances. For example, women were depicted as younger with more smiles and happiness, while men were depicted as older with more neutral expressions and anger, posing a risk that generative AI models may unintentionally depict women as more submissive and less competent than men. Such nuanced biases, by their less overt nature, might be more problematic as they can permeate perceptions unconsciously and may be more difficult to rectify. Although the extent of bias varied depending on the model, the direction of bias remained consistent in both commercial and open-source AI generators. As these tools become commonplace, our study highlights the urgency to identify and mitigate various biases in generative AI, reinforcing the commitment to ensuring that AI technologies benefit all of humanity for a more inclusive future. |
| Date: | 2024–03 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2403.02726&r=big |
| By: | Yuhao Fu; Nobuyuki Hanaki |
| Abstract: | In the era of rapidly advancing artificial intelligence (AI), understanding to what extent people rely on generative AI products (AI tools), such as ChatGPT, is crucial. This study experimentally investigates whether people rely more on AI tools than their human peers in assessing the authenticity of misinformation. We quantify participants’ degree of reliance using the weight of reference (WOR) and decompose it into two stages using the activation-integration model. Our results indicate that participants exhibit a higher reliance on ChatGPT than their peers, influenced significantly by the quality of the reference and their prior beliefs. The proportion of real parts did not impact the WOR. In addition, we found that the reference source affects both the activation and integration stages, but the quality of reference only influences the second stage. |
| Date: | 2024–03 |
| URL: | http://d.repec.org/n?u=RePEc:dpr:wpaper:1233&r=big |
| By: | Martin Berka, (School of Economics and Finance, Massey University, Palmerston North); Yiran Mao (School of Economics and Finance, Massey University, Palmerston North, New Zealand) |
| Abstract: | We develop a new social media sentiment index by quantifying the tone of posts about housing on Weibo between 2010 and 2020 in 35 largest cities in China. We find that the social media sentiment index significantly predicts house price changes for up to six quarters ahead, after controlling for the economic fundamentals. A 1% increase in an accumulated social media sentiment index results in an 0.81% increase in the house price inflation the following quarter, ceteris paribus. Our results cannot be explained by changes to policy, unobserved fundamentals, or censorship bias, and survive a battery of robustness checks. We show they support theories where disperse information has direct economic effects by facilitating social learning as in Burnside et al. (2016); Bailey et al. (2018); Bayer et al. (2021) |
| Keywords: | Sentiment, social learning, house prices, China |
| Date: | 2023 |
| URL: | http://d.repec.org/n?u=RePEc:mas:dpaper:2301&r=big |
| By: | Vasilii Chsherbakov Ilia Karpov |
| Abstract: | Inflation is one of the most important macroeconomic indicators that have a great impact on the population of any country and region. Inflation is influenced by range of factors, one of which is inflation expectations. Many central banks take this factor into consideration while implementing monetary policy within the inflation targeting regime. Nowadays, a lot of people are active users of the Internet, especially social networks. There is a hypothesis that people search, read, and discuss mainly only those issues that are of particular interest to them. It is logical to assume that the dynamics of prices may also be in the focus of user discussions. So, such discussions could be regarded as an alternative source of more rapid information about inflation expectations. This study is based on unstructured data from Vkontakte social network to analyze upward and downward inflationary trends (on the example of the Omsk region). The sample of more than 8.5 million posts was collected between January 2010 and May 2022. The authors used BERT neural networks to solve the problem. These models demonstrated better results than the benchmarks (e.g., logistic regression, decision tree classifier, etc.). It makes possible to define pro-inflationary and disinflationary types of keywords in different contexts and get their visualization with SHAP method. This analysis provides additional operational information about inflationary processes at the regional level The proposed approach can be scaled for other regions. At the same time the limitation of the work is the time and power costs for the initial training of similar models for all regions of Russia. |
| Date: | 2024–02 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2403.00774&r=big |
| By: | Wessel Vermeulen; Fernanda Gutierrez Amaros |
| Abstract: | Data on online job postings represents an important source of information for local labour markets. Many countries lack statistics on labour demand that are sufficiently up-to-date and disaggregated across regions, sectors and occupations. Web-scraped data from online job postings can provide further insights on the trends in labour demand and the skills needed across regions, sectors and occupations. This paper assesses the comparability and validity between Lightcast and other data sources for Austria, Belgium, Bulgaria, Germany, Hungary, the Netherlands, Portugal, Romania, Spain and Sweden, for the years 2019 to 2022 across regions, sectors and occupations. It concludes with some recommendations for labour market analysts that want to use data on online job postings for assessing labour demand trends. |
| Keywords: | big data, Lightcast (Burning Glass), online job postings, unconventional data sources, vacancy data |
| JEL: | C89 J23 J29 J63 O50 R12 Y1 |
| Date: | 2024–03–11 |
| URL: | http://d.repec.org/n?u=RePEc:oec:cfeaaa:2024/02-en&r=big |
| By: | García-Suaza, Andres (Facultad de Economía Universidad del Rosario); Varela, Daniela (Universidad del Rosario) |
| Abstract: | Monitoring patterns of segregation and inequality at small area geographic levels is extremely costly. However, the increased availability of data through nontraditional sources such as satellite imagery facilitates this task. This paper assess the relevance of data from nightlight and day-time satellite imagery as well as building footprints and localization of points of interest for mapping variability in socioeconomic outcomes, i.e., household income, labor formality, life quality perception and household informality. The outcomes are computed at a granular level by combining census data, survey data, and small area estimation. The results reveal that non traditional sources are important to predict spatial differences socio-economic outcomes. Furthermore, the combination of all sources creates complementarities that enable a more accurate spatial distribution of the studied variables. |
| Keywords: | Remote sensing; Satellite imagery; nightlights; points of interest; spatial segregation; urban footprints; informal housing. |
| JEL: | C21 E26 R12 |
| Date: | 2024–02–13 |
| URL: | http://d.repec.org/n?u=RePEc:col:000092:021025&r=big |