|
on Big Data |
| By: | Heinemann, Friedrich; Kemper, Jan |
| Abstract: | In this analysis, we investigate ECB communication by analyzing more than 3, 800 speeches from 1999 until 2022. The study measures the attention which ECB Council members pay to various implicit and explicit monetary policy objectives. While price stability, according to the Maastricht Treaty, is the primary objective, other societal objectives can play a role for monetary policy reflections and decisions as well. A changing emphasis on alternative objectives over time but also cross-sectional differences between ECB Council members are an insightful source for current monetary policy debates. In these debates it is discussed to which extent central bank decisions may increasingly be constrained by objectives other than price stability. In addition to price stability, our analysis considers the following dimensions of a possible central bank objective function: financial stability, sovereign bond market stability, public debt, climate protection, and distribution. |
| Date: | 2022 |
| URL: | http://d.repec.org/n?u=RePEc:zbw:zewexb:2207&r=big |
| By: | Alejandro Sanchez-Becerra |
| Abstract: | Experimenters often collect baseline data to study heterogeneity. I propose the first valid confidence intervals for the VCATE, the treatment effect variance explained by observables. Conventional approaches yield incorrect coverage when the VCATE is zero. As a result, practitioners could be prone to detect heterogeneity even when none exists. The reason why coverage worsens at the boundary is that all efficient estimators have a locally-degenerate influence function and may not be asymptotically normal. I solve the problem for a broad class of multistep estimators with a predictive first stage. My confidence intervals account for higher-order terms in the limiting distribution and are fast to compute. I also find new connections between the VCATE and the problem of deciding whom to treat. The gains of targeting treatment are (sharply) bounded by half the square root of the VCATE. Finally, I document excellent performance in simulation and reanalyze an experiment from Malawi. |
| Date: | 2023–06 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2306.03363&r=big |
| By: | Travis Adams; Andrea Ajello; Diego Silva; Francisco Vazquez-Grande |
| Abstract: | We build a new measure of credit and financial market sentiment using Natural Language Processing on Twitter data. We find that the Twitter Financial Sentiment Index (TFSI) correlates highly with corporate bond spreads and other price- and survey-based measures of financial conditions. We document that overnight Twitter financial sentiment helps predict next day stock market returns. Most notably, we show that the index contains information that helps forecast changes in the U.S. monetary policy stance: a deterioration in Twitter financial sentiment the day ahead of an FOMC statement release predicts the size of restrictive monetary policy shocks. Finally, we document that sentiment worsens in response to an unexpected tightening of monetary policy. |
| Date: | 2023–05 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2305.16164&r=big |
| By: | Hong Guo; Jianwu Lin; Fanlin Huang |
| Abstract: | Market making (MM) is an important research topic in quantitative finance, the agent needs to continuously optimize ask and bid quotes to provide liquidity and make profits. The limit order book (LOB) contains information on all active limit orders, which is an essential basis for decision-making. The modeling of evolving, high-dimensional and low signal-to-noise ratio LOB data is a critical challenge. Traditional MM strategy relied on strong assumptions such as price process, order arrival process, etc. Previous reinforcement learning (RL) works handcrafted market features, which is insufficient to represent the market. This paper proposes a RL agent for market making with LOB data. We leverage a neural network with convolutional filters and attention mechanism (Attn-LOB) for feature extraction from LOB. We design a new continuous action space and a hybrid reward function for the MM task. Finally, we conduct comprehensive experiments on latency and interpretability, showing that our agent has good applicability. |
| Date: | 2023–05 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2305.15821&r=big |
| By: | Yuze Lu; Hailong Zhang; Qiwen Guo |
| Abstract: | Applications of deep learning in financial market prediction has attracted huge attention from investors and researchers. In particular, intra-day prediction at the minute scale, the dramatically fluctuating volume and stock prices within short time periods have posed a great challenge for the convergence of networks result. Informer is a more novel network, improved on Transformer with smaller computational complexity, longer prediction length and global time stamp features. We have designed three experiments to compare Informer with the commonly used networks LSTM, Transformer and BERT on 1-minute and 5-minute frequencies for four different stocks/ market indices. The prediction results are measured by three evaluation criteria: MAE, RMSE and MAPE. Informer has obtained best performance among all the networks on every dataset. Network without the global time stamp mechanism has significantly lower prediction effect compared to the complete Informer; it is evident that this mechanism grants the time series to the characteristics and substantially improves the prediction accuracy of the networks. Finally, transfer learning capability experiment is conducted, Informer also achieves a good performance. Informer has good robustness and improved performance in market prediction, which can be exactly adapted to real trading. |
| Date: | 2023–05 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2305.14382&r=big |
| By: | Harsimrat Kaeley; Ye Qiao; Nader Bagherzadeh |
| Abstract: | Stock trend analysis has been an influential time-series prediction topic due to its lucrative and inherently chaotic nature. Many models looking to accurately predict the trend of stocks have been based on Recurrent Neural Networks (RNNs). However, due to the limitations of RNNs, such as gradient vanish and long-term dependencies being lost as sequence length increases, in this paper we develop a Transformer based model that uses technical stock data and sentiment analysis to conduct accurate stock trend prediction over long time windows. This paper also introduces a novel dataset containing daily technical stock data and top news headline data spanning almost three years. Stock prediction based solely on technical data can suffer from lag caused by the inability of stock indicators to effectively factor in breaking market news. The use of sentiment analysis on top headlines can help account for unforeseen shifts in market conditions caused by news coverage. We measure the performance of our model against RNNs over sequence lengths spanning 5 business days to 30 business days to mimic different length trading strategies. This reveals an improvement in directional accuracy over RNNs as sequence length is increased, with the largest improvement being close to 18.63% at 30 business days. |
| Date: | 2023–05 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2305.14368&r=big |
| By: | Tingsong Jiang; Andy Zeng |
| Abstract: | We apply sentiment analysis in financial context using FinBERT, and build a deep neural network model based on LSTM to predict the movement of financial market movement. We apply this model on stock news dataset, and compare its effectiveness to BERT, LSTM and classical ARIMA model. We find that sentiment is an effective factor in predicting market movement. We also propose several method to improve the model. |
| Date: | 2023–06 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2306.02136&r=big |
| By: | Taeisha Nundlall; Terence L Van Zyl |
| Abstract: | Socially responsible investors build investment portfolios intending to incite social and environmental advancement alongside a financial return. Although Mean-Variance (MV) models successfully generate the highest possible return based on an investor's risk tolerance, MV models do not make provisions for additional constraints relevant to socially responsible (SR) investors. In response to this problem, the MV model must consider Environmental, Social, and Governance (ESG) scores in optimisation. Based on the prominent MV model, this study implements portfolio optimisation for socially responsible investors. The amended MV model allows SR investors to enter markets with competitive SR portfolios despite facing a trade-off between their investment Sharpe Ratio and the average ESG score of the portfolio. |
| Date: | 2023–05 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2305.12364&r=big |
| By: | Sofia Patsali (Université Côte d'Azur, France; CNRS, GREDEG); Michele Pezzoni (Université Côte d'Azur, France; CNRS, GREDEG; Observatoire des Sciences et Techniques, HCERES, France; ICRIOS, Bocconi University, Italy); Jackie Krafft (Université Côte d'Azur, France; CNRS, GREDEG) |
| Abstract: | In line with the innovation procurement literature, this work investigates the impact of becoming a supplier of a national network of excellence regrouping French hospitals on the supplier's innovative performance. It investigates whether a higher information flow from hospitals to suppliers, proxied by the supply of AI-powered medical equipment, is associated with higher innovative performance. Our empirical analysis relies on a dataset combining unprecedented granular data on procurement bids and equipment with patent data to measure the firm's innovative performance. To identify the firm's innovative activities relevant to the bid, we use an advanced neural network algorithm for text analysis linking firms' equipment descriptions with relevant patent documents. Our results show that firms becoming hospital suppliers have a significantly higher propensity to innovate. About the mechanism, we show that supplying AI-powered equipment further boosts the suppliers' innovative performance, and this raises potential important policy implications. |
| Keywords: | Innovation performance, public procurement, medical equipment, hospitals, artificial intelligence |
| JEL: | H57 D22 O31 C81 |
| Date: | 2023–03 |
| URL: | http://d.repec.org/n?u=RePEc:gre:wpaper:2023-05&r=big |
| By: | Samir Huseynov |
| Abstract: | This paper investigates the causal impact of negatively and positively framed ChatGPT Artificial Intelligence (AI) discussions on US students' anticipated labor market outcomes. Our findings reveal students reduce their confidence regarding their future earnings prospects after exposure to AI debates, and this effect is more pronounced after reading discussion excerpts with a negative tone. Unlike STEM majors, students in Non-STEM fields show asymmetric and pessimistic belief changes, suggesting that they might feel more vulnerable to emerging AI technologies. Pessimistic belief updates regarding future earnings are also prevalent across gender and GPA levels, indicating widespread AI concerns among all student subgroups. Educators, administrators, and policymakers may regularly engage with students to address their concerns and enhance educational curricula to better prepare them for a future that will be inevitably shaped by AI. |
| Date: | 2023–05 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2305.11900&r=big |
| By: | Simerjot Kaur; Andrea Stefanucci; Sameena Shah |
| Abstract: | Determining industry and product/service codes for a company is an important real-world task and is typically very expensive as it involves manual curation of data about the companies. Building an AI agent that can predict these codes automatically can significantly help reduce costs, and eliminate human biases and errors. However, unavailability of labeled datasets as well as the need for high precision results within the financial domain makes this a challenging problem. In this work, we propose a hierarchical multi-class industry code classifier with a targeted multi-label product/service code classifier leveraging advances in unsupervised representation learning techniques. We demonstrate how a high quality industry and product/service code classification system can be built using extremely limited labeled dataset. We evaluate our approach on a dataset of more than 20, 000 companies and achieved a classification accuracy of more than 92\%. Additionally, we also compared our approach with a dataset of 350 manually labeled product/service codes provided by Subject Matter Experts (SMEs) and obtained an accuracy of more than 96\% resulting in real-life adoption within the financial domain. |
| Date: | 2023–05 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2305.13532&r=big |
| By: | Abushama, Hala; Guo, Zhe; Siddig, Khalid; Kirui, Oliver K.; Abay, Kibrom A.; You, Liangzhi |
| Keywords: | REPUBLIC OF THE SUDAN; EAST AFRICA; AFRICA SOUTH OF SAHARA; AFRICA; satellite observation; data; conflicts; economic activities; nitrogen dioxide; air quality; air pollution; Sudanese Armed Forces (SAF); Rapid Support Forces (RSF) |
| Date: | 2023 |
| URL: | http://d.repec.org/n?u=RePEc:fpr:ssspwp:7&r=big |
| By: | J Bayoán Santiago Calderón; Dylan Rassier (Bureau of Economic Analysis) |
| Abstract: | With the recent proliferation of data collection and uses in the digital economy, the understanding and statistical treatment of data stocks and flows is of interest among compilers and users of national economic accounts. In this paper, we measure the value of own-account data stocks and flows for the U.S. business sector by summing the production costs of data-related activities implicit in occupations. Our method augments the traditional sum-of-costs methodology for measuring other own-account intellectual property products in national economic accounts by proxying occupation-level time-use factors using a machine learning model and the text of online job advertisements (Blackburn 2021). In our experimental estimates, we find that annual current-dollar investment in own-account data assets for the U.S. business sector grew from $84 billion in 2002 to $186 billion in 2021, with an average annual growth rate of 4.2 percent. Cumulative current-dollar investment for the period 2002–2021 was $2.6 trillion. In addition to the annual current-dollar investment, we present historical-cost net stocks, real growth rates, and effects on value-added by the industrial sector. |
| JEL: | E22 O3 O51 |
| Date: | 2022–10 |
| URL: | http://d.repec.org/n?u=RePEc:bea:wpaper:0204&r=big |
| By: | Donato Masciandaro (Department of Economics, Bocconi University); Davide Romelli (Department of Economics, Trinity College Dublin); Gaia Rubera (Department of Marketing, Bocconi University) |
| Abstract: | Monetary policy announcements of major central banks trigger substantial discussions about the policy on social media. In this paper, we use machine learning tools to identify Twitter messages related to monetary policy in a short-time window around the release of policy decisions of three major central banks, namely the ECB, the US Fed and the Bank of England. We then build an hourly measure of similarity between the tweets about monetary policy and the text of policy announcements that can be used to evaluate both the ex-ante predictability and the ex-post credibility of the announcement. We show that large differences in similarity are associated with a higher stock market and sovereign yield volatility, particularly around ECB press conferences. Our results also show a strong link between changes in similarity and asset price returns for the ECB, but less so for the Fed or the Bank of England. |
| Keywords: | monetarypolicy, centralbankcommunication, financialmarkets, socialmedia, Twitter, USFederalReserve, EuropeanCentralBank, BankofEngland. |
| JEL: | E44 E52 E58 G14 G15 G41 |
| Date: | 2023–06 |
| URL: | http://d.repec.org/n?u=RePEc:tcd:tcduee:tep1023&r=big |
| By: | Xu, Wenfei |
| Abstract: | Mid-20th urban renewal in the United States was transformational for the physical urban fabric and socioeconomic trajectories of these neighborhoods and its displaced residents. However, there is little research that systematically investigates its impacts due to incomplete national data. This article uses a multiple machine learning method to discover 204 new Census tracts that were likely sites of federal urban renewal, highway construction related demolition, and other urban renewal projects between 1949 and 1970. It also aims to understand the factors motivating the decision to “renew” certain neighborhoods. I find that race, housing age, and homeownership are all determinants of renewal. Moreover, by stratifying the analysis along neighborhoods perceived to be more or less risky, I also find that race and housing age are two distinct channels that influence renewal. |
| Date: | 2023–05–13 |
| URL: | http://d.repec.org/n?u=RePEc:osf:socarx:bsvr8&r=big |
| By: | Aadhitya A; Rajapriya R; Vineetha R S; Anurag M Bagde |
| Abstract: | Stock market is often important as it represents the ownership claims on businesses. Without sufficient stocks, a company cannot perform well in finance. Predicting a stock market performance of a company is nearly hard because every time the prices of a company stock keeps changing and not constant. So, its complex to determine the stock data. But if the previous performance of a company in stock market is known, then we can track the data and provide predictions to stockholders in order to wisely take decisions on handling the stocks to a company. To handle this, many machine learning models have been invented but they didn't succeed due to many reasons like absence of advanced libraries, inaccuracy of model when made to train with real time data and much more. So, to track the patterns and the features of data, a CNN-LSTM Neural Network can be made. Recently, CNN is now used in Natural Language Processing (NLP) based applications, so by identifying the features from stock data and converting them into tensors, we can obtain the features and then send it to LSTM neural network to find the patterns and thereby predicting the stock market for given period of time. The accuracy of the CNN-LSTM NN model is found to be high even when allowed to train on real-time stock market data. This paper describes about the features of the custom CNN-LSTM model, experiments we made with the model (like training with stock market datasets, performance comparison with other models) and the end product we obtained at final stage. |
| Date: | 2023–05 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2305.14378&r=big |
| By: | Julia M. Puaschunder (Columbia University, Graduate School of Arts and Sciences) |
| Abstract: | We live in the age of digitalization. Digital disruption is the advancement of our lifetimes. Never before in the history of humankind have human beings given up as much decision-making autonomy as today to a growing body of artificial intelligence (AI). Digitalization features a wave of self-learning entities that generate information from exponentially-growing big data sources that are encroaching every aspect of our daily lives. Inequality is one of the most significant pressing concern of our times. Ample evidence exists in economics, law and historical studies that multiple levels of inequality dominate the current socio-dynamics, politics and living conditions around the world. Social inequality stretches from societal levels within nation states to global dimensions but also intergenerational inequality domains. While digitalization and inequality are predominant features of our times, hardly any information exists on the inequality inherent in digitalization. This paper breaks new ground in theoretically arguing for inequality being an overlooked by-product of innovative change – featuring concrete examples in insights and applications in the digitalization domain. A multi-faceted analysis will draw a contemporary digital inequality account from behavioral economic, macroeconomic, comparative and legal economic perspectives. This paper targets at aiding academics and practitioners in understanding the advantages but also the potential inequalities imbued in digitalization. It sets a historic landmark to capture the Zeitgeist of our digitalization disruption heralding unexpected inequalities stemming from innovative change. The article may open eyes to understand our times holistically in its advantageous innovation capacities but also potential societal, international and intertemporal unequal gains and losses perspectives from digitalization. |
| Keywords: | AI, Artificial Intelligence, Behavioral Economics, Behavioral Macroeconomics, Big Data, Big Data Insights, Coronavirus crisis |
| Date: | 2022–06 |
| URL: | http://d.repec.org/n?u=RePEc:smo:raiswp:0201&r=big |
| By: | Aman Saggu; Lennart Ante |
| Abstract: | The introduction of OpenAI's large language model, ChatGPT, catalyzed investor attention towards artificial intelligence (AI) technologies, including AI-related crypto assets not directly related to ChatGPT. Utilizing the synthetic difference-in-difference methodology, we identify significant 'ChatGPT effects' with returns of AI-related crypto assets experiencing average returns ranging between 10.7% and 15.6% (35.5% to 41.3%) in the one-month (two-month) period after the ChatGPT launch. Furthermore, Google search volumes, a proxy for attention to AI, emerged as critical pricing indicators for AI-related crypto post-launch. We conclude that investors perceived AI-assets as possessing heightened potential or value after the launch, resulting in higher market valuations. |
| Date: | 2023–05 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2305.12739&r=big |
| By: | Minhyeok Lee |
| Abstract: | In this paper, we navigate the intricate domain of reviewer rewards in open-access academic publishing, leveraging the precision of mathematics and the strategic acumen of game theory. We conceptualize the prevailing voucher-based reviewer reward system as a two-player game, subsequently identifying potential shortcomings that may incline reviewers towards binary decisions. To address this issue, we propose and mathematically formalize an alternative reward system with the objective of mitigating this bias and promoting more comprehensive reviews. We engage in a detailed investigation of the properties and outcomes of both systems, employing rigorous game-theoretical analysis and deep reinforcement learning simulations. Our results underscore a noteworthy divergence between the two systems, with our proposed system demonstrating a more balanced decision distribution and enhanced stability. This research not only augments the mathematical understanding of reviewer reward systems, but it also provides valuable insights for the formulation of policies within journal review system. Our contribution to the mathematical community lies in providing a game-theoretical perspective to a real-world problem and in the application of deep reinforcement learning to simulate and understand this complex system. |
| Date: | 2023–05 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2305.12088&r=big |
| By: | Jaydip Sen; Aditya Jaiswal; Anshuman Pathak; Atish Kumar Majee; Kushagra Kumar; Manas Kumar Sarkar; Soubhik Maji |
| Abstract: | This paper presents a comparative analysis of the performances of three portfolio optimization approaches. Three approaches of portfolio optimization that are considered in this work are the mean-variance portfolio (MVP), hierarchical risk parity (HRP) portfolio, and reinforcement learning-based portfolio. The portfolios are trained and tested over several stock data and their performances are compared on their annual returns, annual risks, and Sharpe ratios. In the reinforcement learning-based portfolio design approach, the deep Q learning technique has been utilized. Due to the large number of possible states, the construction of the Q-table is done using a deep neural network. The historical prices of the 50 premier stocks from the Indian stock market, known as the NIFTY50 stocks, and several stocks from 10 important sectors of the Indian stock market are used to create the environment for training the agent. |
| Date: | 2023–05 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2305.17523&r=big |
| By: | Julia M. Puaschunder (The New School, New York, USA) |
| Abstract: | The Artificial Intelligence (AI) evolution is a broad set of methods, algorithms, and technologies making software human-like intelligent that is encroaching our contemporary workplace. Thinking like humans but acting rational is the primary goal of AI innovations. The current market disruption with AI lies at the core of the IT-enhanced economic growth driven by algorithms – for instance enabled via the sharing economies and big data information gains, self-check outs, online purchases and bookings, medical services social care, law, retail, logistics and finance to name a few domains in which AI leads to productivity enhancement. While we have ample account of AI entering our everyday lives, we hardly have any information about economic growth driven by AI. Preliminary studies found a negative relation between digitalization and economic growth, indicating that we lack a proper growth theory capturing the economic value imbued in AI. We also have information that indicates AI-led growth based on ICT technologies may widen an inequality-rising skilled versus unskilled labor wage gap. This paper makes the theoretical case of AI as a self-learning entity to be integrated into endogenous growth theory, which gives credit to learning and knowledge transformation as vital economic productivity ingredients. Future research may empirically validate the claim that AI as a self-learning entity is a driver of endogenous growth. All these endeavors may prepare for research on how to enhance human welfare with AI-induced growth based on inclusive AI-human compatibility and mutual exchange between machines and human beings. |
| Keywords: | Algorithms, Artificial Intelligence (AI), Digitalization, Digitalization disruption, Digital inequality, Economic growth, Endogenous growth |
| Date: | 2022–10 |
| URL: | http://d.repec.org/n?u=RePEc:smo:raiswp:0224&r=big |
| By: | Reza Nematirad; Amin Ahmadisharaf; Ali Lashgari |
| Abstract: | The US stock market experienced instability following the recession (2007-2009). COVID-19 poses a significant challenge to US stock traders and investors. Traders and investors should keep up with the stock market. This is to mitigate risks and improve profits by using forecasting models that account for the effects of the pandemic. With consideration of the COVID-19 pandemic after the recession, two machine learning models, including Random Forest and LSTM are used to forecast two major US stock market indices. Data on historical prices after the big recession is used for developing machine learning models and forecasting index returns. To evaluate the model performance during training, cross-validation is used. Additionally, hyperparameter optimizing, regularization, such as dropouts and weight decays, and preprocessing improve the performances of Machine Learning techniques. Using high-accuracy machine learning techniques, traders and investors can forecast stock market behavior, stay ahead of their competition, and improve profitability. Keywords: COVID-19, LSTM, S&P500, Random Forest, Russell 2000, Forecasting, Machine Learning, Time Series JEL Code: C6, C8, G4. |
| Date: | 2023–06 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2306.03620&r=big |
| By: | Vincent Lemaire; Gilles Pag\`es; Christian Yeo |
| Abstract: | We propose two parametric approaches to price swing contracts with firm constraints. Our objective is to create approximations for the optimal control, which represents the amounts of energy purchased throughout the contract. The first approach involves explicitly defining a parametric function to model the optimal control, and the parameters using stochastic gradient descent-based algorithms. The second approach builds on the first one, replacing the parameters with neural networks. Our numerical experiments demonstrate that by using Langevin-based algorithms, both parameterizations provide, in a short computation time, better prices compared to state-of-the-art methods (like the one given by Longstaff and Schwartz). |
| Date: | 2023–06 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2306.03822&r=big |
| By: | Andrew J. Patton; Yasin Simsek |
| Abstract: | We propose methods to improve the forecasts from generalized autoregressive score (GAS) models (Creal et. al, 2013; Harvey, 2013) by localizing their parameters using decision trees and random forests. These methods avoid the curse of dimensionality faced by kernel-based approaches, and allow one to draw on information from multiple state variables simultaneously. We apply the new models to four distinct empirical analyses, and in all applications the proposed new methods significantly outperform the baseline GAS model. In our applications to stock return volatility and density prediction, the optimal GAS tree model reveals a leverage effect and a variance risk premium effect. Our study of stock-bond dependence finds evidence of a flight-to-quality effect in the optimal GAS forest forecasts, while our analysis of high-frequency trade durations uncovers a volume-volatility effect. |
| Date: | 2023–05 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2305.18991&r=big |