|
on Computational Economics |
| By: | Chen Zhang; Giovanni Amici; Marco Morandotti |
| Abstract: | We propose a gradient-based deep learning framework to calibrate the Heston option pricing model (Heston, 1993). Our neural network, henceforth deep differential network (DDN), learns both the Heston pricing formula for plain-vanilla options and the partial derivatives with respect to the model parameters. The price sensitivities estimated by the DDN are not subject to the numerical issues that can be encountered in computing the gradient of the Heston pricing function. Thus, our network is an excellent pricing engine for fast gradient-based calibrations. Extensive tests on selected equity markets show that the DDN significantly outperforms non-differential feedforward neural networks in terms of calibration accuracy. In addition, it dramatically reduces the computational time with respect to global optimizers that do not use gradient information. |
| Date: | 2024–07 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2407.15536 |
| By: | Fernando Berzal; Alberto Garcia |
| Abstract: | Trend following and momentum investing are common strategies employed by asset managers. Even though they can be helpful in the proper situations, they are limited in the sense that they work just by looking at past, as if we were driving with our focus on the rearview mirror. In this paper, we advocate for the use of Artificial Intelligence and Machine Learning techniques to predict future market trends. These predictions, when done properly, can improve the performance of asset managers by increasing returns and reducing drawdowns. |
| Date: | 2024–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2407.13685 |
| By: | Melissa Dell |
| Abstract: | Deep learning provides powerful methods to impute structured information from large-scale, unstructured text and image datasets. For example, economists might wish to detect the presence of economic activity in satellite images, or to measure the topics or entities mentioned in social media, the congressional record, or firm filings. This review introduces deep neural networks, covering methods such as classifiers, regression models, generative AI, and embedding models. Applications include classification, document digitization, record linkage, and methods for data exploration in massive scale text and image corpora. When suitable methods are used, deep learning models can be cheap to tune and can scale affordably to problems involving millions or billions of data points.. The review is accompanied by a companion website, EconDL, with user-friendly demo notebooks, software resources, and a knowledge base that provides technical details and additional applications. |
| Date: | 2024–07 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2407.15339 |
| By: | Hurlin, Christophe (University of Orleans); Pérignon, Christophe (HEC Paris) |
| Abstract: | This survey proposes a theoretical and practical reflection on the use of machine learning methods in the context of the Internal Ratings Based (IRB) approach to banks' capital requirements. While machine learning is still rarely used in the regulatory domain (IRB, IFRS 9, stress tests), recent discussions initiated by the European Banking Authority suggest that this may change in the near future. While technically complex, this subject is crucial given growing concerns about the potential financial instability caused by the banks' use of opaque internal models. Conversely, for their proponents, machine learning models offer the prospect of better measurement of credit risk and enhancing financial inclusion. This survey yields several conclusions and recommendations regarding (i) the accuracy of risk parameter estimations, (ii) the level of regulatory capital, (iii) the trade-off between performance and interpretability, (iv) international banking competition, and (v) the governance and operational risks of machine learning models. |
| Keywords: | Banking; Machine Learning; Artificial Intelligence; Internal models; Prudential regulation; Regulatory capital |
| JEL: | C10 C38 C55 G21 G29 |
| Date: | 2023–06–25 |
| URL: | https://d.repec.org/n?u=RePEc:ebg:heccah:1480 |
| By: | Liyang Wang; Yu Cheng; Xingxin Gu; Zhizhong Wu |
| Abstract: | With the increasing complexity of financial markets and rapid growth in data volume, traditional risk monitoring methods no longer suffice for modern financial institutions. This paper designs and optimizes a risk monitoring system based on big data and machine learning. By constructing a four-layer architecture, it effectively integrates large-scale financial data and advanced machine learning algorithms. Key technologies employed in the system include Long Short-Term Memory (LSTM) networks, Random Forest, Gradient Boosting Trees, and real-time data processing platform Apache Flink, ensuring the real-time and accurate nature of risk monitoring. Research findings demonstrate that the system significantly enhances efficiency and accuracy in risk management, particularly excelling in identifying and warning against market crash risks. |
| Date: | 2024–07 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2407.19352 |
| By: | Nacira Agram; Bernt {\O}ksendal; Jan Rems |
| Abstract: | We propose a deep learning approach to study the minimal variance pricing and hedging problem in an incomplete jump diffusion market. It is based upon a rigorous stochastic calculus derivation of the optimal hedging portfolio, optimal option price, and the corresponding equivalent martingale measure through the means of the Stackelberg game approach. A deep learning algorithm based on the combination of the feedforward and LSTM neural networks is tested on three different market models, two of which are incomplete. In contrast, the complete market Black-Scholes model serves as a benchmark for the algorithm's performance. The results that indicate the algorithm's good performance are presented and discussed. In particular, we apply our results to the special incomplete market model studied by Merton and give a detailed comparison between our results based on the minimal variance principle and the results obtained by Merton based on a different pricing principle. Using deep learning, we find that the minimal variance principle leads to typically higher option prices than those deduced from the Merton principle. On the other hand, the minimal variance principle leads to lower losses than the Merton principle. |
| Date: | 2024–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2407.13688 |
| By: | Chunhui Qiao; Xiangwei Wan |
| Abstract: | This paper proposes a deep delta hedging framework for options, utilizing neural networks to learn the residuals between the hedging function and the implied Black-Scholes delta. This approach leverages the smoother properties of these residuals, enhancing deep learning performance. Utilizing ten years of daily S&P 500 index option data, our empirical analysis demonstrates that learning the residuals, using the mean squared one-step hedging error as the loss function, significantly improves hedging performance over directly learning the hedging function, often by more than 100%. Adding input features when learning the residuals enhances hedging performance more for puts than calls, with market sentiment being less crucial. Furthermore, learning the residuals with three years of data matches the hedging performance of directly learning with ten years of data, proving that our method demands less data. |
| Date: | 2024–07 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2407.19367 |
| By: | Han Gui |
| Abstract: | To predict the future movements of stock markets, numerous studies concentrate on daily data and employ various machine learning (ML) models as benchmarks that often vary and lack standardization across different research works. This paper tries to solve the problem from a fresh standpoint by aiming to predict the weekly movements, and introducing a novel benchmark of random traders. This benchmark is independent of any ML model, thus making it more objective and potentially serving as a commonly recognized standard. During training process, apart from the basic features such as technical indicators, scaling laws and directional changes are introduced as additional features, furthermore, the training datasets are also adjusted by assigning varying weights to different samples, the weighting approach allows the models to emphasize specific samples. On back-testing, several trained models show good performance, with the multi-layer perception (MLP) demonstrating stability and robustness across extensive and comprehensive data that include upward, downward and cyclic trends. The unique perspective of this work that focuses on weekly movements, incorporates new features and creates an objective benchmark, contributes to the existing literature on stock market prediction. |
| Date: | 2024–07 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2407.09831 |
| By: | Patrick Rehill |
| Abstract: | Machine learning methods for estimating treatment effect heterogeneity promise greater flexibility than existing methods that test a few pre-specified hypotheses. However, one problem these methods can have is that it can be challenging to extract insights from complicated machine learning models. A high-dimensional distribution of conditional average treatment effects may give accurate, individual-level estimates, but it can be hard to understand the underlying patterns; hard to know what the implications of the analysis are. This paper proposes the Distilled Causal Tree, a method for distilling a single, interpretable causal tree from a causal forest. This compares well to existing methods of extracting a single tree, particularly in noisy data or high-dimensional data where there are many correlated features. Here it even outperforms the base causal forest in most simulations. Its estimates are doubly robust and asymptotically normal just as those of the causal forest are. |
| Date: | 2024–08 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2408.01023 |
| By: | Cesare Carissimo; Marcin Korecki |
| Abstract: | We gather many perspectives on Capital and synthesize their commonalities. We provide a characterization of Capital as a historical agential system and propose a model of Capital using tools from computer science. Our model consists of propositions which, if satisfied by a specific grounding, constitute a valid model of Capital. We clarify the manners in which Capital can evolve. We claim that, when its evolution is driven by quantitative optimization processes, Capital can possess qualities of Artificial Intelligence. We find that Capital may not uniquely represent meaning, in the same way that optimization is not intentionally meaningful. We find that Artificial Intelligences like modern day Large Language Models are a part of Capital. We link our readers to a web-interface where they can interact with a part of Capital. |
| Date: | 2024–07 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2407.16314 |
| By: | Aditya Saxena; Dr Parizad Dungore |
| Abstract: | Credit ratings are becoming one of the primary references for financial institutions of the country to assess credit risk in order to accurately predict the likelihood of business failure of an individual or an enterprise. Financial institutions, therefore, depend on credit rating tools and services to help them predict the ability of creditors to meet financial persuasions. Conventional credit rating is broadly categorized into two classes namely: good credit and bad credit. This approach lacks adequate precision to perform credit risk analysis in practice. Related studies have shown that data-driven machine learning algorithms outperform many conventional statistical approaches in solving this type of problem, both in terms of accuracy and efficiency. The purpose of this paper is to construct and validate a credit risk assessment model using Linear Discriminant Analysis as a dimensionality reduction technique to discriminate good creditors from bad ones and identify the best classifier for credit assessment of commercial banks based on real-world data. This will help commercial banks to avoid monetary losses and prevent financial crisis |
| Date: | 2024–07 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2407.12044 |
| By: | Dangxing Chen; Yuan Gao |
| Abstract: | Over the past few decades, machine learning models have been extremely successful. As a result of axiomatic attribution methods, feature contributions have been explained more clearly and rigorously. There are, however, few studies that have examined domain knowledge in conjunction with the axioms. In this study, we examine asset pricing in finance, a field closely related to risk management. Consequently, when applying machine learning models, we must ensure that the attribution methods reflect the underlying risks accurately. In this work, we present and study several axioms derived from asset pricing domain knowledge. It is shown that while Shapley value and Integrated Gradients preserve most axioms, neither can satisfy all axioms. Using extensive analytical and empirical examples, we demonstrate how attribution methods can reflect risks and when they should not be used. |
| Date: | 2024–07 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2407.08953 |
| By: | Siqiao Zhao; Zhikang Dong; Zeyu Cao; Raphael Douady |
| Abstract: | When constructing portfolios, a key problem is that a lot of financial time series data are sparse, making it challenging to apply machine learning methods. Polymodel theory can solve this issue and demonstrate superiority in portfolio construction from various aspects. To implement the PolyModel theory for constructing a hedge fund portfolio, we begin by identifying an asset pool, utilizing over 10, 000 hedge funds for the past 29 years' data. PolyModel theory also involves choosing a wide-ranging set of risk factors, which includes various financial indices, currencies, and commodity prices. This comprehensive selection mirrors the complexities of the real-world environment. Leveraging on the PolyModel theory, we create quantitative measures such as Long-term Alpha, Long-term Ratio, and SVaR. We also use more classical measures like the Sharpe ratio or Morningstar's MRAR. To enhance the performance of the constructed portfolio, we also employ the latest deep learning techniques (iTransformer) to capture the upward trend, while efficiently controlling the downside, using all the features. The iTransformer model is specifically designed to address the challenges in high-dimensional time series forecasting and could largely improve our strategies. More precisely, our strategies achieve better Sharpe ratio and annualized return. The above process enables us to create multiple portfolio strategies aiming for high returns and low risks when compared to various benchmarks. |
| Date: | 2024–08 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2408.03320 |
| By: | Alex Kim; Maximilian Muhn; Valeri Nikolaev |
| Abstract: | We investigate whether an LLM can successfully perform financial statement analysis in a way similar to a professional human analyst. We provide standardized and anonymous financial statements to GPT4 and instruct the model to analyze them to determine the direction of future earnings. Even without any narrative or industry-specific information, the LLM outperforms financial analysts in its ability to predict earnings changes. The LLM exhibits a relative advantage over human analysts in situations when the analysts tend to struggle. Furthermore, we find that the prediction accuracy of the LLM is on par with the performance of a narrowly trained state-of-the-art ML model. LLM prediction does not stem from its training memory. Instead, we find that the LLM generates useful narrative insights about a company's future performance. Lastly, our trading strategies based on GPT's predictions yield a higher Sharpe ratio and alphas than strategies based on other models. Taken together, our results suggest that LLMs may take a central role in decision-making. |
| Date: | 2024–07 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2407.17866 |
| By: | Alireza Mohammadshafie; Akram Mirzaeinia; Haseebullah Jumakhan; Amir Mirzaeinia |
| Abstract: | Recent deep reinforcement learning (DRL) methods in finance show promising outcomes. However, there is limited research examining the behavior of these DRL algorithms. This paper aims to investigate their tendencies towards holding or trading financial assets as well as purchase diversity. By analyzing their trading behaviors, we provide insights into the decision-making processes of DRL models in finance applications. Our findings reveal that each DRL algorithm exhibits unique trading patterns and strategies, with A2C emerging as the top performer in terms of cumulative rewards. While PPO and SAC engage in significant trades with a limited number of stocks, DDPG and TD3 adopt a more balanced approach. Furthermore, SAC and PPO tend to hold positions for shorter durations, whereas DDPG, A2C, and TD3 display a propensity to remain stationary for extended periods. |
| Date: | 2024–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2407.09557 |
| By: | Qiqin Zhou |
| Abstract: | In the contemporary financial landscape, accurately predicting the probability of filling a Request-For-Quote (RFQ) is crucial for improving market efficiency for less liquid asset classes. This paper explores the application of explainable AI (XAI) models to forecast the likelihood of RFQ fulfillment. By leveraging advanced algorithms including Logistic Regression, Random Forest, XGBoost and Bayesian Neural Tree, we are able to improve the accuracy of RFQ fill rate predictions and generate the most efficient quote price for market makers. XAI serves as a robust and transparent tool for market participants to navigate the complexities of RFQs with greater precision. |
| Date: | 2024–07 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2407.15038 |
| By: | Felix Drinkall; Janet B. Pierrehumbert; Stefan Zohren |
| Abstract: | Large Language Models (LLMs) have been shown to perform well for many downstream tasks. Transfer learning can enable LLMs to acquire skills that were not targeted during pre-training. In financial contexts, LLMs can sometimes beat well-established benchmarks. This paper investigates how well LLMs perform in the task of forecasting corporate credit ratings. We show that while LLMs are very good at encoding textual information, traditional methods are still very competitive when it comes to encoding numeric and multimodal data. For our task, current LLMs perform worse than a more traditional XGBoost architecture that combines fundamental and macroeconomic data with high-density text-based embedding features. |
| Date: | 2024–07 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2407.17624 |
| By: | Simon Hirsch; Jonathan Berrisch; Florian Ziel |
| Abstract: | Large-scale streaming data are common in modern machine learning applications and have led to the development of online learning algorithms. Many fields, such as supply chain management, weather and meteorology, energy markets, and finance, have pivoted towards using probabilistic forecasts, which yields the need not only for accurate learning of the expected value but also for learning the conditional heteroskedasticity and conditional distribution moments. Against this backdrop, we present a methodology for online estimation of regularized, linear distributional models. The proposed algorithm is based on a combination of recent developments for the online estimation of LASSO models and the well-known GAMLSS framework. We provide a case study on day-ahead electricity price forecasting, in which we show the competitive performance of the incremental estimation combined with strongly reduced computational effort. Our algorithms are implemented in a computationally efficient Python package. |
| Date: | 2024–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2407.08750 |
| By: | Yuan Li; Bingqiao Luo; Qian Wang; Nuo Chen; Xu Liu; Bingsheng He |
| Abstract: | The utilization of Large Language Models (LLMs) in financial trading has primarily been concentrated within the stock market, aiding in economic and financial decisions. Yet, the unique opportunities presented by the cryptocurrency market, noted for its on-chain data's transparency and the critical influence of off-chain signals like news, remain largely untapped by LLMs. This work aims to bridge the gap by developing an LLM-based trading agent, CryptoTrade, which uniquely combines the analysis of on-chain and off-chain data. This approach leverages the transparency and immutability of on-chain data, as well as the timeliness and influence of off-chain signals, providing a comprehensive overview of the cryptocurrency market. CryptoTrade incorporates a reflective mechanism specifically engineered to refine its daily trading decisions by analyzing the outcomes of prior trading decisions. This research makes two significant contributions. Firstly, it broadens the applicability of LLMs to the domain of cryptocurrency trading. Secondly, it establishes a benchmark for cryptocurrency trading strategies. Through extensive experiments, CryptoTrade has demonstrated superior performance in maximizing returns compared to traditional trading strategies and time-series baselines across various cryptocurrencies and market conditions. Our code and data are available at \url{https://anonymous.4open.science/r/C ryptoTrade-Public-92FC/}. |
| Date: | 2024–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2407.09546 |
| By: | Bonelli, Maxime (HEC Paris) |
| Abstract: | Using data technologies, like machine learning, investors can gain a comparative advantage in forecasting outcomes frequently observed in historical data. I investigate the implications for capital allocation using venture capitalists (VCs) as a laboratory. VCs adopting data technologies tilt their investments towards startups developing businesses similar to those already explored, and become better at avoiding failures within this pool. However, these VCs become concurrently less likely to pick startups achieving rare major success. Plausibly exogenous variations in VCs' screening automation suggest a causality between data technologies adoption and these effects. These findings highlight potential downsides of investors embracing data technologies. |
| Keywords: | big data; machine learning; artificial intelligence; venture capital; entrepreneurship; innovation; capital allocation |
| JEL: | G24 L26 O30 |
| Date: | 2023–02–22 |
| URL: | https://d.repec.org/n?u=RePEc:ebg:heccah:1470 |
| By: | Hafsa Lemsieh (UH2MC - Université Hassan II [Casablanca]); Ibtissam Abarar |
| Abstract: | In that emerging digital era, Artificial Intelligence technology headed by machine learning, digital-smart technologies as well as the Big Data that allows predictive analysis has a significant influence over many people precisely those who are not all conscious and aware that the datasets are assembled from their online interactions and activities, consequently it can be used to anticipate and manipulate their purchasing psychology and behavior out of their control. In these terms, this study is going to present the literature that is in relation basically with the approach to the contribution of the artificial intelligence technology in manipulating the purchasing behavior based on the psychological factor. To guide this in deep study we will include multiple sources of the secondary data, going from journal articles, conference papers, internet sources and so on. The main objective is to bridge and eliminate the gap in this somehow empty field of research. The theoretical conclusions will offer an insight about the main importance in terms of implementing the artificial intelligence tools in the field and the department of marketing as a successful way to understand the consumers preferences and their journey in terms of purchasing. The goal is to provide predictive analysis and to know precisely how to manipulate the psychology of consumers in order to influence their behavior. The generation Z are a real opportunity to achieve this aim since they are digitally native and most of their purchasing decisions occurs through the use of their smartphones as they rely on social media for collecting and gathering any kind of information |
| Keywords: | Artificial intelligence, Consumer behaviour, Digital Marketing, Manipulation, Psychology., Artificial intelligence Consumer behaviour Digital Marketing Manipulation Psychology. JEL Classification: M31 M15 D91 Type du papier: Theoretical Research, Psychology. JEL Classification: M31, M15, D91 Type du papier: Theoretical Research |
| Date: | 2024–06–23 |
| URL: | https://d.repec.org/n?u=RePEc:hal:journl:hal-04629533 |
| By: | Adam Bahelka; Harmen de Weerd |
| Abstract: | Inflation is one of the most important economic indicators closely watched by both public institutions and private agents. This study compares the performance of a traditional econometric model, Mixed Data Sampling regression, with one of the newest developments from the field of Artificial Intelligence, a foundational time series forecasting model based on a Long short-term memory neural network called Lag-Llama, in their ability to nowcast the Harmonized Index of Consumer Prices in the Euro area. Two models were compared and assessed whether the Lag-Llama can outperform the MIDAS regression, ensuring that the MIDAS regression is evaluated under the best-case scenario using a dataset spanning from 2010 to 2022. The following metrics were used to evaluate the models: Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), Mean Squared Error (MSE), correlation with the target, R-squared and adjusted R-squared. The results show better performance of the pre-trained Lag-Llama across all metrics. |
| Date: | 2024–07 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2407.08510 |
| By: | Xiaohui Victor Li; Francesco Sanna Passino |
| Abstract: | Dynamic knowledge graphs (DKGs) are popular structures to express different types of connections between objects over time. They can also serve as an efficient mathematical tool to represent information extracted from complex unstructured data sources, such as text or images. Within financial applications, DKGs could be used to detect trends for strategic thematic investing, based on information obtained from financial news articles. In this work, we explore the properties of large language models (LLMs) as dynamic knowledge graph generators, proposing a novel open-source fine-tuned LLM for this purpose, called the Integrated Contextual Knowledge Graph Generator (ICKG). We use ICKG to produce a novel open-source DKG from a corpus of financial news articles, called FinDKG, and we propose an attention-based GNN architecture for analysing it, called KGTransformer. We test the performance of the proposed model on benchmark datasets and FinDKG, demonstrating superior performance on link prediction tasks. Additionally, we evaluate the performance of the KGTransformer on FinDKG for thematic investing, showing it can outperform existing thematic ETFs. |
| Date: | 2024–07 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2407.10909 |
| By: | Atin Aboutorabi; Ga\'etan de Rassenfosse |
| Abstract: | Macroeconomic data are crucial for monitoring countries' performance and driving policy. However, traditional data acquisition processes are slow, subject to delays, and performed at a low frequency. We address this 'ragged-edge' problem with a two-step framework. The first step is a supervised learning model predicting observed low-frequency figures. We propose a neural-network-based nowcasting model that exploits mixed-frequency, high-dimensional data. The second step uses the elasticities derived from the previous step to interpolate unobserved high-frequency figures. We apply our method to nowcast countries' yearly research and development (R&D) expenditure series. These series are collected through infrequent surveys, making them ideal candidates for this task. We exploit a range of predictors, chiefly Internet search volume data, and document the relevance of these data in improving out-of-sample predictions. Furthermore, we leverage the high frequency of our data to derive monthly estimates of R&D expenditures, which are currently unobserved. We compare our results with those obtained from the classical regression-based and the sparse temporal disaggregation methods. Finally, we validate our results by reporting a strong correlation with monthly R&D employment data. |
| Date: | 2024–07 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2407.11765 |
| By: | Si, Yafei; Yang, Yuyi; Wang, Xi; An, Ruopeng; Zu, Jiaqi; Chen, Xi; Fan, Xiaojing; Gong, Sen |
| Abstract: | Using simulated patients to mimic nine established non-communicable and infectious diseases over 27 trials, we assess ChatGPT's effectiveness and reliability in diagnosing and treating common diseases in low- and middle-income countries. We find ChatGPT's performance varied within a single disease, despite a high level of accuracy in both correct diagnosis (74.1%) and medication prescription (84.5%). Additionally, ChatGPT recommended a concerning level of unnecessary or harmful medications (85.2%) even with correct diagnoses. Finally, ChatGPT performed better in managing non-communicable diseases compared to infectious ones. These results highlight the need for cautious AI integration in healthcare systems to ensure quality and safety. |
| Keywords: | ChatGPT, Large Language Models, Generative AI, Simulated Patient, Healthcare, Quality, Safety, Low- and Middle-Income Countries |
| JEL: | C0 I10 I11 C90 |
| Date: | 2024 |
| URL: | https://d.repec.org/n?u=RePEc:zbw:glodps:1472 |
| By: | Vincent Ragel; Damien Challet |
| Abstract: | Reinforcement learning works best when the impact of the agent's actions on its environment can be perfectly simulated or fully appraised from available data. Some systems are however both hard to simulate and very sensitive to small perturbations. An additional difficulty arises when an RL agent must learn to be part of a multi-agent system using only anonymous data, which makes it impossible to infer the state of each agent, thus to use data directly. Typical examples are competitive systems without agent-resolved data such as financial markets. We introduce consistent data time travel for offline RL as a remedy for these problems: instead of using historical data in a sequential way, we argue that one needs to perform time travel in historical data, i.e., to adjust the time index so that both the past state and the influence of the RL agent's action on the state coincide with real data. This both alleviates the need to resort to imperfect models and consistently accounts for both the immediate and long-term reactions of the system when using anonymous historical data. We apply this idea to market making in limit order books, a notoriously difficult task for RL; it turns out that the gain of the agent is significantly higher with data time travel than with naive sequential data, which suggests that the difficulty of this task for RL may have been overestimated. |
| Date: | 2024–08 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2408.02322 |
| By: | Lionel Fontagn\'e; Francesca Micocci; Armando Rungi |
| Abstract: | This paper introduces a causal machine learning approach to investigate the impact of the EU-Canada Comprehensive Economic Trade Agreement (CETA). We propose a matrix completion algorithm on French customs data to obtain multidimensional counterfactuals at the firm, product and destination levels. We find a small but significant positive impact on average at the product-level intensive margin. On the other hand, the extensive margin shows product churning due to the treaty beyond regular entry-exit dynamics: one product in eight that was not previously exported substitutes almost as many that are no longer exported. When we delve into the heterogeneity, we find that the effects of the treaty are higher for products at a comparative advantage. Focusing on multiproduct firms, we find that they adjust their portfolio in Canada by reallocating towards their first and most exported product due to increasing local market competition after trade liberalization. Finally, multidimensional counterfactuals allow us to evaluate the general equilibrium effect of the CETA. Specifically, we observe trade diversion, as exports to other destinations are re-directed to Canada. |
| Date: | 2024–07 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2407.07652 |
| By: | Zantsi, Siphe; Mack, Gabriele; Möhring, Anke; Cloete, Kandas; Greyling, Jan C; Mann, Stefan |
| Abstract: | This paper wants to make the case that agent-based modelling may contribute to provide support for the difficult process of South Africa’s land reform by running scenarios that then do not need to be explored in practice. An agent-based model (ILUPSA) was developed from a database of 605 commercial farmers and 833 commercially oriented smallholders, which are the potential land redistribution beneficiaries. Three scenarios are simulated (1) when a willing buyer- willing seller mechanism (WB-WS) is used to acquire land (baseline scenario), (2) WB- WS whereas redistributed land is subdivided into viable emerging farm parcels and (3) when less productive farms are expropriated. Simulation results shows that under WB-WS only 14% of commercial farmland becomes available for redistribution. Ninety-nine percent of this land is for grazing and the remainder is field crop and horticultural land. The redistribution becomes even more marginal when only farmland with low productivity is expropriated (less than a quarter of the land that becomes available in the baseline scenario). An estimated amount of R50 billion will be required to implement land redistribution. |
| Keywords: | Agricultural and Food Policy, Farm Management |
| Date: | 2024–08–07 |
| URL: | https://d.repec.org/n?u=RePEc:ags:cfcp15:344233 |
| By: | Preetha Saha; Jingrao Lyu; Dhruv Desai; Rishab Chauhan; Jerinsh Jeyapaulraj; Philip Sommer; Dhagash Mehta |
| Abstract: | The trading ecosystem of the Municipal (muni) bond is complex and unique. With nearly 2\% of securities from over a million securities outstanding trading daily, determining the value or relative value of a bond among its peers is challenging. Traditionally, relative value calculation has been done using rule-based or heuristics-driven approaches, which may introduce human biases and often fail to account for complex relationships between the bond characteristics. We propose a data-driven model to develop a supervised similarity framework for the muni bond market based on CatBoost algorithm. This algorithm learns from a large-scale dataset to identify bonds that are similar to each other based on their risk profiles. This allows us to evaluate the price of a muni bond relative to a cohort of bonds with a similar risk profile. We propose and deploy a back-testing methodology to compare various benchmarks and the proposed methods and show that the similarity-based method outperforms both rule-based and heuristic-based methods. |
| Date: | 2024–08 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2408.02273 |
| By: | Mingshu Li; Bhaskarjit Sarmah; Dhruv Desai; Joshua Rosaler; Snigdha Bhagat; Philip Sommer; Dhagash Mehta |
| Abstract: | Due to the dynamic nature of financial markets, maintaining models that produce precise predictions over time is difficult. Often the goal isn't just point prediction but determining uncertainty. Quantifying uncertainty, especially the aleatoric uncertainty due to the unpredictable nature of market drivers, helps investors understand varying risk levels. Recently, quantile regression forests (QRF) have emerged as a promising solution: Unlike most basic quantile regression methods that need separate models for each quantile, quantile regression forests estimate the entire conditional distribution of the target variable with a single model, while retaining all the salient features of a typical random forest. We introduce a novel approach to compute quantile regressions from random forests that leverages the proximity (i.e., distance metric) learned by the model and infers the conditional distribution of the target variable. We evaluate the proposed methodology using publicly available datasets and then apply it towards the problem of forecasting the average daily volume of corporate bonds. We show that using quantile regression using Random Forest proximities demonstrates superior performance in approximating conditional target distributions and prediction intervals to the original version of QRF. We also demonstrate that the proposed framework is significantly more computationally efficient than traditional approaches to quantile regressions. |
| Date: | 2024–08 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2408.02355 |
| By: | Yoontae Hwang; Stefan Zohren; Yongjae Lee |
| Abstract: | In the era of rapid globalization and digitalization, accurate identification of similar stocks has become increasingly challenging due to the non-stationary nature of financial markets and the ambiguity in conventional regional and sector classifications. To address these challenges, we examine SimStock, a novel temporal self-supervised learning framework that combines techniques from self-supervised learning (SSL) and temporal domain generalization to learn robust and informative representations of financial time series data. The primary focus of our study is to understand the similarities between stocks from a broader perspective, considering the complex dynamics of the global financial landscape. We conduct extensive experiments on four real-world datasets with thousands of stocks and demonstrate the effectiveness of SimStock in finding similar stocks, outperforming existing methods. The practical utility of SimStock is showcased through its application to various investment strategies, such as pairs trading, index tracking, and portfolio optimization, where it leads to superior performance compared to conventional methods. Our findings empirically examine the potential of data-driven approach to enhance investment decision-making and risk management practices by leveraging the power of temporal self-supervised learning in the face of the ever-changing global financial landscape. |
| Date: | 2024–07 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2407.13751 |
| By: | Flora Lutz; Yuanchen Yang; Chengyu Huang |
| Abstract: | Canada’s muted productivity growth during recent years has sparked concerns about the country’s investment climate. In this study, we develop a new natural language processing (NPL) based indicator, mining the richness of Twitter (now X) accounts to measure trends in the public perceptions of Canada’s investment climate. We find that while the Canadian investment climate appears to be generally favorable, there are signs of slippage in some categories in recent periods, such as with respect to governance and infrastructure. This result is confirmed by both survey-based and NLP-based indicators. We also find that our NLP-based indicators would suggest that perceptions of Canada’s investment climate are similar to perceptions of U.S. investment climate, except with respect to governance, where views of U.S. governance are notably more negative. Comparing our novel indicator relative to traditional survey-based indicators, we find that the NLP-based indicators are statistically significant in helping to predict investment flows, similar to survey-based measures. Meanwhile, the new NLP-based indicator offers insights into the nuances of data, allowing us to identify specific grievances. Finally, we construct a similar indicator for the U.S. and compare trends across countries. |
| Keywords: | Investment Climate; Canada; Machine Learning; Sentiment Analysis; muted productivity growth; investmest climate; investment flow; NLP-based indicator; Climate finance; Competition; Infrastructure; Productivity; Mining sector; Global |
| Date: | 2024–07–26 |
| URL: | https://d.repec.org/n?u=RePEc:imf:imfwpa:2024/165 |
| By: | Araujo, Inacio F. (Departamento de Economia, Universidade de São Paulo); Donaghy, Kieran P. (Department of City and Regional Planning, Cornell University); Haddad, Eduardo A. (Departamento de Economia, Universidade de São Paulo); Hewings, Geoffrey J.D. (Department of Urban & Regional Planning, University of Illinois Urbana-Champaign) |
| Abstract: | This study develops a methodology to assess the effects of extreme events. This method measures the geographic propagation of indirect impacts of disasters through supply chains. This modeling framework incorporates an inter-regional input-output system to calibrate a computable general equilibrium model. Our methodological approach includes examining the supply and demand constraints caused by the disruptive event. We also model regional resilience through input substitution possibilities. To illustrate the applicability of the methodology, we analyze the higher-order effects of the regional ISIS-created conflict in Iraq between 2014 and 2017. We also extend the general equilibrium model to downscale Iraq’s national economic accounts to the regional level. This strategy projects the post-conflict Iraqi economy at a granular level of spatial aggregation. The model produced for this analysis offers policymakers simulations to identify economic vulnerabilities at the regional and industrial levels and explore alternatives to mitigate the damage caused by extreme events. |
| Keywords: | armed conflict; costs of war; risk analysis; disruptive events; higher-order impacts; CGE model |
| JEL: | C68 R13 |
| Date: | 2024–08–02 |
| URL: | https://d.repec.org/n?u=RePEc:ris:nereus:2024_006 |
| By: | Amirreza Talebi |
| Abstract: | Discrete choice models (DCMs) have been widely utilized in various scientific fields, especially economics, for many years. These models consider a stochastic environment influencing each decision maker's choices. Extensive research has shown that the agents' socioeconomic characteristics, the chosen options' properties, and the conditions characterizing the decision-making environment all impact these models. However, the complex interactions between these factors, confidentiality concerns, time constraints, and costs, have made real experimentation impractical and undesirable. To address this, simulations have gained significant popularity among academics, allowing the study of these models in a controlled setting using simulated data. This paper presents multidisciplinary research to bridge the gap between DCMs, experimental design, and simulation. By reviewing related literature, the authors explore these interconnected areas. We then introduce a simulation method integrated with experimental design to generate synthetic data based on behavioral models of agents. A utility function is used to describe the developed simulation tool. The paper investigates the discrepancy between simulated data and real-world data. |
| Date: | 2024–07 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2407.17014 |
| By: | Pascal Fran\c{c}ois; Genevi\`eve Gauthier; Fr\'ed\'eric Godin; Carlos Octavio P\'erez Mendoza |
| Abstract: | The recent work of Horikawa and Nakagawa (2024) claims that under a complete market admitting statistical arbitrage, the difference between the hedging position provided by deep hedging and that of the replicating portfolio is a statistical arbitrage. This raises concerns as it entails that deep hedging can include a speculative component aimed simply at exploiting the structure of the risk measure guiding the hedging optimisation problem. We test whether such finding remains true in a GARCH-based market model. We observe that the difference between deep hedging and delta hedging can be a statistical arbitrage if the risk measure considered does not put sufficient relative weight on adverse outcomes. Nevertheless, a suitable choice of risk measure can prevent the deep hedging agent from including a speculative overlay within its hedging strategy. |
| Date: | 2024–07 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2407.14736 |