nep-cmp New Economics Papers
on Computational Economics
Issue of 2022‒06‒20
twenty papers chosen by
Stan Miles
Thompson Rivers University

  1. Machine Learning for Economists: An Introduction By Sonan Memon
  2. Calibrating for Class Weights by Modeling Machine Learning By Andrew Caplin; Daniel Martin; Philip Marx
  3. Deep Stochastic Optimization in Finance By A. Max Reppen; H. Mete Soner; Valentin Tissot-Daguette
  4. HARNet: A convolutional neural network for realized volatility forecasting By Reisenhofer, Rafael; Bayer, Xandro; Hautsch, Nikolaus
  5. Machine learning techniques in joint default assessment By Margherita Doria; Elisa Luciano; Patrizia Semeraro
  6. A basic macroeconomic agent-based model for analyzing monetary regime shifts By Florian Peters; Doris Neuberger; Oliver Reinhardt; Adelinde Uhrmacher
  7. Machine Learning Methods: Potential for Deposit Insurance By Ryan Defina
  8. Deep learning based Chinese text sentiment mining and stock market correlation research By Chenrui Zhang
  9. On learning agent-based models from data By Corrado Monti; Marco Pangallo; Gianmarco De Francisci Morales; Francesco Bonchi
  10. MIRAGRODEP-AEZ 1.0: Documentation By Bouët, Antoine; Laborde Debucquet, David; Traoré, Fousseini
  11. AI Watch: Revisiting Technology Readiness Levels for relevant Artificial Intelligence technologies By MARTINEZ PLUMED Fernando; CABALLERO BENÍTEZ Fernando; CASTELLANO FALCÓN David; FERNANDEZ LLORCA David; GOMEZ Emilia; HUPONT TORRES Isabelle; MERINO Luis; MONSERRAT Carlos; HERNÁNDEZ ORALLO José
  12. Gamma and Vega Hedging Using Deep Distributional Reinforcement Learning By Jay Cao; Jacky Chen; Soroush Farghadani; John Hull; Zissis Poulos; Zeyu Wang; Jun Yuan
  13. Risk Aversion In Learning Algorithms and an Application To Recommendation Systems By Andreas Haupt; Aroon Narayanan
  14. Randomized geometric tools for anomaly detection in stock markets By Cyril Bachelard; Apostolos Chalkis; Vissarion Fisikopoulos; Elias Tsigaridas
  15. Three Families of Automated Text Analysis By van Loon, Austin
  16. A time-varying study of Chinese investor sentiment, stock market liquidity and volatility: Based on deep learning BERT model and TVP-VAR model By Chenrui Zhang; Xinyi Wu; Hailu Deng; Huiwei Zhang
  17. Differentiating artificial intelligence capability clusters in Australia By Bratanova, Alexandra; Pham, Hien; Mason, Claire; Hajkowicz, Stefan; Naughtin, Claire; Schleiger, Emma; Sanderson, Conrad; Chen, Caron; Karimi, Sarvnaz
  18. Large Scale Probabilistic Simulation of Renewables Production By Mike Ludkovski; Glen Swindle; Eric Grannan
  19. The Right Tool for the Job: Matching Active Learning Techniques to Learning Objectives By Sarah A. Jacobson; Luyao Zhang; Jiasheng Zhu
  20. AI Watch: Estimating AI investments in the European Union By Tatjana Evas; Maikki Sipinen; Martin Ulbrich; Alessandro Dalla Benetta; Maciej Sobolewski; Daniel Nepelski

  1. By: Sonan Memon (Pakistan Institute of Development Economics)
    Abstract: Machine Learning (henceforth ML) refers to the set of algorithms and computational methods which enable computers to learn patterns from training data without being explicitly programmed to do so.[1] ML uses training data to learn patterns by estimating a mathematical model and making predictions in out of sample based on new or unseen input data. ML has the tremendous capacity to discover complex, flexible and crucially generalisable structure in training data.
    Keywords: Machine Learning, Economists, Introduction
    Date: 2021
    URL: http://d.repec.org/n?u=RePEc:pid:kbrief:2021:33&r=
  2. By: Andrew Caplin; Daniel Martin; Philip Marx
    Abstract: A much studied issue is the extent to which the confidence scores provided by machine learning algorithms are calibrated to ground truth probabilities. Our starting point is that calibration is seemingly incompatible with class weighting, a technique often employed when one class is less common (class imbalance) or with the hope of achieving some external objective (cost-sensitive learning). We provide a model-based explanation for this incompatibility and use our anthropomorphic model to generate a simple method of recovering likelihoods from an algorithm that is miscalibrated due to class weighting. We validate this approach in the binary pneumonia detection task of Rajpurkar, Irvin, Zhu, et al. (2017).
    Date: 2022–05
    URL: http://d.repec.org/n?u=RePEc:arx:papers:2205.04613&r=
  3. By: A. Max Reppen; H. Mete Soner; Valentin Tissot-Daguette
    Abstract: This paper outlines, and through stylized examples evaluates a novel and highly effective computational technique in quantitative finance. Empirical Risk Minimization (ERM) and neural networks are key to this approach. Powerful open source optimization libraries allow for efficient implementations of this algorithm making it viable in high-dimensional structures. The free-boundary problems related to American and Bermudan options showcase both the power and the potential difficulties that specific applications may face. The impact of the size of the training data is studied in a simplified Merton type problem. The classical option hedging problem exemplifies the need of market generators or large number of simulations.
    Date: 2022–05
    URL: http://d.repec.org/n?u=RePEc:arx:papers:2205.04604&r=
  4. By: Reisenhofer, Rafael; Bayer, Xandro; Hautsch, Nikolaus
    Abstract: Despite the impressive success of deep neural networks in many application areas, neural network models have so far not been widely adopted in the context of volatility forecasting. In this work, we aim to bridge the conceptual gap between established time series approaches, such as the Heterogeneous Autoregressive (HAR) model (Corsi, 2009), and state-of-the-art deep neural network models. The newly introduced HARNet is based on a hierarchy of dilated convolutional layers, which facilitates an exponential growth of the receptive field of the model in the number of model parameters. HARNets allow for an explicit initialization scheme such that before optimization, a HARNet yields identical predictions as the respective baseline HAR model. Particularly when considering the QLIKE error as a loss function, we find that this approach significantly stabilizes the optimization of HARNets. We evaluate the performance of HARNets with respect to three different stock market indexes. Based on this evaluation, we formulate clear guidelines for the optimization of HARNets and show that HARNets can substantially improve upon the forecasting accuracy of their respective HAR baseline models. In a qualitative analysis of the filter weights learnt by a HARNet, we report clear patterns regarding the predictive power of past information. Among information from the previous week, yesterday and the day before, yesterday's volatility makes by far the most contribution to today's realized volatility forecast. Moroever, within the previous month, the importance of single weeks diminishes almost linearly when moving further into the past.
    Date: 2022
    URL: http://d.repec.org/n?u=RePEc:zbw:cfswop:680&r=
  5. By: Margherita Doria; Elisa Luciano; Patrizia Semeraro
    Abstract: This paper studies the consequences of capturing non-linear dependence among the covariates that drive the default of different obligors and the overall riskiness of their credit portfolio. Joint default modeling is, without loss of generality, the classical Bernoulli mixture model. Using an application to a credit card dataset we show that, even when Machine Learning techniques perform only slightly better than Logistic Regression in classifying individual defaults as a function of the covariates, they do outperform it at the portfolio level. This happens because they capture linear and non-linear dependence among the covariates, whereas Logistic Regression only captures linear dependence. The ability of Machine Learning methods to capture non-linear dependence among the covariates produces higher default correlation compared with Logistic Regression. As a consequence, on our data, Logistic Regression underestimates the riskiness of the credit portfolio.
    Date: 2022–05
    URL: http://d.repec.org/n?u=RePEc:arx:papers:2205.01524&r=
  6. By: Florian Peters; Doris Neuberger; Oliver Reinhardt; Adelinde Uhrmacher
    Abstract: In macroeconomics, an emerging discussion of alternative monetary systems addresses the dimensions of systemic risk in advanced financial systems. Monetary regime changes with the aim of achieving a more sustainable financial system have already been discussed in several European parliaments and were the subject of a referendum in Switzerland. However, their effectiveness and efficacy concerning macro-financial stability are not well-known. This paper introduces a macroeconomic agent-based model (MABM) in a novel simulation environment to simulate the current monetary system, which may serve as a basis to implement and analyze monetary regime shifts. In this context, the monetary system affects the lending potential of banks and might impact the dynamics of financial crises. MABMs are predestined to replicate emergent financial crisis dynamics, analyze institutional changes within a financial system, and thus measure macro-financial stability. The used simulation environment makes the model more accessible and facilitates exploring the impact of different hypotheses and mechanisms in a less complex way. The model replicates a wide range of stylized economic facts, including simplifying assumptions to reduce model complexity.
    Date: 2022–05
    URL: http://d.repec.org/n?u=RePEc:arx:papers:2205.00752&r=
  7. By: Ryan Defina (International Association of Deposit Insurers)
    Abstract: The field of deposit insurance is yet to realise fully the potential of machine learning, and the substantial benefits that it may present to its operational and policy-oriented activities. There are practical opportunities available (some specified in this paper) that can assist in improving deposit insurers’ relationship with the technology. Sharing of experiences and learnings via international engagement and collaboration is fundamental in developing global best practices in this space.
    Keywords: deposit insurance, bank resolution
    JEL: G21 G33
    Date: 2021–09
    URL: http://d.repec.org/n?u=RePEc:awl:finbri:3&r=
  8. By: Chenrui Zhang
    Abstract: We explore how to crawl financial forum data such as stock bars and combine them with deep learning models for sentiment analysis. In this paper, we will use the BERT model to train against the financial corpus and predict the SZSE Component Index, and find that applying the BERT model to the financial corpus through the maximum information coefficient comparison study. The obtained sentiment features will be able to reflect the fluctuations in the stock market and help to improve the prediction accuracy effectively. Meanwhile, this paper combines deep learning with financial text, in further exploring the mechanism of investor sentiment on stock market through deep learning method, which will be beneficial for national regulators and policy departments to develop more reasonable policy guidelines for maintaining the stability of stock market.
    Date: 2022–05
    URL: http://d.repec.org/n?u=RePEc:arx:papers:2205.04743&r=
  9. By: Corrado Monti; Marco Pangallo; Gianmarco De Francisci Morales; Francesco Bonchi
    Abstract: Agent-Based Models (ABMs) are used in several fields to study the evolution of complex systems from micro-level assumptions. However, ABMs typically can not estimate agent-specific (or "micro") variables: this is a major limitation which prevents ABMs from harnessing micro-level data availability and which greatly limits their predictive power. In this paper, we propose a protocol to learn the latent micro-variables of an ABM from data. The first step of our protocol is to reduce an ABM to a probabilistic model, characterized by a computationally tractable likelihood. This reduction follows two general design principles: balance of stochasticity and data availability, and replacement of unobservable discrete choices with differentiable approximations. Then, our protocol proceeds by maximizing the likelihood of the latent variables via a gradient-based expectation maximization algorithm. We demonstrate our protocol by applying it to an ABM of the housing market, in which agents with different incomes bid higher prices to live in high-income neighborhoods. We demonstrate that the obtained model allows accurate estimates of the latent variables, while preserving the general behavior of the ABM. We also show that our estimates can be used for out-of-sample forecasting. Our protocol can be seen as an alternative to black-box data assimilation methods, that forces the modeler to lay bare the assumptions of the model, to think about the inferential process, and to spot potential identification problems.
    Date: 2022–05
    URL: http://d.repec.org/n?u=RePEc:arx:papers:2205.05052&r=
  10. By: Bouët, Antoine; Laborde Debucquet, David; Traoré, Fousseini
    Abstract: MIRAGRODEP-AEZ is a recursive dynamic multi-region, multi-sector Computable General Equilibrium (CGE) model based on MIRAGRODEP which in turn is based on MIRAGE (Modelling International Relations Under Applied General Equilibrium) with Agro-ecological zones (regions). It constitutes an extension of the MIRAGRODEP model that allows the user to perform analysis at the subnational level using spatial disaggregated data. The model is particularly suitable for agricultural policy analysis that require working at different levels of disaggregation to consider differences in agro-ecological conditions.
    Keywords: WORLD; models; modelling; production; demand; supply; markets; economics
    Date: 2022
    URL: http://d.repec.org/n?u=RePEc:fpr:agrotn:tn-24&r=
  11. By: MARTINEZ PLUMED Fernando (European Commission - JRC); CABALLERO BENÍTEZ Fernando; CASTELLANO FALCÓN David; FERNANDEZ LLORCA David (European Commission - JRC); GOMEZ Emilia (European Commission - JRC); HUPONT TORRES Isabelle (European Commission - JRC); MERINO Luis; MONSERRAT Carlos; HERNÁNDEZ ORALLO José
    Abstract: Artificial intelligence (AI) offers the potential to transform our lives in radical ways. However, we lack the tools to determine which achievements will be attained in the near future. Also, we usually underestimate which various technologies in AI are capable of today. This report constitutes the second edition of a study proposing an example-based methodology to categorise and assess several AI technologies, by mapping them onto Technology Readiness Levels (TRL) (e.g., maturity and availability levels). We first interpret the nine TRLs in the context of AI and identify different categories in AI to which they can be assigned. We then introduce new bidimensional plots, called readiness-vs-generality charts, where we see that higher TRLs are achievable for low-generality technologies focusing on narrow or specific abilities, while high TRLs are still out of reach for more general capabilities. In an incremental way, this edition builds on the first report on the topic by updating the assessment of the original set of AI technologies and complementing it with an analysis of new AI technologies. We include numerous examples of AI technologies in a variety of fields and show their readiness-vs-generality charts, serving as a base for a broader discussion of AI technologies. Finally, we use the dynamics of several AI technologies at different generality levels and moments of time to forecast some short-term and mid-term trends for AI.
    Keywords: Artificial Intelligence, Technology Readiness Level, AI technology, evaluation, machine learning, recommender systems, expert systems, apprentice by demonstration, audio-visual content generation, machine translation, speech recognition, massive multi-modal models, facial recognition, text recognition, transport scheduling systems, self-driving cars, home cleaning robots, logistic robots, negotiation agents, virtual assistants, risks
    Date: 2022–05
    URL: http://d.repec.org/n?u=RePEc:ipt:iptwpa:jrc129399&r=
  12. By: Jay Cao; Jacky Chen; Soroush Farghadani; John Hull; Zissis Poulos; Zeyu Wang; Jun Yuan
    Abstract: We use deep distributional reinforcement learning (RL) to develop hedging strategies for a trader responsible for derivatives dependent on a particular underlying asset. The transaction costs associated with trading the underlying asset are usually quite small. Traders therefore tend to carry out delta hedging daily, or even more frequently, to ensure that the portfolio is almost completely insensitive to small movements in the asset's price. Hedging the portfolio's exposure to large asset price movements and volatility changes (gamma and vega hedging) is more expensive because this requires trades in derivatives, for which transaction costs are quite large. Our analysis takes account of these transaction cost differences. It shows how RL can be used to develop a strategy for using options to manage gamma and vega risk with three different objective functions. These objective functions involve a mean-variance trade-off, value at risk, and conditional value at risk. We illustrate how the optimal hedging strategy depends on the asset price process, the trader's objective function, the level of transaction costs when options are traded, and the maturity of the options used for hedging.
    Date: 2022–05
    URL: http://d.repec.org/n?u=RePEc:arx:papers:2205.05614&r=
  13. By: Andreas Haupt; Aroon Narayanan
    Abstract: Consider a bandit learning environment. We demonstrate that popular learning algorithms such as Upper Confidence Band (UCB) and $\varepsilon$-Greedy exhibit risk aversion: when presented with two arms of the same expectation, but different variance, the algorithms tend to not choose the riskier, i.e. higher variance, arm. We prove that $\varepsilon$-Greedy chooses the risky arm with probability tending to $0$ when faced with a deterministic and a Rademacher-distributed arm. We show experimentally that UCB also shows risk-averse behavior, and that risk aversion is present persistently in early rounds of learning even if the riskier arm has a slightly higher expectation. We calibrate our model to a recommendation system and show that algorithmic risk aversion can decrease consumer surplus and increase homogeneity. We discuss several extensions to other bandit algorithms, reinforcement learning, and investigate the impacts of algorithmic risk aversion for decision theory.
    Date: 2022–05
    URL: http://d.repec.org/n?u=RePEc:arx:papers:2205.04619&r=
  14. By: Cyril Bachelard; Apostolos Chalkis; Vissarion Fisikopoulos; Elias Tsigaridas
    Abstract: We propose novel randomized geometric tools to detect low-volatility anomalies in stock markets; a principal problem in financial economics. Our modeling of the (detection) problem results in sampling and estimating the (relative) volume of geodesically non-convex and non-connected spherical patches that arise by intersecting a non-standard simplex with a sphere. To sample, we introduce two novel Markov Chain Monte Carlo (MCMC) algorithms that exploit the geometry of the problem and employ state-of-the-art continuous geometric random walks (such as Billiard walk and Hit-and-Run) adapted on spherical patches. To our knowledge, this is the first geometric formulation and MCMC-based analysis of the volatility puzzle in stock markets. We have implemented our algorithms in C++ (along with an R interface) and we illustrate the power of our approach by performing extensive experiments on real data. Our analyses provide accurate detection and new insights into the distribution of portfolios' performance characteristics. Moreover, we use our tools to show that classical methods for low-volatility anomaly detection in finance form bad proxies that could lead to misleading or inaccurate results.
    Date: 2022–05
    URL: http://d.repec.org/n?u=RePEc:arx:papers:2205.03852&r=
  15. By: van Loon, Austin
    Abstract: Since the beginning of this millennium, data in the form of human-generated text in a machine-readable format has become increasingly available to social scientists, presenting a unique window into social life. However, harnessing vast quantities of this highly unstructured data in a systematic way presents a unique combination of analytical and methodological challenges. Luckily, our understanding of how to overcome these challenges has also developed greatly over this same period. In this article, I present a novel typology of the methods social scientists have used to analyze text data at scale in the interest of testing and developing social theory. I describe three “families” of methods: analyses of (1) term frequency, (2) document structure, and (3) semantic similarity. For each family of methods, I discuss their logical and statistical foundations, analytical strengths and weaknesses, as well as prominent variants and applications.
    Date: 2022–05–07
    URL: http://d.repec.org/n?u=RePEc:osf:socarx:htnej&r=
  16. By: Chenrui Zhang; Xinyi Wu; Hailu Deng; Huiwei Zhang
    Abstract: Based on the commentary data of the Shenzhen Stock Index bar on the EastMoney website from January 1, 2018 to December 31, 2019. This paper extracts the embedded investor sentiment by using a deep learning BERT model and investigates the time-varying linkage between investment sentiment, stock market liquidity and volatility using a TVP-VAR model. The results show that the impact of investor sentiment on stock market liquidity and volatility is stronger. Although the inverse effect is relatively small, it is more pronounced with the state of the stock market. In all cases, the response is more pronounced in the short term than in the medium to long term, and the impact is asymmetric, with shocks stronger when the market is in a downward spiral.
    Date: 2022–05
    URL: http://d.repec.org/n?u=RePEc:arx:papers:2205.05719&r=
  17. By: Bratanova, Alexandra; Pham, Hien; Mason, Claire; Hajkowicz, Stefan; Naughtin, Claire; Schleiger, Emma; Sanderson, Conrad; Chen, Caron; Karimi, Sarvnaz
    Abstract: We demonstrate how cluster analysis underpinned by analysis of revealed technology advantage can be used to differentiate geographic regions with comparative advantage in artificial intelligence (AI). Our analysis uses novel datasets on Australian AI businesses, intellectual property patents and labour markets to explore location, concentration and intensity of AI activities across 333 geographical regions. We find that Australia's AI business and innovation activity is clustered in geographic locations with higher investment in research and development. Through cluster analysis we identify three tiers of AI capability regions that are developing across the economy: ‘AI hotspots’ (10 regions), ‘Emerging AI regions’ (85 regions) and ‘Nascent AI regions’ (238 regions). While the AI hotspots are mainly concentrated in central business district locations, there are examples when they also appear outside CBD in areas where there has been significant investment in innovation and technology hubs. Policy makers can use the results of this study to facilitate and monitor the growth of AI capability to boost economic recovery. Investors may find these results helpful to learn about the current landscape of AI business and innovation activities in Australia.
    Keywords: Artificial intelligence, cluster, revealed technology advantage, regional innovation, Australia
    JEL: O31 O33 O38 R12
    Date: 2022–05–31
    URL: http://d.repec.org/n?u=RePEc:pra:mprapa:113237&r=
  18. By: Mike Ludkovski; Glen Swindle; Eric Grannan
    Abstract: We develop a probabilistic framework for joint simulation of short-term electricity generation from renewable assets. In this paper we describe a method for producing hourly day-ahead scenarios of generated power at grid-scale across hundreds of assets. These scenarios are conditional on specified forecasts and yield a full uncertainty quantification both at the marginal asset-level and across asset collections. Our simulation pipeline first applies asset calibration to normalize hourly, daily and seasonal generation profiles, and to Gaussianize the forecast--actuals distribution. We then develop a novel clustering approach to stably estimate the covariance matrix across assets; clustering is done hierarchically to achieve scalability. An extended case study using an ERCOT-like system with nearly 500 solar and wind farms is used for illustration.
    Date: 2022–05
    URL: http://d.repec.org/n?u=RePEc:arx:papers:2205.04736&r=
  19. By: Sarah A. Jacobson; Luyao Zhang; Jiasheng Zhu
    Abstract: Active learning comprises many varied techniques that engage students actively in the construction of their understanding. Because of this variation, different active learning techniques may be best suited to achieving different learning objectives. We study students' perceptions of a set of active learning techniques (including a Python simulation and an interactive game) and some traditional techniques (like lecture). We find that students felt they engaged fairly actively with all of the techniques, though more with those with a heavy grade weight and some of the active learning techniques, and they reported enjoying the active learning techniques the most except for an assignment that required soliciting peer advice on a research idea. All of the techniques were rated as relatively effective for achieving each of six learning objectives, but to varying extents. The most traditional techniques like exams were rated highest for achieving an objective associated with lower order cognitive skills, remembering concepts. In contrast, some active learning techniques like class presentations and the Python simulation were rated highest for achieving objectives related to higher order cognitive skills, including learning to conduct research, though lectures also performed surprisingly well for these objectives. Other technique-objective matches are intuitive; for example, the debate is rated highly for understanding pros and cons of an issue, and small group discussion is rated highly for collaborative learning. Our results support the idea that different teaching techniques are best suited for different outcomes, which implies that a mix of techniques may be optimal in course design.
    Date: 2022–05
    URL: http://d.repec.org/n?u=RePEc:arx:papers:2205.03393&r=
  20. By: Tatjana Evas (European Commission – DG CNECT); Maikki Sipinen (European Commission – DG CNECT); Martin Ulbrich (European Commission – DG CNECT); Alessandro Dalla Benetta (European Commission - JRC); Maciej Sobolewski (European Commission - JRC); Daniel Nepelski (European Commission - JRC)
    Abstract: This report provides estimates of AI investments in the EU between 2018 and 2020 and, for selected investments categories, in the UK and the US. It considers AI as a general-purpose technology and, besides direct investments in the development and adoption of AI technologies, also includes investments in complementary assets and capabilities such as skills, data, product design and organisational capital among AI investments. According to current estimates, in 2020 the EU invested EUR 12.7-16 billion in AI. In 2020, due to the COVID19 outbreak, the EU AI investments grew by 20-28%, compared to a growth of 43-51% in 2019.
    Keywords: General Purpose Technology, Artificial Intelligence, digital technologies, investments, intangibles, Europe
    Date: 2022–05
    URL: http://d.repec.org/n?u=RePEc:ipt:iptwpa:jrc129174&r=

This nep-cmp issue is ©2022 by Stan Miles. It is provided as is without any express or implied warranty. It may be freely redistributed in whole or in part for any purpose. If distributed in part, please include this notice.
General information on the NEP project can be found at http://nep.repec.org. For comments please write to the director of NEP, Marco Novarese at <director@nep.repec.org>. Put “NEP” in the subject, otherwise your mail may be rejected.
NEP’s infrastructure is sponsored by the School of Economics and Finance of Massey University in New Zealand.