nep-cmp New Economics Papers
on Computational Economics
Issue of 2023‒06‒19
eleven papers chosen by
Stan Miles
Thompson Rivers University

  1. Using neural networks to predict the value of stocks based on news data By Borisenko Georgy
  2. Artificial neural networks to solve dynamic programming problems: A bias-corrected Monte Carlo operator By Julien Pascal
  3. Temporal and Heterogeneous Graph Neural Network for Financial Time Series Prediction By Sheng Xiang; Dawei Cheng; Chencheng Shang; Ying Zhang; Yuqi Liang
  4. Copula Variational LSTM for High-dimensional Cross-market Multivariate Dependence Modeling By Jia Xu; Longbing Cao
  5. The Newsvendor with Advice By Lin An; Andrew A. Li; Benjamin Moseley; R. Ravi
  6. Measuring Consistency in Text-based Financial Forecasting Models By Linyi Yang; Yingpeng Ma; Yue Zhang
  7. Information and Transparency: Using Machine Learning to Detect Communication By Brown, David P.; Cajueiro, Daniel O.; Eckert, Andrew; Silveira, Douglas
  8. CAP reform and GHG emissions: policy assessment using a PMP agent-based model By Lisa Baldi; Arfini, Filippo; Calzolai, Sara; Donati, Michele
  9. Calibration and Validation of Macroeconomic Simulation Models: A General Protocol by Causal Search By Mario Martinoli; Alessio Moneta; Gianluca Pallante
  10. E2EAI: End-to-End Deep Learning Framework for Active Investing By Zikai Wei; Bo Dai; Dahua Lin
  11. The fundamental value of art NFTs By Fridgen, Gilbert; Kräussl, Roman; Papageorgiou, Orestis; Tugnetti, Alessandro

  1. By: Borisenko Georgy (Department of Economics, Lomonosov Moscow State University)
    Abstract: This paper is devoted to forecasting the value of shares of large Russian companies traded on the Moscow Stock Exchange based on news. Neural networks transformers are used as models for forecasting. Moreover, classical machine learning methods are also involved in the analysis for comparison with the neural network approach. Major Russian news sources and Telegram channels are used as news data. Models trained on different sources are also compared. As a result of the study, it was found that classical machine learning methods cope better with this task in the general case, but neural networks also show good quality. The paper also provides recommendations on the choice of a news source and the choice of a task statement.
    Keywords: shape price, news, network approach, Telegr?m
    JEL: C63 G14
    Date: 2023–05
  2. By: Julien Pascal
    Abstract: Artificial Neural Networks (ANNs) are powerful tools that can solve dynamic programming problems arising in economics. In this context, estimating ANN parameters involves minimizing a loss function based on the model’s stochastic functional equations. In general, the expectations appearing in the loss function admit no closed-form solution, so numerical approximation techniques must be used. In this paper, I analyze a bias-corrected Monte Carlo operator (bc-MC) that approximates expectations by Monte Carlo. I show that the bc-MC operator is a generalization of the all-in-one expectation operator, already proposed in the literature. I propose a method to optimally set the hyperparameters defining the bc-MC operator and illustrate the findings numerically with well-known economic models. I also demonstrate that the bc-MC operator can scale to high-dimensional models. With just a few minutes of computing time, I find a global solution to an economic model with a kink in the decision function and more than 100 dimensions.
    Keywords: Dynamic programming, Artificial Neural Network, Machine Learning, Monte Carlo
    JEL: C45 C61 C63 C68 E32 E37
    Date: 2023–03
  3. By: Sheng Xiang; Dawei Cheng; Chencheng Shang; Ying Zhang; Yuqi Liang
    Abstract: The price movement prediction of stock market has been a classical yet challenging problem, with the attention of both economists and computer scientists. In recent years, graph neural network has significantly improved the prediction performance by employing deep learning on company relations. However, existing relation graphs are usually constructed by handcraft human labeling or nature language processing, which are suffering from heavy resource requirement and low accuracy. Besides, they cannot effectively response to the dynamic changes in relation graphs. Therefore, in this paper, we propose a temporal and heterogeneous graph neural network-based (THGNN) approach to learn the dynamic relations among price movements in financial time series. In particular, we first generate the company relation graph for each trading day according to their historic price. Then we leverage a transformer encoder to encode the price movement information into temporal representations. Afterward, we propose a heterogeneous graph attention network to jointly optimize the embeddings of the financial time series data by transformer encoder and infer the probability of target movements. Finally, we conduct extensive experiments on the stock market in the United States and China. The results demonstrate the effectiveness and superior performance of our proposed methods compared with state-of-the-art baselines. Moreover, we also deploy the proposed THGNN in a real-world quantitative algorithm trading system, the accumulated portfolio return obtained by our method significantly outperforms other baselines.
    Date: 2023–05
  4. By: Jia Xu; Longbing Cao
    Abstract: We address an important yet challenging problem - modeling high-dimensional dependencies across multivariates such as financial indicators in heterogeneous markets. In reality, a market couples and influences others over time, and the financial variables of a market are also coupled. We make the first attempt to integrate variational sequential neural learning with copula-based dependence modeling to characterize both temporal observable and latent variable-based dependence degrees and structures across non-normal multivariates. Our variational neural network WPVC-VLSTM models variational sequential dependence degrees and structures across multivariate time series by variational long short-term memory networks and regular vine copula. The regular vine copula models nonnormal and long-range distributional couplings across multiple dynamic variables. WPVC-VLSTM is verified in terms of both technical significance and portfolio forecasting performance. It outperforms benchmarks including linear models, stochastic volatility models, deep neural networks, and variational recurrent networks in cross-market portfolio forecasting.
    Date: 2023–05
  5. By: Lin An; Andrew A. Li; Benjamin Moseley; R. Ravi
    Abstract: The standard newsvendor model assumes a stochastic demand distribution as well as costs for overages and underages. The celebrated critical fractile formula can be used to determine the optimal inventory levels. While the model has been leveraged in numerous applications, often in practice more characteristics and features of the problem are known. Using these features, it is common to employ machine learning to predict inventory levels over the classic newsvendor approach. An emerging line of work has shown how to use incorporate machine learned predictions into models to circumvent lower bounds and give improved performance. This paper develops the first newsvendor model that incorporates machine learned predictions. The paper considers a repeated newsvendor setting with nonstationary demand. There is a prediction is for each period's demand and, as is the case in machine learning, the prediction can be noisy. The goal is for an inventory management algorithm to take advantage of the prediction when it is high quality and to have performance bounded by the best possible algorithm without a prediction when the prediction is highly inaccurate. This paper proposes a generic model of a nonstationary newsvendor without predictions and develops optimal upper and lower bounds on the regret. The paper then propose an algorithm that takes a prediction as advice which, without a priori knowledge of the accuracy of the advice, achieves the nearly optimal minimax regret. The perforamce mataches the best possible had the accuracy been known in advance. We show the theory is predictive of practice on real data and demonstrtate emprically that our algorithm has a 14% to 19% lower cost than a clairvoyant who knows the quality of the advice beforehand.
    Date: 2023–05
  6. By: Linyi Yang; Yingpeng Ma; Yue Zhang
    Abstract: Financial forecasting has been an important and active area of machine learning research, as even the most modest advantage in predictive accuracy can be parlayed into significant financial gains. Recent advances in natural language processing (NLP) bring the opportunity to leverage textual data, such as earnings reports of publicly traded companies, to predict the return rate for an asset. However, when dealing with such a sensitive task, the consistency of models -- their invariance under meaning-preserving alternations in input -- is a crucial property for building user trust. Despite this, current financial forecasting methods do not consider consistency. To address this problem, we propose FinTrust, an evaluation tool that assesses logical consistency in financial text. Using FinTrust, we show that the consistency of state-of-the-art NLP models for financial forecasting is poor. Our analysis of the performance degradation caused by meaning-preserving alternations suggests that current text-based methods are not suitable for robustly predicting market information. All resources are available on GitHub.
    Date: 2023–05
  7. By: Brown, David P. (University of Alberta, Department of Economics); Cajueiro, Daniel O. (University of Brasilia); Eckert, Andrew (University of Alberta, Department of Economics); Silveira, Douglas (University of Alberta, Department of Economics)
    Abstract: Information and data transparency have been shown to have an important impact on competitive behavior and market outcomes. Market transparency can enhance competition by allowing firms to respond efficiently to a changing market environment. However, a high degree of information can facilitate coordination by enhancing communication and the monitoring of rival behavior. A recent example highlighting concerns over the use of publicly available information to communicate across firms involves the Alberta wholesale electricity market. This market used to release anonymized information on firms’ pricing strategies in near real-time. Allegations were raised that firms were using unique patterns in their prices to reveal their identities to rival firms and coordinate on higher prices. This paper uses machine learning techniques to investigate how firms could use anonymized publicly available information to communicate with their rivals. These techniques can be employed as a possible screen to evaluate whether publicly available information can be used to identify rival behavior and facilitate coordination. Based on these results, regulators can determine if the degree of market transparency is detrimental to market competition.
    Keywords: Machine Learning; Electricity; Market Power; Competition Policy
    JEL: D43 L13 L50 L94 Q40
    Date: 2023–05–23
  8. By: Lisa Baldi; Arfini, Filippo; Calzolai, Sara; Donati, Michele
    Abstract: The aim of this research work is to assess the likelihood of dairy farmers to accept predefined policy scenarios that implies different level of CO2 taxation on GHG emissions produced by the livestock sector. It uses an agent-based model (ABM) and it follows the positive mathematical programming (PMP) approach. ABMs allow to evaluate agricultural policies and farmers’ level of acceptance simulating interaction between farmers, taking territorial specificity and farm heterogeneity into account. The PMP methodology enables to add social and cultural perspective to the economical drivers. The Least Square method, applied to the PMP methodology, allows to overcome shortage in data availability. The model is calibrated on FADN data for the Emilia Romagna region (Italy), year 2020. Results show that farmers take decisions based on economic profitability but also on social and cultural background. Farmers opt for more efficient agricultural management practices if economically convenient, however the possibility to exchange production factors can contribute to the optimisation of their utility function.
    Keywords: Environmental Economics and Policy
    Date: 2023–03
  9. By: Mario Martinoli; Alessio Moneta; Gianluca Pallante
    Abstract: We propose a general protocol for calibration and validation of complex simulation models by an approach based on discovery and comparison of causal structures. The key idea is that configurations of parameters of a given theoretical model are selected by minimizing a distance index between two structural models: one estimated from the data generated by the theoretical model, another estimated from a set of observed data. Validation is conceived as a measure of matching between the theoretical and the empirical causal structure. Causal structures are identified combining structural vector autoregressive and independent component analysis, so as to avoid a priori restrictions. We use model confidence set as a tool to measure the uncertainty associated to the alternative configurations of parameters and causal structures. We illustrate the procedure by applying it to a large-scale macroeconomic agent-based model, namely the ''dystopian Schumpeter-meeting-Keynes'' model.
    Keywords: Calibration; Validation; Simulation models; SVAR models; Causal inference; Model confidence sets; Independent component analysis.
    Date: 2022–10–24
  10. By: Zikai Wei; Bo Dai; Dahua Lin
    Abstract: Active investing aims to construct a portfolio of assets that are believed to be relatively profitable in the markets, with one popular method being to construct a portfolio via factor-based strategies. In recent years, there have been increasing efforts to apply deep learning to pursue "deep factors'' with more active returns or promising pipelines for asset trends prediction. However, the question of how to construct an active investment portfolio via an end-to-end deep learning framework (E2E) is still open and rarely addressed in existing works. In this paper, we are the first to propose an E2E that covers almost the entire process of factor investing through factor selection, factor combination, stock selection, and portfolio construction. Extensive experiments on real stock market data demonstrate the effectiveness of our end-to-end deep leaning framework in active investing.
    Date: 2023–05
  11. By: Fridgen, Gilbert; Kräussl, Roman; Papageorgiou, Orestis; Tugnetti, Alessandro
    Abstract: This paper examines the level of speculation associated with art non-fungible tokens (NFTs), comprehends the characteristics that confer value on them and designs a profitable trading strategy based on our findings. We analyze 860, 067 art NFTs that have been deployed on the Ethereum blockchain and have been involved in 317, 950 sales using machine learning methods to forecast the probability of sale, the trade frequency and the average price. We find that NFTs are highly speculative assets and that their price and recurrence of sale are heavily determined by the floor and the last sales prices, independent of any fundamental value.
    Keywords: Non-fungible tokens (NFTs), Machine Learning, Fundamental Value, Speculation, Ethereum, Blockchain, Non-fungible tokens (NFTs)
    JEL: C55 G11 Z11
    Date: 2023

This nep-cmp issue is ©2023 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 For comments please write to the director of NEP, Marco Novarese at <>. 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.