|
on Computational Economics |
|
Issue of 2023‒02‒06
fifteen papers chosen by |
| By: | Thomas Wong; Mauricio Barahona |
| Abstract: | The application of deep learning algorithms to financial data is difficult due to heavy non-stationarities which can lead to over-fitted models that underperform under regime changes. Using the Numerai tournament data set as a motivating example, we propose a machine learning pipeline for trading market-neutral stock portfolios based on tabular data which is robust under changes in market conditions. We evaluate various machine-learning models, including Gradient Boosting Decision Trees (GBDTs) and Neural Networks with and without simple feature engineering, as the building blocks for the pipeline. We find that GBDT models with dropout display high performance, robustness and generalisability with relatively low complexity and reduced computational cost. We then show that online learning techniques can be used in post-prediction processing to enhance the results. In particular, dynamic feature neutralisation, an efficient procedure that requires no retraining of models and can be applied post-prediction to any machine learning model, improves robustness by reducing drawdown in volatile market conditions. Furthermore, we demonstrate that the creation of model ensembles through dynamic model selection based on recent model performance leads to improved performance over baseline by improving the Sharpe and Calmar ratios. We also evaluate the robustness of our pipeline across different data splits and random seeds with good reproducibility of results. |
| Date: | 2022–12 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2301.00790&r=cmp |
| By: | Stéphane Goutte (Université Paris-Saclay); Viet Hoang Le (Université Paris-Saclay); Fei Liu (IPAG Business School); Hans-Jörg Mettenheim, Von (IPAG Business School) |
| Abstract: | A large number of modern practices in financial forecasting rely on technical analysis, which involves several heuristics techniques of price charts visual pattern recognition as well as other technical indicators. In this study, we aim to investigate the potential use of those technical information (candlestick information as well as technical indicators) as inputs for machine learning models, especially the state-of-the-art deep learning algorithms, to generate trading signals. To properly address this problem, empirical research is conducted which applies several machine learning methods to 5 years of Bitcoin hourly data from 2017 to 2022. From the result of our study, we confirm the potential of trading strategies using machine learning approaches. We also find that among several machine learning models, deep learning models, specifically the recurrent neural networks, tend to outperform the others in time-series prediction. |
| Keywords: | Bitcoin Technical Analysis Machine Learning Deep Learning Convolutional Neural Networks Recurrent Neural Network, Bitcoin, Technical Analysis, Machine Learning, Deep Learning, Convolutional Neural Networks, Recurrent Neural Network |
| Date: | 2023–01–01 |
| URL: | http://d.repec.org/n?u=RePEc:hal:wpaper:halshs-03917333&r=cmp |
| By: | Huyên Pham (UPD7 - Université Paris Diderot - Paris 7, LPSM (UMR_8001) - Laboratoire de Probabilités, Statistique et Modélisation - UPD7 - Université Paris Diderot - Paris 7 - SU - Sorbonne Université - CNRS - Centre National de la Recherche Scientifique); Xavier Warin (EDF R&D - EDF R&D - EDF - EDF, FiME Lab - Laboratoire de Finance des Marchés d'Energie - Université Paris Dauphine-PSL - PSL - Université Paris sciences et lettres - CREST - EDF R&D - EDF R&D - EDF - EDF) |
| Abstract: | This paper is devoted to the numerical resolution of McKean-Vlasov control problems via the class of mean-field neural networks introduced in our companion paper [25] in order to learn the solution on the Wasserstein space. We propose several algorithms either based on dynamic programming with control learning by policy or value iteration, or backward SDE from stochastic maximum principle with global or local loss functions. Extensive numerical results on different examples are presented to illustrate the accuracy of each of our eight algorithms. We discuss and compare the pros and cons of all the tested methods. |
| Keywords: | McKean-Vlasov control mean-field neural networks learning on Wasserstein space dynamic programming backward SDE deep learning algorithms, McKean-Vlasov control, mean-field neural networks, learning on Wasserstein space, dynamic programming, backward SDE, deep learning algorithms |
| Date: | 2022–12–21 |
| URL: | http://d.repec.org/n?u=RePEc:hal:wpaper:hal-03900810&r=cmp |
| By: | Yves-C\'edric Bauwelinckx; Jan Dhaene; Tim Verdonck; Milan van den Heuvel |
| Abstract: | Modeling lies at the core of both the financial and the insurance industry for a wide variety of tasks. The rise and development of machine learning and deep learning models have created many opportunities to improve our modeling toolbox. Breakthroughs in these fields often come with the requirement of large amounts of data. Such large datasets are often not publicly available in finance and insurance, mainly due to privacy and ethics concerns. This lack of data is currently one of the main hurdles in developing better models. One possible option to alleviating this issue is generative modeling. Generative models are capable of simulating fake but realistic-looking data, also referred to as synthetic data, that can be shared more freely. Generative Adversarial Networks (GANs) is such a model that increases our capacity to fit very high-dimensional distributions of data. While research on GANs is an active topic in fields like computer vision, they have found limited adoption within the human sciences, like economics and insurance. Reason for this is that in these fields, most questions are inherently about identification of causal effects, while to this day neural networks, which are at the center of the GAN framework, focus mostly on high-dimensional correlations. In this paper we study the causal preservation capabilities of GANs and whether the produced synthetic data can reliably be used to answer causal questions. This is done by performing causal analyses on the synthetic data, produced by a GAN, with increasingly more lenient assumptions. We consider the cross-sectional case, the time series case and the case with a complete structural model. It is shown that in the simple cross-sectional scenario where correlation equals causation the GAN preserves causality, but that challenges arise for more advanced analyses. |
| Date: | 2023–01 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2301.01109&r=cmp |
| By: | Stéphane Goutte (Université Paris-Saclay); Viet Hoang Le (Université Paris-Saclay); Fei Liu (IPAG Business School); Hans-Jörg Mettenheim, Von (IPAG Business School) |
| Abstract: | We analyze the predictability of news sentiment (both general news and ESG-related news) on the return of stocks from European and the potential of applying them as a proper trading strategy over seven years from 2015 to 2022. We find that sentiment indicators extracted from news supplied by GDELT such as Tone, Polarity, and Activity Density show significant relationships to the return of the stock price. Those relationships can be exploited, even in the most naive way, to create trading strategies that can be profitable and outperform the market. Furthermore, those indicators can be used as inputs for more sophisticated machine learning algorithms to create even better-performing trading strategies. Among the indicators, those extracted from ESG-related news tend to show better performance in both cases: when they are used naively or as inputs for machine learning algorithms. |
| Keywords: | ESG Stock Market Prediction Sentiment Analysis Machine Learning Big Data GDELT, ESG, Stock Market Prediction, Sentiment Analysis, Machine Learning, Big Data, GDELT |
| Date: | 2023–01–01 |
| URL: | http://d.repec.org/n?u=RePEc:hal:wpaper:halshs-03917335&r=cmp |
| By: | Cero, Ian (University of Rochester Medical Center); Wyman, Peter |
| Abstract: | Agent-based simulations comparing the relative effectiveness of network-based and individual-focused interventions for preventing suicide. |
| Date: | 2023–01–03 |
| URL: | http://d.repec.org/n?u=RePEc:osf:osfxxx:r6v2e&r=cmp |
| By: | Jiwon Kim; Moon-Ju Kang; KangHun Lee; HyungJun Moon; Bo-Kwan Jeon |
| Abstract: | Recently, there are many trials to apply reinforcement learning in asset allocation for earning more stable profits. In this paper, we compare performance between several reinforcement learning algorithms - actor-only, actor-critic and PPO models. Furthermore, we analyze each models' character and then introduce the advanced algorithm, so called Reward clipping model. It seems that the Reward Clipping model is better than other existing models in finance domain, especially portfolio optimization - it has strength both in bull and bear markets. Finally, we compare the performance for these models with traditional investment strategies during decreasing and increasing markets. |
| Date: | 2023–01 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2301.05300&r=cmp |
| By: | Konstantīns Beņkovskis (Latvijas Banka); Ludmila Fadejeva (Latvijas Banka); Anna Pluta (The Baltic International Centre for Economic Policy Studies); Anna Zasova (The Baltic International Centre for Economic Policy Studies) |
| Abstract: | In this paper, we link a CGE model with the tax-benefit microsimulation model EUROMOD for Latvia. The model linkage is done using an iterative top-down bottom-up approach, ensuring the convergence of changes in disposable income, employment and wage in both models. We also incorporate the unreported wage payments in CGE and EUROMOD to account for the substantial labour tax non-compliance in Latvia and improve the modelling of the fiscal sector. Several simulations demonstrate the advantages of the joint CGE-EUROMOD system over the individual macro and microsimulation models. The lack of income distribution aspect and the scarcity of fiscal instruments in CGE can be overcome by the features of EUROMOD. The CGE model, on the other hand, provides macroeconomic spillovers that are missing in the simulations of EUROMOD. |
| Keywords: | EUROMOD, CGE model, model linkage, informal sector |
| JEL: | C68 D58 D90 J46 |
| Date: | 2023–01–17 |
| URL: | http://d.repec.org/n?u=RePEc:ltv:wpaper:202301&r=cmp |
| By: | Tianran Ding; Wouter M.J. Achten |
| Date: | 2022–12–01 |
| URL: | http://d.repec.org/n?u=RePEc:ulb:ulbeco:2013/352782&r=cmp |
| By: | Konstantīns Beņkovskis (Latvijas Banka); Oļegs Matvejevs (Latvijas Banka) |
| Abstract: | This paper describes the new version of Latvian CGE model, which is now an integral part of the joint CGE-EUROMOD modelling system. Special attention is devoted to the labour market and consumption blocks of CGE that are substantially improved compared with the previous version. We briefly describe the motivation to link Latvian CGE with Latvian EUROMOD and provide major technical details. We also provide an example of the policy simulation by the joint CGE-EUROMOD system, demonstrating how the introduction of the progressive personal income tax rate affected the Latvian economy at macro, industry and micro level. |
| Keywords: | CGE model, Latvia, labour market, consumption, EUROMOD |
| JEL: | D58 C68 H2 H6 D9 |
| Date: | 2023–01–18 |
| URL: | http://d.repec.org/n?u=RePEc:ltv:wpaper:202302&r=cmp |
| By: | Fateme Shahabi Nejad; Mohammad Mehdi Ebadzadeh |
| Abstract: | Applying machine learning methods to forecast stock prices has been one of the research topics of interest in recent years. Almost few studies have been reported based on generative adversarial networks (GANs) in this area, but their results are promising. GANs are powerful generative models successfully applied in different areas but suffer from inherent challenges such as training instability and mode collapse. Also, a primary concern is capturing correlations in stock prices. Therefore, our challenges fall into two main categories: capturing correlations and inherent problems of GANs. In this paper, we have introduced a novel framework based on DRAGAN and feature matching for stock price forecasting, which improves training stability and alleviates mode collapse. We have employed windowing to acquire temporal correlations by the generator. Also, we have exploited conditioning on discriminator inputs to capture temporal correlations and correlations between prices and features. Experimental results on data from several stocks indicate that our proposed method outperformed long short-term memory (LSTM) as a baseline method, also basic GANs and WGAN-GP as two different variants of GANs. |
| Date: | 2023–01 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2301.05693&r=cmp |
| By: | Ali Bayar (EcoMod); Dizem Ertac Varoglu (EcoMod and Near East University) |
| Abstract: | This article investigates environmental and energy policies that Turkey needs to adopt on its way to a sustainable development path. A multi-sectoral CGE model is developed to analyze the effects of several environmental and energy policy scenarios available for the Turkish economy to attain a low-carbon society with a reduced reliance on fossil fuel imports. Domestic energy demand has significantly increased in Turkey over the past decades, and this has put a lot of pressure on policymakers as the economy greatly depends on imports of natural gas and oil as far as current energy consumption is concerned. The CGE model used in this study is based on an energy-disaggregated Social Accounting Matrix (SAM), constructed in previous work by the authors. The energy-disaggregated SAM serves as the benchmark database and the high disaggregation of the energy commodities and the electricity sector to include 8 different types of power generating sectors (5 of which are renewable energy sources) enables electric power substitution in the model. The energy-disaggregated SAM is further linked with satellite accounts which include data on derived energy demand and greenhouse gas (GHG) emissions. The macroeconomic and environmental impacts of three distinct sets of scenarios are analyzed with respect to the baseline scenario. The first scenario simulates a 30% increase in energy efficiency in the production sectors and the residential sector and evidence is found for reaching the 21% GHG mitigation target set in Turkey’s pledge for Paris Agreement compliance by 2030. The second set of scenarios is the inclusion of a medium and high-level carbon tax rates for coal, oil and natural gas. The carbon tax scenarios produce significant effects on both emission reduction targets and substituting fossil fuel technologies with cleaner energy technologies. The third scenario estimates the effects of changes in world prices of energy on the Turkish economy. A 20% increase in world energy prices, i.e. oil, natural gas, and coal, induces substantial changes in the breakdown of TPES and the power-generating sector and puts a lot of pressure on the current account deficit of the country. A carbon tax policy proves to be the most viable scenario which leads to reduced energy intensities in all sectors, a 21% GHG emissions abatement, and a transformation of the energy sector towards having a low-carbon content along with a reduced reliance on fossil fuel imports. |
| Date: | 2022–12–20 |
| URL: | http://d.repec.org/n?u=RePEc:erg:wpaper:1622&r=cmp |
| By: | Guijin Son; Hanwool Lee; Nahyeon Kang; Moonjeong Hahm |
| Abstract: | Extraction of sentiment signals from news text, stock message boards, and business reports, for stock movement prediction, has been a rising field of interest in finance. Building upon past literature, the most recent works attempt to better capture sentiment from sentences with complex syntactic structures by introducing aspect-level sentiment classification (ASC). Despite the growing interest, however, fine-grained sentiment analysis has not been fully explored in non-English literature due to the shortage of annotated finance-specific data. Accordingly, it is necessary for non-English languages to leverage datasets and pre-trained language models (PLM) of different domains, languages, and tasks to best their performance. To facilitate finance-specific ASC research in the Korean language, we build KorFinASC, a Korean aspect-level sentiment classification dataset for finance consisting of 12, 613 human-annotated samples, and explore methods of intermediate transfer learning. Our experiments indicate that past research has been ignorant towards the potentially wrong knowledge of financial entities encoded during the training phase, which has overestimated the predictive power of PLMs. In our work, we use the term "non-stationary knowledge'' to refer to information that was previously correct but is likely to change, and present "TGT-Masking'', a novel masking pattern to restrict PLMs from speculating knowledge of the kind. Finally, through a series of transfer learning with TGT-Masking applied we improve 22.63% of classification accuracy compared to standalone models on KorFinASC. |
| Date: | 2023–01 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2301.03136&r=cmp |
| By: | Antonio Villar (Universidad Pablo de Olavide) |
| Abstract: | This paper proposes and characterizes an elementary algorithm to solve multicriteria evaluation problems when individual judgements are categorical and may fail to satisfy both transitivity and completeness. The evaluation function consists of a weighted sum of the average number of times that each alternative precedes some other, in all pairwise comparisons. It provides, therefore, a quantitative assessment which is well-grounded, immediate to compute, and easy to understand. An application to the evaluation of human development illustrates how this evaluation protocol works. |
| Keywords: | multidimensional evaluation; categorical data; non-transitive and incomplete preferences; pairwise comparisons. |
| JEL: | C60 D70 |
| Date: | 2022 |
| URL: | http://d.repec.org/n?u=RePEc:pab:wpaper:22.14&r=cmp |
| By: | Jinge Bao; Patrick Rebentrost |
| Abstract: | Quantum computers have the potential to solve pricing problems in finance by the use of quantum estimation. In a broader context, it is reasonable to ask what happens to the pricing problem and other financial tasks if the market and the assets traded on the market themselves have quantum properties. In this work, we consider a financial setting where instead of by classical probabilities the market is described by a quantum density operator. This setting naturally leads to a new asset class, which we call quantum assets. Under the assumption that such assets have a price and can be traded, we develop an extended definition of arbitrage to quantify gains without the corresponding risk. Our main result is a quantum version of the first fundamental theorem of asset pricing. If and only if there is no arbitrage, there exists a risk-free density operator under which all assets are martingales. This density operator is used for the pricing of quantum derivatives. On the technical side, we study the density operator version of the Radon-Nikodym measure change. We provide small examples to illustrate the theory. |
| Date: | 2022–12 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2212.13815&r=cmp |