|
on Financial Markets |
|
Issue of 2023‒02‒06
eight papers chosen by |
| 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=fmk |
| By: | Tanja Aue; Adam Jatowt; Michael F\"arber |
| Abstract: | Environmental, social and governance (ESG) engagement of companies moved into the focus of public attention over recent years. With the requirements of compulsory reporting being implemented and investors incorporating sustainability in their investment decisions, the demand for transparent and reliable ESG ratings is increasing. However, automatic approaches for forecasting ESG ratings have been quite scarce despite the increasing importance of the topic. In this paper, we build a model to predict ESG ratings from news articles using the combination of multivariate timeseries construction and deep learning techniques. A news dataset for about 3, 000 US companies together with their ratings is also created and released for training. Through the experimental evaluation we find out that our approach provides accurate results outperforming the state-of-the-art, and can be used in practice to support a manual determination or analysis of ESG ratings. |
| Date: | 2022–11 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2212.11765&r=fmk |
| By: | Yuteng Cheng (Bank of Canada); Ryuichiro Izumi (Department of Economics, Wesleyan University) |
| Abstract: | What is the optimal design of anonymity in a central bank digital currency (CBDC)? We examine this question in the context of bank lending by building a stylized model of anonymity in payment instruments. We specify the anonymity of payment instruments in two dimensions: The bank has no information about the entrepreneur’s investment, and the bank has less control over the entrepreneur’s profits. An instrument with higher anonymity may discourage the bank from lending, and thus, the entrepreneur strategically chooses payment instruments. Our analysis shows that introducing a CBDC with modest anonymity can improve welfare in one equilibrium, but can also destroy valuable information in bank lending, leading to inefficient lending in another equilibrium. Our results suggest that central banks should either make a CBDC highly anonymous or share CBDC data with banks to eliminate this bad equilibrium. |
| Keywords: | CBDC, Anonymity, Bank lending |
| JEL: | E42 E58 G28 |
| Date: | 2023–01 |
| URL: | http://d.repec.org/n?u=RePEc:wes:weswpa:2023-002&r=fmk |
| By: | Hayden Brown |
| Abstract: | Daily leveraged exchange traded funds amplify gains and losses of their underlying benchmark indexes on a daily basis. The result of going long in a daily leveraged ETF for more than one day is less clear. Here, bounds are given for the log-returns of a leveraged ETF when going long for more than just one day. The bounds are quadratic in the daily log-returns of the underlying benchmark index, and they are used to find sufficient conditions for outperformance and underperformance of a leveraged ETF in relation to its underlying benchmark index. Results show that if the underlying benchmark index drops 10+\% over the course of 63 consecutive trading days, and the standard deviation of the benchmark index's daily log-returns is no more than .015, then going long in a -3x leveraged ETF during that period gives a log-return of at least 1.5 times the log-return of a short position in the underlying benchmark index. Results also show promise for a 2x daily leveraged S&P 500 ETF. If the average annual log-return of the S&P 500 index continues to be at least .0658, as it has been in the past, and the standard deviation of daily S&P 500 log-returns is under .0125, then a 2x daily leveraged S&P 500 ETF will perform at least as well as the S&P 500 index in the long-run. |
| Date: | 2023–01 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2301.03186&r=fmk |
| 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=fmk |
| 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=fmk |
| 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=fmk |
| 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=fmk |