|
on Financial Markets |
|
Issue of 2022‒01‒10
thirteen papers chosen by |
| By: | Anne-Caroline Hüser; Caterina Lepore; Luitgard Veraart |
| Abstract: | We examine how the repo market operates during liquidity stress by applying network analysis to novel transaction-level data of the overnight gilt repo market including the COVID-19 crisis. During this crisis, the repo network becomes more connected, with most institutions relying on existing trade relationships to transact. There are however significant changes in the repo volumes and spreads during the stress relative to normal times. We find a significant increase in volumes traded in the cleared segment of the market. This reflects a preference for dealers and banks to transact in the cleared rather than the bilateral segment. Funding decreases towards non-banks, only increasing for hedge funds. Further, spreads are higher when dealers and banks lend to rather than borrow from non-banks. Our results can inform the policy debate around the behaviour of banks and non-banks in recent liquidity stress and on widening participation in CCPs by nonbanks. |
| Date: | 2021–11–05 |
| URL: | http://d.repec.org/n?u=RePEc:imf:imfwpa:2021/267&r= |
| By: | Degiannakis, Stavros |
| Abstract: | The paper proposes a novel method to assess whether real investment can be nowcasted based on information that is available on the stock market. The stock market index on a daily sampling frequency is assessed as a predictor of gross fixed capital formation on a quarterly sampling frequency. For France, Germany, Greece and Spain (four representative countries of eurozone), we find significant empirical evidence that the information from the stock market does produce accurate nowcasting values of gross fixed capital formation. |
| Keywords: | Gross fixed capital formation, nowcasting, mixed frequency, predictor, real investment, stock market. |
| JEL: | C53 E22 E27 G17 |
| Date: | 2021–12–31 |
| URL: | http://d.repec.org/n?u=RePEc:pra:mprapa:110914&r= |
| By: | Shwai He; Shi Gu |
| Abstract: | Stock prices move as piece-wise trending fluctuation rather than a purely random walk. Traditionally, the prediction of future stock movements is based on the historical trading record. Nowadays, with the development of social media, many active participants in the market choose to publicize their strategies, which provides a window to glimpse over the whole market's attitude towards future movements by extracting the semantics behind social media. However, social media contains conflicting information and cannot replace historical records completely. In this work, we propose a multi-modality attention network to reduce conflicts and integrate semantic and numeric features to predict future stock movements comprehensively. Specifically, we first extract semantic information from social media and estimate their credibility based on posters' identity and public reputation. Then we incorporate the semantic from online posts and numeric features from historical records to make the trading strategy. Experimental results show that our approach outperforms previous methods by a significant margin in both prediction accuracy (61.20\%) and trading profits (9.13\%). It demonstrates that our method improves the performance of stock movements prediction and informs future research on multi-modality fusion towards stock prediction. |
| Date: | 2021–12 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2112.13593&r= |
| By: | Lee, King Fuei |
| Abstract: | In this study, we investigated the presence of the Halloween effect in the long-term reversal anomaly in the US. After examining the cross-sectional returns of loser-minus-winner portfolios formed on prior returns over the period of 1931–2021, we found evidence of stronger returns during winter months versus summer months. Specifically, the effect appeared to be driven by a significant winter-summer seasonality in the portfolio of small-capitalisation losers and a lack of the Halloween effect in the portfolio of large-capitalisation winners. This study’s results were found to be robust with respect to alternative measures of the long-term reversal effect, differing sub-periods, the inclusion of the January effect and outlier considerations, as well as regarding small- and large-sized companies. |
| Keywords: | Halloween effect, Sell-in-May, long-term reversal, market anomaly |
| JEL: | G00 |
| Date: | 2021–11–29 |
| URL: | http://d.repec.org/n?u=RePEc:pra:mprapa:110859&r= |
| By: | Alexis DIRER |
| Keywords: | , portfolio choice, risk aversion, timing risk |
| Date: | 2021 |
| URL: | http://d.repec.org/n?u=RePEc:leo:wpaper:2916&r= |
| By: | Michael Ewens; Joan Farre-Mensa |
| Abstract: | The U.S. entrepreneurial finance market has changed dramatically over the last two decades. Entrepreneurs raising their first round of venture capital retain 30% more equity in their firm and are more likely to control their board of directors. Late-stage startups are raising larger amounts of capital in the private markets from a growing pool of traditional and new investors. These private market changes have coincided with a sharp decline in the number of firms going public—and when firms do go public, they are older and have raised more private capital. To understand these facts, we provide a systematic description of the differences between private and public firms. Next, we review several regulatory, technological, and competitive changes affecting both startups and investors that help explain how the trade-offs between going public and staying private have changed. We conclude by listing several open research questions. |
| JEL: | G23 G24 G28 G34 G38 |
| Date: | 2021–12 |
| URL: | http://d.repec.org/n?u=RePEc:nbr:nberwo:29532&r= |
| By: | Turan G. Bali; David Hirshleifer; Lin Peng; Yi Tang |
| Abstract: | We find that among stocks dominated by retail investors, the lottery anomaly is amplified by high investor attention (proxied by high analyst coverage, salient earnings surprises, or recency of extreme positive returns) and intense social interactions (proxied by Facebook social connectedness or population density near firm headquarters). Such stocks’ lottery features attract greater Google search volume and retail net buying, followed by more negative earnings surprises and lower announcement-period returns. The findings provide insight into the roles of attention and social interaction in securities markets, and support the hypothesis that these forces contribute to investor attraction to lottery stocks. |
| JEL: | D84 D91 G12 G14 G4 G41 |
| Date: | 2021–12 |
| URL: | http://d.repec.org/n?u=RePEc:nbr:nberwo:29543&r= |
| By: | Uta Pigorsch; Sebastian Sch\"afer |
| Abstract: | This paper proposes a Deep Reinforcement Learning algorithm for financial portfolio trading based on Deep Q-learning. The algorithm is capable of trading high-dimensional portfolios from cross-sectional datasets of any size which may include data gaps and non-unique history lengths in the assets. We sequentially set up environments by sampling one asset for each environment while rewarding investments with the resulting asset's return and cash reservation with the average return of the set of assets. This enforces the agent to strategically assign capital to assets that it predicts to perform above-average. We apply our methodology in an out-of-sample analysis to 48 US stock portfolio setups, varying in the number of stocks from ten up to 500 stocks, in the selection criteria and in the level of transaction costs. The algorithm on average outperforms all considered passive and active benchmark investment strategies by a large margin using only one hyperparameter setup for all portfolios. |
| Date: | 2021–12 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2112.04755&r= |
| By: | Ashish Kumar; Abeer Alsadoon; P. W. C. Prasad; Salma Abdullah; Tarik A. Rashid; Duong Thu Hang Pham; Tran Quoc Vinh Nguyen |
| Abstract: | The prediction of stock price movement direction is significant in financial circles and academic. Stock price contains complex, incomplete, and fuzzy information which makes it an extremely difficult task to predict its development trend. Predicting and analysing financial data is a nonlinear, time-dependent problem. With rapid development in machine learning and deep learning, this task can be performed more effectively by a purposely designed network. This paper aims to improve prediction accuracy and minimizing forecasting error loss through deep learning architecture by using Generative Adversarial Networks. It was proposed a generic model consisting of Phase-space Reconstruction (PSR) method for reconstructing price series and Generative Adversarial Network (GAN) which is a combination of two neural networks which are Long Short-Term Memory (LSTM) as Generative model and Convolutional Neural Network (CNN) as Discriminative model for adversarial training to forecast the stock market. LSTM will generate new instances based on historical basic indicators information and then CNN will estimate whether the data is predicted by LSTM or is real. It was found that the Generative Adversarial Network (GAN) has performed well on the enhanced root mean square error to LSTM, as it was 4.35% more accurate in predicting the direction and reduced processing time and RMSE by 78 secs and 0.029, respectively. This study provides a better result in the accuracy of the stock index. It seems that the proposed system concentrates on minimizing the root mean square error and processing time and improving the direction prediction accuracy, and provides a better result in the accuracy of the stock index. |
| Date: | 2021–11 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2112.03946&r= |
| By: | Peng Zhou; Fangyi Li |
| Abstract: | The net value of the fund is affected by performance and market, and the researchers try to quantify these effects to predict the future net value by establishing different models. The current prediction models usually can only reflect the linear variation law, poorly handled or selectively ignore their nonlinear characteristics, so the prediction results are usually less accurate. This paper uses a fund prediction method based on the ARIMA-LSTM hybrid model. After preprocessing the historical data, the first filter out the linear data characteristics with the ARIMA model, then pass the data to the LSTM model to extract the nonlinear characteristic by residual, and finally superposition the respective prediction values of the two models to obtain the prediction results of the hybrid model. Empirically shows that the methods in the paper are more accurate and applicable than traditional fund prediction methods. |
| Date: | 2021–11 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2111.15355&r= |
| By: | MohammadAmin Fazli; Parsa Alian; Ali Owfi; Erfan Loghmani |
| Abstract: | Portfolio optimization is one of the essential fields of focus in finance. There has been an increasing demand for novel computational methods in this area to compute portfolios with better returns and lower risks in recent years. We present a novel computational method called Representation Portfolio Selection (RPS) by redefining the distance matrix of financial assets using Representation Learning and Clustering algorithms for portfolio selection to increase diversification. RPS proposes a heuristic for getting closer to the optimal subset of assets. Using empirical results in this paper, we demonstrate that widely used portfolio optimization algorithms, such as MVO, CLA, and HRP, can benefit from our asset subset selection. |
| Date: | 2021–11 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2111.15634&r= |
| By: | Seungho Jung; Jongmin Lee; Seohyun Lee |
| Abstract: | We investigate how corporate stock returns respond to geopolitical risk in the case of South Korea, which has experienced large and unpredictable geopolitical swings that originate from North Korea. To do so, a monthly index of geopolitical risk from North Korea (the GPRNK index) is constructed using automated keyword searches in South Korean media. The GPRNK index, designed to capture both upside and downside risk, corroborates that geopolitical risk sharply increases with the occurrence of nuclear tests, missile launches, or military confrontations, and decreases significantly around the times of summit meetings or multilateral talks. Using firm-level data, we find that heightened geopolitical risk reduces stock returns, and that the reductions in stock returns are greater especially for large firms, firms with a higher share of domestic investors, and for firms with a higher ratio of fixed assets to total assets. These results suggest that international portfolio diversification and investment irreversibility are important channels through which geopolitical risk affects stock returns. |
| Keywords: | Geopolitical risk, Textual analysis, Stock returns, Inter-Korean relations.; GPRNK index; stock return; firms' stock; GPRNK trend; search keyword; growth outlook; Stocks; Economic cooperation; Stock markets; Asset prices; Global |
| Date: | 2021–10–22 |
| URL: | http://d.repec.org/n?u=RePEc:imf:imfwpa:2021/251&r= |
| By: | Alim, Wajid; Ali, Amjad; Farid, Maryiam |
| Abstract: | The purpose of this study is to investigate the comparative impact of conventional and Islamic bonds over returns. It provides useful insights to investors to diversify investment by lowering the risk to the optimum level. This study examines the impact of the conventional and Islamic portfolios on returns through simple OLS regression, suggesting that Sukuk returns are positive and significant. Simultaneously, conventional bonds show a negative trend, but in the long run, the returns are significant. It indicates that the market is volatile due to macroeconomic factors that can reduce risks through portfolio diversification. Thus, this research suggests that investment can be secured by taking a rational portfolio decision that confirms robustness. Therefore, it is a good opportunity for the investors to get high margins over the investment tenure. |
| Keywords: | Financial Instruments, Portfolio Diversification, Islamic Finance, Sukuk, Conventional Bonds |
| JEL: | M0 M4 |
| Date: | 2021–11–10 |
| URL: | http://d.repec.org/n?u=RePEc:pra:mprapa:111211&r= |