|
on Financial Markets |
|
Issue of 2018‒01‒15
six papers chosen by |
| By: | Kent Daniel; Lira Mota; Simon Rottke; Tano Santos |
| Abstract: | In the finance literature, a common practice is to create factor-portfolios by sorting on characteristics (such as book-to-market, profitability or investment) associated with average returns. The goal of this exercise is to create a parsimonious set of factor-portfolios that explain the cross-section of average returns, in the sense that the returns of these factor-portfolios span the mean-variance efficient portfolio. We argue that this is unlikely to be the case, as factor-portfolios constructed in this way fail to incorporate information about the covariance structure of returns. By using a high statistical power methodology to forecast future covariances, we are able to construct a set of portfolios which maintains the expected return, but hedges out much of the unpriced risk. We apply our methodology to hedge out unpriced risk in the Fama and French (2015) five-factors. We find that the squared Sharpe ratio of the optimal combination of the resulting hedged factor-portfolios is 2.29, compared with 1.31 for the unhedged portfolios, and is highly statistically significant. |
| JEL: | G00 G1 G12 G14 |
| Date: | 2017–12 |
| URL: | http://d.repec.org/n?u=RePEc:nbr:nberwo:24164&r=fmk |
| By: | Masaya Abe; Hideki Nakayama |
| Abstract: | Many studies have been undertaken by using machine learning techniques, including neural networks, to predict stock returns. Recently, a method known as deep learning, which achieves high performance mainly in image recognition and speech recognition, has attracted attention in the machine learning field. This paper implements deep learning to predict one-month-ahead stock returns in the cross-section in the Japanese stock market and investigates the performance of the method. Our results show that deep neural networks generally outperform shallow neural networks, and the best networks also outperform representative machine learning models. These results indicate that deep learning shows promise as a skillful machine learning method to predict stock returns in the cross-section. |
| Date: | 2018–01 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:1801.01777&r=fmk |
| By: | Xi Zhang; Yunjia Zhang; Senzhang Wang; Yuntao Yao; Binxing Fang; Philip S. Yu |
| Abstract: | Traditional stock market prediction approaches commonly utilize the historical price-related data of the stocks to forecast their future trends. As the Web information grows, recently some works try to explore financial news to improve the prediction. Effective indicators, e.g., the events related to the stocks and the people's sentiments towards the market and stocks, have been proved to play important roles in the stocks' volatility, and are extracted to feed into the prediction models for improving the prediction accuracy. However, a major limitation of previous methods is that the indicators are obtained from only a single source whose reliability might be low, or from several data sources but their interactions and correlations among the multi-sourced data are largely ignored. In this work, we extract the events from Web news and the users' sentiments from social media, and investigate their joint impacts on the stock price movements via a coupled matrix and tensor factorization framework. Specifically, a tensor is firstly constructed to fuse heterogeneous data and capture the intrinsic relations among the events and the investors' sentiments. Due to the sparsity of the tensor, two auxiliary matrices, the stock quantitative feature matrix and the stock correlation matrix, are constructed and incorporated to assist the tensor decomposition. The intuition behind is that stocks that are highly correlated with each other tend to be affected by the same event. Thus, instead of conducting each stock prediction task separately and independently, we predict multiple correlated stocks simultaneously through their commonalities, which are enabled via sharing the collaboratively factorized low rank matrices between matrices and the tensor. Evaluations on the China A-share stock data and the HK stock data in the year 2015 demonstrate the effectiveness of the proposed model. |
| Date: | 2018–01 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:1801.00588&r=fmk |
| By: | Ming Dong; David Hirshleifer; Siew Hong Teoh |
| Abstract: | We test how market overvaluation affects corporate innovative activities and success. Estimated stock overvaluation is very strongly associated with R&D spending, innovative output, and measures of innovative novelty, originality, and scope. R&D is much more sensitive than capital investment to overvaluation. The effects of misvaluation on R&D come more from a non-equity channel than via equity issuance. The sensitivity of R&D and innovative output to misvaluation is greater among growth, overvalued, and high turnover firms. This evidence suggests that market overvaluation may have social value by increasing innovative output and by encouraging firm to engage in ‘moon shots.’ |
| JEL: | D22 D23 G14 G3 G31 G32 O32 |
| Date: | 2017–12 |
| URL: | http://d.repec.org/n?u=RePEc:nbr:nberwo:24142&r=fmk |
| By: | Kamilla Sabitova |
| Abstract: | The paper examines the Chinese market reaction to the ADR issue by comparing returns and their stochastic variances of the Chinese firms cross-listed in the U.S. stock market. First, It was implemented capital asset pricing model (CAPM) to determine expected returns A and N shares. The CAPM provided with a methodology to quantify risk and translate that risk into estimates of expected return on equity. Overall findings document that N shares of Chinese entities listed on U.S. market were greatly affected by economic turmoil during the period of World Financial Crises 2007-2008 than the A shares listed on the local market. After in order to test the hypothesis of beneficial cross-listing, it was implemented an event study method and the returns was modeled following GARCH process, which assumes homoscedasticity in residual returns. The results indicate a significant negative abnormal market return on an ADR listing date. The return volatilities after the listing date are compared to those before the listing. Four out of ten companies experienced increased volatility of local return after the cross-listing. Keywords: cross-listing, ADR, rate of return, volatility, CAPM, GARCH model, N shares, A shares |
| Date: | 2017–11 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:1711.08799&r=fmk |
| By: | Guduza, Sinazo; Phiri, Andrew |
| Abstract: | This study investigates weak form efficiency for 4 stock and 7 bond market return under the Johannesburg Stock Exchange (JSE) using monthly data spanning from 2002 to 2016. Our empirical strategy consists of using both individual and panel based unit root testing procedures. Moreover, we split our empirical data into two sub-samples corresponding to periods before and periods subsequent to the global financial crisis. Our empirical results point to an overwhelming evidence of weak form efficiency as the integration test fail to produce convincing evidence of unit root behaviour amongst the observed time series. The study thus confirms the efficiency of equities and debt markets in South Africa in light of the global financial crisis. |
| Keywords: | Equity markets, Bond market; Efficient market hypothesis; unit root tests; Johannesburg Stock Exchange (JSE); South Africa |
| JEL: | C12 C13 C22 C23 G10 N27 |
| Date: | 2017–12–26 |
| URL: | http://d.repec.org/n?u=RePEc:pra:mprapa:83487&r=fmk |