Journal of Finance and Data Science最新文献

There has been much debate about whether returns on financial assets, such as stock returns or commodity returns, are predictable; however, few studies have investigated cryptocurrency return predictability. In this article we examine whether bitcoin returns are predictable by a large set of bitcoin price-based technical indicators. Specifically, we construct a classification tree-based model for return prediction using 124 technical indicators. We provide evidence that the proposed model has strong out-of-sample predictive power for narrow ranges of daily returns on bitcoin. This finding indicates that using big data and technical analysis can help predict bitcoin returns that are hardly driven by fundamentals.

To better understand the relation between public markets and private equity, we consider quadratic hedging strategies to replicate the typical payment stream pattern associated with private equity funds by traded factors. Our methodology is inspired by the risk-minimization framework developed in financial mathematics and applies the componentwise L₂ Boosting machine learning technique to empirically identify feasible replication strategies. The application to US venture capital fund data further draws on a stability selection procedure to enhance model sparsity. Interestingly a natural connection to the famous Kaplan and Schoar (2005) public market equivalent approach can be established.

The Publisher regrets that this article is an accidental duplication of an article that has already been published in <JFDS, 5/2(2019) 116-125>,http://dx.doi.org/10.1016/j.jfds.2019.04.001.The duplicate article has therefore been withdrawn.

The full Elsevier Policy on Article Withdrawal can be found at https://www.elsevier.com/about/our-business/policies/article-withdrawal.

Government of India aims at making the Indian Banks internationally competitive. In the wake of intense competition and changing global and national business environment, the efficiency issues have emerged as an important pillar of success in the Indian banking sector. Therefore, it is an essential task to comprehend the efficiency levels of the overall Indian banking sector and also across different ownership structures (viz. Public, Private and Foreign). The present study endeavors to carry out an assessment of intra-sector efficiency in the Indian banking sector based on a cross-sectional data of 66 banks for the year 2015-16. The authors employ directional distance function based meta-frontier DEA approach and the results reveal that the Indian banking sector is 73.44% efficient. It also confirms the existence of different production functions across different ownership structures of the industry. Among the different ownership structures, the group frontier of foreign banks coincides with the meta-frontier. The group frontier of private sector banks is the second closest to the meta-frontier and public sector banks are found to be the laggards in the overall industry. The study gains special significance in the backdrop of the recommendations floated by the Reserve Bank of India and Ministry of Finance (Government of India) to consolidate the public sector banks in order to retain fewer but healthier banks. The finding of the study fully support these recommendations and affirms that consolidation in the industry will bring positive synergies and will lead to the enhancement of efficiency levels in the industry.

This paper examines the return and volatility spillovers in the Nigerian Financial market. We specifically analyse the spillovers in the capital market, money market and foreign exchange market utilizing monthly data for the period January 2002 to June 2017. The paper employs the Diebold and Yilmaz (DY hereafter) (2009, 2012) approach to compute the total spillover, directional spillover, and net spillover indexes. We also consider the rolling window analyses to capture the secular and cyclical movement in the financial markets over the period of consideration. The paper observes weak degree of interdependence as well as cross-market spillovers among the financial instruments.

The stock market is the largest net receiver and sender of return spillovers to other markets, while the foreign exchange market is the net giver of volatility spillovers followed by the money market, and the stock market is the net recipient. In addition, return spillovers unveils slight trends and bursts while volatility spillovers show significant bursts but no trends. Concomitantly, the significant burst was attributed to the removal of currency peg in 2016 by the Central Bank of Nigeria. Our results are robust to the different VAR lag structure.

We analyzed data collected from retail investors in the Chinese stock market from a Fintech mobile platform to find evidence of the self-fulfilling prophecy effect. We found a statistically significant correlation between the predicted and actual Shanghai Stock Exchange Composite Index (SSECI) as well as non-random deviation patterns. We also analyzed participating investor behaviors and discussed the implications and future research.

This paper aims to investigate how Machine Learning (ML) techniques perform in the prediction of cryptocurrency prices. We answer if Support Vector Machines (SVM) and Artificial Neural Networks (ANN) based strategies can generate abnormal risk-adjusted returns when applied to Bitcoin, the largest decentralized digital currency in terms of market capitalization. Findings indicate that traders are able to earn conservative returns on the risk adjusted basis, even accounting for transaction costs, when using SVM. Furthermore, the study suggests that ANN can explore short run informational inefficiencies to generate abnormal profits, being able to beat even buy-and-hold during strong bull trends.

Over the years, financial engineering ranging from the study of financial signals to the modelling of financial prediction is one of the most stimulating topics for both academia and financial community. Not only because of its importance in terms of financial and commercial values, but more it vitally poses a real challenge to worldwide researchers and quants owing to its highly chaotic and almost unpredictable nature.

This paper devises an innovative Chaotic Oscillatory Multi-agent-based Neuro-computing System (a.k.a. COSMOS) for worldwide financial prediction and intelligent trading. With the adoption of author's theoretical works on Lee-oscillator with profound transient-chaotic property, COSMOS effectively integrates chaotic neural oscillator technology into: 1) COSMOS Forecaster - Chaotic FFBP-based Time-series Supervised-learning agent for worldwide financial forecast and; 2) COSMOS Trader - Chaotic RBF-based Actor-Critic Reinforcement-learning agents for the optimization of trading strategies. COSMOS not only provides a fast reinforcement learning and forecast solution, more prominently it successfully resolves the massive data over-training and deadlock problems which usually imposed by traditional recurrent neural networks and RBF networks using classical sigmoid or gaussian-based activation functions.

From the implementation perspective, COSMOS is integrated with 2048-trading day time-series financial data and 39 major financial signals as input signals for the real-time prediction and intelligent agent trading of 129 worldwide financial products which consists of: 9 major cryptocurrencies, 84 forex, 19 major commodities and 17 worldwide financial indices. In terms of system performance, past 500-day average daily forecast performance of COSMOS attained less 1% forecast percentage errors and with promising results of 8–13% monthly average returns.

In this study, a liquidity timing ability of mutual fund managers in emerging markets had been examined. The analysis based on three important emerging markets in ASEAN Economic Community, namely Indonesia, Malaysia, and Thailand. We found that these mutual fund managers have an ability to forecast the market wide liquidity at both aggregate level and portfolio level. Additional, the evidence suggested that the high ability fund managers can successfully manage the liquidity in all markets at portfolio level. Besides, a robustness test demonstrates a similar result.