Predicting Stock Market Price Using Neural Network Model

The present article predicts the movement of daily Indian stock market (S&P CNX Nifty) price by using Feedforward Neural Network Model over a period of eight years from January 1st 2008 to April 8th 2016. The prediction accuracy of the model is accessed by normalized mean square error (NMSE) and sign correctness percentage (SCP) measure. The study indicates that the predicted output is very close to actual data since the normalized error of one-day lag is 0.02. The analysis further shows that 60 percent accuracy found in the prediction of the direction of daily movement of Indian stock market price after the financial crises period 2008. The study indicates that the predictive power of the feedforward neural network models reasonably influenced by one-day lag stock market price. Hence, the validity of an efficient market hypothesis does not hold in practice in the Indian stock market. This article is quite useful to the investors, professional traders and regulators for understanding the effectiveness of Indian stock market to take appropriate investment decision in the stock market.

Disaggregated IPO returns, economic uncertainty and the long-run performance of SME IPOs

PurposeSmall and medium enterprises (SMEs) play a crucial role in national economies worldwide, generating employment and contributing to innovation. This study tries to investigate the performance of the newly started IPO platform for the SMEs in India through a two-staged framework developed to measure pre-market and post-market underpricing separately and the impact of economic policy uncertainty (EPU) on the IPO returns using the EPU index which is based on newspaper coverage frequency. Further, the long-run performance of SME IPOs and the factors affecting the same have also been analyzed. The two-staged framework is helpful in capturing the impact of different factors separately on the two distinctive markets and providing effective investment strategies to the investors.Design/methodology/approachA sample of 384 SME IPOs issued during 2012–2018 has been analyzed using robust regression analysis.FindingsThe study highlights the fact that there are differences in the factors affecting pre-market and post-market underpricing and reports that investors subscription rate, issue expenses, lead manager reputation and EPU are positively associated, whereas the age of the firm is negatively associated with the pre-market underpricing, and lead manager reputation positively impacts the post-market underpricing whereas issue premium and pre-market underpricing are negatively associated. Pre-market underpricing subsumes all the impact of EPU (publicly available information) in it, hence providing credence to the semi-strong market hypothesis of the Efficient Market Hypothesis (EMH). The long-run performance of SME IPOs increases with time, and lead manager reputation, pre-market and post-market underpricing are positively related to the one-year return whereas issue size, turnover and issue expense are negatively related.Originality/valueThis paper is believed to be the first attempt to analyze the performance of SME IPOs by disaggregating IPO underpricing. The findings of this study will have a great insight for the investors and policymakers.

The Liquidity Spillover Effects Between the Stock Index Futures and Spot Under the Fractal Market Hypothesis

In recent years, the extreme risk events occurred frequently in the financial market have not only brought huge losses to investors and inflicted heavy losses on the market, but also posed a severe challenge for the traditional effective market hypothesis. These extreme risk events are often accompanied by sudden plummeting of liquidity. Different from the efficient market hypothesis(EMT), firstly, this paper studies the nonlinear fluctuation characteristics and causes of contracts with different maturity periods in China stock index futures market under the framework of fractal market theory and using the multifractal detrended fluctuation model Secondly, under the framework of the fractal market theory, the existence of the liquidity spillover effect between the stock index futures and spot is tested, the direction, intensity, and contribution of spillover between stock index futures and spot are analyzed. Finally, there is a robustness test. The study finds that both stock index futures and stock index spot in China have obvious nonlinear fractal fluctuation characteristics, and stock index futures have higher degree of multifractal, the characteristics are related to correlated multifractal and distributed multifractal; the longer the maturity period of the stock index futures contract, the lower the multifractal degree; there are significant asymmetric liquidity spillover effects between the stock index futures and spot; the multifractal degree has an important influence on the intensity and contribution of the liquidity spillover effect, and the multifractal degree is inversely proportional to the intensity of liquidity spillover and the contribution of spot to futures fluctuations.

Beating the market? A mathematical puzzle for market efficiency

The efficient market hypothesis is highly discussed in economic literature. In its strongest form, it states that there are no price trends. When weakening the non-trending assumption to arbitrary short, small, and fully unknown trends, we mathematically prove for a specific class of control-based trading strategies positive expected gains. These strategies are model free, i.e., a trader neither has to think about predictable patterns nor has to estimate market parameters such as the trend’s sign like momentum traders have to do. That means, since the trader does not have to know any trend, even trends too small to find are enough to beat the market. Adjustments for risk and comparisons with buy-and-hold strategies do not satisfactorily solve the problem. In detail, we generalize results from the literature on control-based trading strategies to market settings without specific model assumptions, but with time-varying parameters in discrete and continuous time. We give closed-form formulae for the expected gain as well as the gain’s variance and generalize control-based trading rules to a setting where older information counts less. In addition, we perform an exemplary backtesting study taking transaction costs and bid-ask spreads into account and still observe—on average—positive gains.

GMDH-type Neural Networks for Predicting Financial Time Series: A Study of Informational Efficiency of Stock Markets

A theory of Efficient Market Hypothesis (EMH) has been introduced by Fama to analyse financial markets. In particular the EMH theory has been proven in real cases under different conditions, including financial crises and frauds. The EMH assumes to examine the prediction accuracy of models designed on retrospective data. Such prediction models could be designed in different ways that motivated us to explore Machine Learning (ML) methods known for building models providing a high prediction performance. In this study we propose a ``deep'' learning method for building high-performance prediction models. The proposed method is based on the Group Method of Data Handling (GMDH) that is the deep learning paradigm capable of building multilayer neural-network models of a near-optimal complexity on given data. We show that the developed GMDH-type neural network has outperformed the models built by the conventional ML methods on the Warsaw Stock Exchange data. It is important that the complexity of the designed GMDH-type neural-networks is defined by the number of layers and connections between neurons. The performances of models were compared in terms of the prediction errors. We report a significantly smaller prediction error of the proposed method than that of the conventional autoregressive and "shallow’’ neural-network models. This finally allows us to conclude that traders will be advantaged by the proposed method.

The Predictability and profitability of Trading Range Break-out Trading Rules: Evidence from Pakistan Stock Exchange

The efficient market hypothesis has been one of themost extensively researched topics in the academic literature for decades. An implication ofweak form of efficiency is that the technical trading rules will not produce abnormal returns. The purpose of this research is to analyze findings of application of trading range breakout test on daily closing share prices of 100 companies listed on a Pakistan Stock Exchange over ten years from 2006 to 2015,thus examining its efficiency at the weak form. The results show strong support for trading range break-out rules having both predictability and profitability for PSX. It refers that the returns from these rules are not same as investors earn from a naïve buy and hold strategy. The uses of the trading range break-out rules produce abnormal returns to investors and hence nullify the weak form of efficiency on PSX.

The Impact of Behavioural Biases on Stock Volatility: Evidence From Pakistan Stock Exchange

The main purpose of the current study is to investigate the impact of behavioural biases such as confidence, optimism, and pessimism on stock volatility evidence from Pakistan Stock Exchange (PSX). Prospect theory and overconfidence theory formed the foundation of this study. The methodology composed of positivist philosophical stance, deductive approach and quantitative methods with secondary data. Data analysis involved the use of descriptive statistics, correlation and regression. The study consists ofa 10-years analysis from June 2008 to June 2018 and includes daily trading volumes KSE-100 index in PSX. Results reveal that behavioral biases such as confidence have a positive impact on stock volatility. Similarly, optimism bias has also a positive impact on stock volatility. While pessimism bias has recorded a negative impact on stock volatility. Therefore, it is concluded that behavioural biases have an impact on stock volatility. The current study has a contribution to the body of knowledge on the ground that it attempts to change the traditional notion of society who believes in the efficient market hypothesis. The study has implications for different stakeholders of stock markets.