Showing papers by "M. Thenmozhi published in 2007"
TL;DR: In this article, support vector machines (SVM) have been used as an alternative forecasting tool for Nifty Index returns and it will lead to better returns based on the traditional forecasting accuracy measures, such as root mean squared errors, and financial criteria such as risk-adjusted measures of return.
Abstract: The present study, investigates the predictability of S&P CNX NIFTY Index returns using Support vector machines (SVM). The performance of the SVM model in forecasting Nifty index returns is rigorously evaluated in terms of widely used statistical metrics like mean absolute error, root mean square error, normalized mean square error, correctness of sign and direction change (Pesaran and Timmermann (1992, DA test), and equal forecast accuracy using Diebold and Mariano (1995, DM test) by comparing its performance with those of neural network, random forest regression and a linear ARIMA model. The four competiting models are also examined in terms of various trading performance and economic criteria like annualized return, Sharpe ratio, maximum drawdown, annualized volatility, average gain/loss ratio etc via a trading experiment. The findings of the study reveal that SVM model achieves greater forecasting accuracy and improves prediction quality compared to other models experimented in the study. The SVM model can be used as an alternative forecasting tool for Nifty Index returns and it will lead to better returns based on the traditional forecasting accuracy measures, such as root mean squared errors, and financial criteria, such as risk-adjusted measures of return.
22 citations
Posted Content•
TL;DR: In this paper, the authors examined share price reaction to the announcement of bonus issue for a sample of Indian companies and showed that the number of shares issued does not affect the abnormal returns of the company.
Abstract: This study examines share price reaction to the announcement of Bonus Issue for a sample of Indian Companies. Standard event study methodology has been used for the purpose of studying the Bonus issue announcement reaction. Bonus issue announcement yields negative abnormal returns around the announcement date. There is a negative reaction after the bonus issue announcement conveying that the market underreacts after the announcement. It is also observed that there is no information leakage prior to the announcement. Reduction in the liquidity ratio after the announcement is evidenced, though insignificant. All the three liquidity measures seem to be inconsistent with the enhanced trading liquidity expectation. Cross sectional regression shows that the number of shares issued, convey a positive signal to the investors. Further it has been evidenced that the size of the firm issuing bonus shares does not affect the abnormal returns of the company. The study supports Signaling Hypothesis and Cash Substitution Hypothesis.
9 citations
TL;DR: In this paper, the authors investigated the price discovery function in spot and S&PCNX Nifty futures market and showed that the information flow from spot to futures is stronger and spot market dominates the futures market in terms of return and volatility.
Abstract: The lead-lag relationship between spot and futures markets has been investigated extensively in the financial economics literature. This paper investigates the price discovery function in spot and S&PCNX Nifty futures market. The analysis has been done with reference to near month, next month and far month index futures respectively. The results of VECM-SURE model show that there exists bi-directional Granger causality between spot and futures market, but spot market plays a more important role in price discovery. The results of impulse response function and information share indicate that most of the price discovery happens in index spot market. The evidence of EGARCH model shows that the volatility spillover between spot and futures markets is bi-directional. However, the information flow from spot to futures is stronger and spot market dominates the futures market in terms of return and volatility.
3 citations
TL;DR: In this paper, the authors present the application and development of three different hybrid methodology that combine both the ARIMA and ANN model to take advantage of the unique strengths of both linear and nonlinear modeling to model and predict the stock market index returns.
Abstract: This study presents the application and development of three different hybrid methodology that combines both the ARIMA and ANN model to take advantage of the unique strengths of both linear and nonlinear modeling to model and predict the stock market index returns. The input to the hybrid ARIMA - neural network models, includes (a) past returns, the forecast and residual (results from ARIMA model), (b) forecast and residual value (results from ARIMA model) - ARIMABP model and (c) the forecast (results from ARIMA model) and the forecast residual (results of ARIMA model) of neural network. On the other hand, the benchmark model includes, ARIMA and neural network models. The performance of the models are evaluated in terms of widely used statistical metrics, correctness of sign and direction change, and various trading performance measures like annualized return, Sharpe ratio, maximum drawdown, annualized volatility, average gain/loss ratio etc via a trading strategy. The findings of the study reveals that ARIMABP model achieve greater accuracy based on the traditional forecasting accuracy measures, sign and directional change and trading experiments and add value as a forecasting and quantitative trading tool.
3 citations