• E. Jayanthi
• S. Shunmugapriya

To profit from trading or to mitigate market dangers, investors need dependable financial application forecasting methods. When the FTSE100 and the New York Stock Exchange return, this study examines the predictive accuracy of a trading strategy using a neurofuzzy model. Furthermore, empirical evidence supports the premise proposed by Bekaert and Wu (2000) that the inclusion of conditional volatility change estimates substantially improves the predictability of the neurofuzzy model. Consequently, headed into the following trading day—a potentially pivotal juncture—we are armed with reliable data. By continuously surpassing the returns of feedforward neural networks, Markov-switching models, and buy-and-hold strategies, the volatility-based neurofuzzy model yields a superior total return (including transaction costs). Two plausible hypotheses that provide weight to the notion that dependence on indicators results from reliance on volatility are the presence of portfolio insurance plans in the stock markets and the "volatility feedback" idea. Passive portfolio management may be surpassed by an investing strategy established on the suggested neurofuzzy model.

Hybrid neurofuzzy approaches for sign prediction and volatility dynamics

"Hybrid neurofuzzy approaches for sign prediction and volatility dynamics", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 6, page no.c506-c520, June-2024, Available :http://www.jetir.org/papers/JETIR2406265.pdf

"Hybrid neurofuzzy approaches for sign prediction and volatility dynamics", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 6, page no. ppc506-c520, June-2024, Available at : http://www.jetir.org/papers/JETIR2406265.pdf