The nonlinear relationship in the joint time-frequency domain has been studied for the Indian National Stock Exchange (NSE) with the international Gold price and WTI Crude Price being converted from Dollar to Indian National Rupee based on that week’s closing exchange rate. Though a good correlation was obtained during some period, but as a whole no such cointegration relation can be found out. Using the Discrete Wavelet Analysis, the data was decomposed and the presence of Granger Causal relations was tested. Unfortunately, no significant relationships are being found. We then studied the Wavelet Coherence of the two pairs, namely NSE-Nifty & Gold and NSE-Nifty & Crude. For different frequencies, the coherence between the pairs have been studied. At lower frequencies, some relatively good coherence have been found. In this paper, we report for the first time the co-movements between Crude Oil, Gold and Indian Stock Market Index using Wavelet Analysis (both Discrete and Continuous), a technique which is most sophisticated and recent in market analysis. Thus, for long-term traders they can include gold and/or crude in their portfolio along with NSE-Nifty index in order to decrease the risk (volatility) of the portfolio for the Indian Market. But for short-term traders, it will not be effective, not to include all the three in their portfolio.

Various researches have been conducted on forecasting stock prices. Several tools ranging from statistical techniques to quantitative methods have been used by researchers to forecast the market. But so far, very little research has been done on forecasting the stock markets of the Gulf countries such as Saudi Arabia, United Arab Emirates, Oman, Kuwait, Bahrain, and Qatar. Our approach is to predict the market indices of the Gulf countries using Long Short‐Term Memory (LSTM) techniques. Thereafter, we optimized the hyperparameters of the LSTM technique using various optimization methods such as Grid Search and Bayesian Optimization with Gaussian Process and found out the best‐suited hyperparameter for the LSTM model. We tried the LSTM method for predicting the indices using data from the last twenty years.

No abstract

No abstract

No abstract