Precise Stock Price Prediction for Robust Portfolio Design from Selected\n Sectors of the Indian Stock Market

Stock price prediction is a challenging task and a lot of propositions exist\nin the literature in this area. Portfolio construction is a process of choosing\na group of stocks and investing in them optimally to maximize the return while\nminimizing the risk. Since the time when Markowitz proposed the Modern\nPortfolio Theory, several advancements have happened in the area of building\nefficient portfolios. An investor can get the best benefit out of the stock\nmarket if the investor invests in an efficient portfolio and could take the buy\nor sell decision in advance, by estimating the future asset value of the\nportfolio with a high level of precision. In this project, we have built an\nefficient portfolio and to predict the future asset value by means of\nindividual stock price prediction of the stocks in the portfolio. As part of\nbuilding an efficient portfolio we have studied multiple portfolio optimization\nmethods beginning with the Modern Portfolio theory. We have built the minimum\nvariance portfolio and optimal risk portfolio for all the five chosen sectors\nby using past daily stock prices over the past five years as the training data,\nand have also conducted back testing to check the performance of the portfolio.\nA comparative study of minimum variance portfolio and optimal risk portfolio\nwith equal weight portfolio is done by backtesting.\n