Proposed system for estimating intrinsic value of stock using Monte Carlo simulation

Stock market prediction has been the bane and goal for investors, and one of the biggest challenges for artificial intelligence (AI) community. National economies have a great impact by the behaviour of their stock markets. Markets have become a more accessible investment tool. Attribute that all stock markets have in common is uncertainty. This uncertainty associated with stock value in short and long term future investments are undesirable. Stock market prediction is instrumental in process of investment. Drawbacks of existing system faces technical difficulties such as estimating share of dividends, state vector while implementing stochastic modelling for risk analysis. To overcome drawbacks of existing system, proposed system makes an effort of generating a combination of more than one lakh seventy thousand scenarios to find intrinsic value of company, displaying results in graphical visualization. A large scenario generation of distinct intrinsic stock value done by the system will provide intrinsic stock value for each scenario. A large set of values for all the input parameters for example high growth value, declining growth value, terminal growth value, return on equity needs to be created, so that possible intrinsic value can be generated by system. The system will calculate statistical indicators like mean, median, mode, skewness and kurtosis of large data set consisting intrinsic value of company. Comparing statistically calculated intrinsic value and current market price, system will be able to add a robust statistical reasoning for investment decision. This reasoning will have no human or emotional biases as there will be no human intervention involved for arriving to the final intrinsic value of stock. Monte Carlo simulation is best suited solution for generating random scenarios that fall in line with Brownian walk motion of stock prices.