Association rule mining using enhanced apriori with modified GA for stock prediction

In stock marketing, picking the right stock depends on the true stock value and the ability to pick the stock is crucial as it influences the profit of investors. Data mining techniques have been used for forecasting the stock market price and have shown successful results too. Yet, the investors are looking for a genuine forecasting model to predict the stock rule more efficiently. This work intends to form a technique based on association rule mining using enhanced apriori algorithm with modified genetic algorithm for the estimation of fine stock rule. The enhanced apriori algorithm mainly focuses on association rule mining and hence to avoid the time computation complexity. This modified GA uses interrelating crossover and mutation operations. These genetic operations avoid genetic algorithm from premature convergence and hence, enables strong association rules to be generated.