Mining quantitative association rules with stock trading data using multi-objective Meta heuristic algorithms based on genetic algorithm

Forecasting stock return is an important financial subject that has attracted researchers’ attention for many years. Investors have been trying to find a way to predict stock prices and to find the right stocks and right timing to buy or sell. Recently, data mining techniques and artificial intelligence techniques have been applied to this area. Association discovery is one of the most common Data Mining techniques used to extract interesting knowledge from large datasets. In this paper, we propose a new multi-objective evolutionary model which maximizes the omprehensibility, interestingness and performance of the objectives in order to mine a set of quantitative association rules from financial datasets, including 10 common indicators of technical analysis. To accomplish this, the model extends the two well-known Multi-objective Evolutionary Algorithms, Non-dominated Sorting Genetic Algorithm II and Non-dominated Ranked Genetic Algorithm, to perform an evolutionary learning of the intervals of the attributes and a condition selection for each rule. Moreover, this proposal introduces an external population and a restarting process to the evolutionary model in order to store all the nondominated rules found and improve the diversity of the rule set obtained. The results obtained over real-world stock datasets demonstrate the effectiveness of the proposed approach.