In recent years, equivolume charting has become a popular technical analysis tool used by individual investors and brokerage firms for make better investment and trading decisions. While useful, any approach or modification that can help improve the performance of technical analysis based equivolume charting for trading stocks should be of great assistance to investors. To this end, this dissertation proposes the development of a hybrid intelligent system applied to the Volume Adjusted Moving Average (VAMA), a technical indicator developed from equivolume charting. A Neuro-Fuzzy based Genetic Algorithm (NF-GA) system of the VAMA membership functions that integrates neural networks, fuzzy logic, and genetic algorithms techniques for increasing the efficiency of the VAMA for trading stocks is presented. The NF-GA system takes advantage of the synergy among these intelligent techniques to provide effective trading decisions for investors. For the system, the neural networks help provide earlier VAMA trading signals, fuzzy logic helps the system handle the uncertainty of the trading signals, and the genetic algorithms help the system optimize the trading signals. The trading simulation was tested in different market trends, including trending-up, flat, and trending-down markets of past S&P 500 index data. The trading with and without a 0.50% transaction cost was also examined. The overall results show that the NF-GA system performed best and displays robustness when compared to other benchmarks, including the VAMA alone, the VAMA with neural networks assistance, the neuro-fuzzy system of the VAMA, and the-buy-and-hold trading strategy.