Low Complexity Algorithmic Trading by Feedforward Neural Networks

In this paper, novel neural based algorithms are developed for electronic trading on financial time series. The proposed method is estimation based and trading actions are carried out after estimating the forward conditional probability distribution. The main idea is to introduce special encoding schemes on the observed prices in order to obtain an efficient estimation of the forward conditional probability distribution performed by a feedforward neural network. Based on these estimations, a trading signal is launched if the probability of price change becomes significant which is measured by a quadratic criterion. The performance analysis of our method tested on historical time series (NASDAQ/NYSE stocks) has demonstrated that the algorithm is profitable. As far as high frequency trading is concerned, the algorithm lends itself to GPU implementation, which can considerably increase its performance when time frames become shorter and the computational time tends to be the critical aspect of the algorithm.