Weightless Neural Network for High Frequency Trading

摘要

High frequency trading depends on quick reactions to meaningful information. In order to identify opportunities in intraday negotiation in the stock markets, we propose a weightless neural network autonomous trader agent composed by forecasting and decision modules. The forecasting module uses ridge regression, which compared favorably against recursive least squares with exponential forgetting. The decision model applies the predicted prices to compute technical indicators based on a set of relative strength indicators evaluated by back-testing, which are then used to train the weightless neural network WiSARD in deciding whether to buy or sell stocks. Experimental results on a real dataset from the Brazilian stock market showed that it is feasible encode the back-testing in WiSARD in order to improve trading rules in a way that is compatible with the reaction time required by online market updates.