In this paper, an Adaptive Rival Penalized Competitive Learning and Combined Linear Prediction model is applied to the forecast of stock price and exchange rate. As shown by the experimental results, this approach not only is better than Elman Net and MA(q) models in the criterion of root mean square error, but also can bring in more returns in the trade… (More)
on financial prediction. They are evaluated in terms of prediction accuracy as well as profit gains under two simple trading systems. Computer experiments show how Adaptive RPCL-CLP out-performs RPCL-ART and some traditional methods such as MA and Random Walk Models.