Mani, G., and D. Barr. 1994. Stock-specific , non-linear neural net models: The AXON system. Paper presented at the second international workshop on neural networks in the capital markets, Pasadena, Calif.  Home/Search   Document Not in Database   Summary   Related Articles

....a stock s relative return as the stock s return minus the average return of the over 1600 stocks we model. We make predictions for all 1600 stocks at three different points in time and summarize the results. As a benchmark, the GA system is compared to an established neural network (NN) system (Mani Barr, 1994) using the same 1600 stocks and three points in time. We have used the NN system and its predecessors to forecast stock prices and manage portfolios for approximately 3 years. We examine the potential synergy from combining the GA and NN forecasts, as well as other ways in which the two ....

....Expectation 10 and Volatility 7 and . THEN Prediction = Up Such rules can serve as approximate explanations of how the various technical and fundamental input factors relate to future, individual stock returns. We perform the same set of 100 experiments using a neural network system (Mani Barr, 1994) with one layer of hidden nodes. Each experiment involves training the NN with the backpropagation algorithm, using the same training, stopping, and test sets as in the corresponding GA experiment. For each experiment, the NN makes no prediction when the squared correlation on the stopping set is ....

Mani, G., and D. Barr. 1994. Stock-specific , non-linear neural net models: The AXON system. Paper presented at the second international workshop on neural networks in the capital markets, Pasadena, Calif.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC