论文信息 - Forecasting real time financial series

Forecasting real time financial series

The author reports how he generated a set of real time neural network forecasts to win the second place in the Financial Series Competition at the International Joint Conference on Neural Networks in 1999 (IJCNN'99). The accuracy and profitability of his forecasts are evaluated, and the finance implication is discussed. He provides comprehensive evaluation on the accuracy of the forecasts relative to those from the benchmark model of random walk. Various measures of forecasting accuracy, such as MAE, RMSE, and MAPE are used to facilitate the comparison.

Min Qi | M. Qi

[1] F. Diebold,et al. Comparing Predictive Accuracy , 1994, Business Cycles.

[2] M. Hashem Pesaran,et al. A generalization of the non-parametric Henriksson-Merton test of market timing , 1994 .

[3] Bernard Widrow,et al. Improving the learning speed of 2-layer neural networks by choosing initial values of the adaptive weights , 1990, 1990 IJCNN International Joint Conference on Neural Networks.

[4] Kurt Hornik,et al. Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[5] Halbert White,et al. Connectionist nonparametric regression: Multilayer feedforward networks can learn arbitrary mappings , 1990, Neural Networks.

[6] H. White,et al. A Reality Check for Data Snooping , 2000 .