Caldwell, R.B., "Performances Metrics for Neural Network-based Trading System Development", NeuroVe$t Journal, Vol. 3, No. 2. 1995, pp22-26. Home/Search Document Not in Database Summary Related Articles Check |
This paper is cited in the following contexts:
Time dependent Directional Profit Model for Financial Time Series.. - Chew (2000) (Correct)
.... statistical techniques for forecasting have reached their limitation in applications with nonlinearities in the data set [5] It is observed that Normalized Mean Square Error (NMSE) and other error functions that are used for financial forecasting models may not make sense in the financial context [1]. Caldwell [1] gives a general review for the performance metrics. Yao et al. 9] use the correctness of trend and a paper profit to judge the performance of neural network forecasting model. Caldwell [1] also proposes a new measure, namely, weighted directional symmetry (WDS) which weights ....
.... for forecasting have reached their limitation in applications with nonlinearities in the data set [5] It is observed that Normalized Mean Square Error (NMSE) and other error functions that are used for financial forecasting models may not make sense in the financial context [1] Caldwell [1] gives a general review for the performance metrics. Yao et al. 9] use the correctness of trend and a paper profit to judge the performance of neural network forecasting model. Caldwell [1] also proposes a new measure, namely, weighted directional symmetry (WDS) which weights errors based on a ....
[Article contains additional citation context not shown here]
Caldwell, R.B., "Performances Metrics for Neural Network-based Trading System Development", NeuroVe$t Journal, Vol. 3, No. 2. 1995, pp22-26.
A Study on Training Criteria for Financial Time Series Forecasting - Yao, Tan (2001) (1 citation) (Correct)
.... statistical techniques for forecasting have reached their limitation in applications with nonlinearities in the data set [5] It is observed that Normalized Mean Square Error (NMSE) and other error functions that are used for financial forecasting models may not make sense in the financial context [1]. Caldwell [1] gives a general review for the performance metrics. Yao et al. 9] use the correctness of trend and a paper profit to judge the performance of neural network forecasting model. Caldwell [1] also proposes a new measure, namely, weighted directional symmetry (WDS) which weights ....
.... for forecasting have reached their limitation in applications with nonlinearities in the data set [5] It is observed that Normalized Mean Square Error (NMSE) and other error functions that are used for financial forecasting models may not make sense in the financial context [1] Caldwell [1] gives a general review for the performance metrics. Yao et al. 9] use the correctness of trend and a paper profit to judge the performance of neural network forecasting model. Caldwell [1] also proposes a new measure, namely, weighted directional symmetry (WDS) which weights errors based on a ....
[Article contains additional citation context not shown here]
Caldwell, R.B., "Performances Metrics for Neural Network-based Trading System Development", NeuroVe$t Journal, Vol. 3, No. 2. 1995, pp22-26.
An Explicit Feature Selection Strategy for Predictive.. - Chenoweth, Obradovic (1 citation) (Correct)
....the S P 500 index for period i. For comparison purposes the simple buy and hold ARR for the monthly test data is 8.76 and for the daily test data is 11.49 . The ARR for an ideal model with perfect prediction (r i = r a i for all 1 i n) is 42 for monthly data and 147 for daily data. Following Caldwell [1995], the directional symmetry metric is defined as DS = 100 n X i=1 d i n (7) where d i = 1 if (p i ) r a i ) 0 0 otherwise (8) The variable p i is defined either as the predicted return for period i (for continuous variable prediction experiments) or as p i = 1 if S P index ....
....s.t. #fr a i : r a i hg = #fr a i : r a i hg. Similarly, the large prediction set (Large) is the subset of the All 2 tuples (p i ; r a i ) where r a i is above the median value, defined more precisely as Large = f(p i ; r a i ) r a i hg. The Sharpe ration is a widely used metric [Caldwell 1995] that attempts to normalize returns according to the risk of the trading strategy. The sharp ration is defined as Sharpe = n X i=1 r a i Gamma n X i=1 r f i noe a (10) where r a i is defined previously, oe a is the standard deviation of the elements in the set fr a i : 1 i ng, and ....
Caldwell, R., [1995] "Performance Metrics for Neural Network-based Trading System Development, " NeuroVe$t Journal, Vol. 3 Num 2, pp. 13-23.
An Analysis of the INFFC Cotton Futures Time Series: Lower.. - Drossu, Obradovic (Correct)
No context found.
Caldwell, R. B. [1995] "Performance Metrics for Neural Network-based Trading System Development," NeuroVe$t Journal, Vol. 3, No. 2, pp. 13-23.
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