Feed-forward Neural Nets as Models for Time Series Forecasting

  title={Feed-forward Neural Nets as Models for Time Series Forecasting},
  author={Zaiyong Tang and Paul A. Fishwick},
We have studied neural networks as models for time series forecasting, and our research compares the Box-Jenkins method against the neural network method for long and short term memory series. Our work was inspired by previously published works that yielded inconsistent results about comparative performance. We have since experimented with 16 time series of di ering complexity using neural networks. The performance of the neural networks is compared with that of the Box-Jenkins method. Our… CONTINUE READING

From This Paper

Topics from this paper.


Publications citing this paper.
Showing 1-10 of 46 extracted citations


Publications referenced by this paper.
Showing 1-10 of 30 references

Neural networks as forecasting experts: An empirical test

  • R. Sharda, R. Patil
  • In
  • 1990
Highly Influential
10 Excerpts

TIMESLAB: A Time Series Analysis Laboratory

  • H. Newton
  • Wadsworth & Brooks Cole,
  • 1988
Highly Influential
6 Excerpts

A Practical Guide to BOX-JENKINS Forecasting

  • C. J. Ho
  • Lifetime Learning Publica-
  • 1983
Highly Influential
4 Excerpts

On the recognition capabilities of feedforward nets

  • E. Sontag
  • Technical Report Report
  • 1990
Highly Influential
3 Excerpts

Modeling the judgement of bond rating agencies

  • J. C. Singleton, A. J. Surkan
  • 1990
3 Excerpts

Similar Papers

Loading similar papers…