Forecasting the behavior of multivariate time series using neural networks

Kanad Chakraborty, Kishan Mehrotra, Chilukuri K. Mohan, Sanjay Ranka

Research output: Contribution to journalArticlepeer-review

362 Scopus citations


This paper presents a neural network approach to multivariate time-series analysis. Real world observations of flour prices in three cities have been used as a benchmark in our experiments. Feedforward connectionist networks have been designed to model flour prices over the period from August 1972 to November 1980 for the cities of Buffalo, Minneapolis, and Kansas City. Remarkable success has been achieved in training the networks to learn the price curve for each of these cities and in making accurate price predictions. Our results show that the neural network approach is a leading contender with the statistical modeling approaches.

Original languageEnglish (US)
Pages (from-to)961-970
Number of pages10
JournalNeural Networks
Issue number6
StatePublished - 1992


  • Back propagation
  • Combined modeling
  • Forecasting
  • Multi-lag prediction
  • Multivariate time-series
  • Neural networks
  • One-lag prediction
  • Statistical models
  • Training

ASJC Scopus subject areas

  • Cognitive Neuroscience
  • Artificial Intelligence


Dive into the research topics of 'Forecasting the behavior of multivariate time series using neural networks'. Together they form a unique fingerprint.

Cite this