Forecasting of naphtha demand and supply using time serial data causal analysis

Byeonggil Lyu, Hweeung Kwon, Jinsuk Lee, Haesub Yoon, Jaehyung Jin, Il Moon

Research output: Chapter in Book/Report/Conference proceedingChapter

3 Citations (Scopus)

Abstract

Naphtha is an important resource used to produce petrochemical products. Historically, petrochemical companies have been keen to the variations of naphtha prices as it has had great effects on their profits. Naphtha price is closely aligned with crude oil price. In particular, more directly, supply and demand of naphtha affect its price fluctuations. This research is focused to propose an approach for forecasting supply and demand of naphtha, with an emphasis on key affecting factors such as the margin of petrochemical companies and the use of alternative raw material. The demand of naphtha is estimated on the basis of the margin and operation rate of a petrochemical plant, while its supply is affected by operation rate of refinery. Modeling of forecasting naphtha supply/demand, based on time series method, is developed along with absolute errors derived from a statistical analysis; the model at present time is used to forecast future supply/demand over historical time series data from March 2010 to September 2012. Key set of affecting factors are identified by combined heuristic and statistical analysis and a set of equations correlating between those factors are set up. The proposed model was validated by actual data for the underlying period, which should be useful to forecast the price of naphtha.

Original languageEnglish
Title of host publicationComputer Aided Chemical Engineering
PublisherElsevier B.V.
Pages829-834
Number of pages6
DOIs
Publication statusPublished - 2014

Publication series

NameComputer Aided Chemical Engineering
Volume33
ISSN (Print)1570-7946

All Science Journal Classification (ASJC) codes

  • Chemical Engineering(all)
  • Computer Science Applications

Fingerprint Dive into the research topics of 'Forecasting of naphtha demand and supply using time serial data causal analysis'. Together they form a unique fingerprint.

  • Cite this

    Lyu, B., Kwon, H., Lee, J., Yoon, H., Jin, J., & Moon, I. (2014). Forecasting of naphtha demand and supply using time serial data causal analysis. In Computer Aided Chemical Engineering (pp. 829-834). (Computer Aided Chemical Engineering; Vol. 33). Elsevier B.V.. https://doi.org/10.1016/B978-0-444-63456-6.50139-3