Oil Price Trackers Inspired by Immune Memory
WIlliam Wilson, Phil Birkin, Uwe Aickelin
Proceedings of the Workshop on Artificial Immune Systems and Immune System Modelling (AISB06) | Society for the Study of Artificial Intelligence and the Simulation of Behaviour | Published : 2006
We outline initial concepts for an immune inspired algorithm to evaluate and predict oil price time series data. The proposed solution evolves a short term pool of trackers dynamically, with each member attempting to map trends and anticipate future price movements. Successful trackers feed into a long term memory pool that can generalise across repeating trend patterns. The resulting sequence of trackers, ordered in time, can be used as a forecasting tool. Examination of the pool of evolving trackers also provides valuable insight into the properties of the crude oil market.