Orchestrating Real-Valued Negative Selection Algorithm with Computational Efficiency for Crude Oil Price

This paper implements the real-valued negative selection with variable-sized detectors (V-Detectors) for projecting the right decision with respect to crude oil price. The Brent crude oil data is retrieved from US department of energy. Using varying radius values of the V-Detector, comparison in terms of detection rate and false alarm rate, with support vector machine, naïve bayes, multi-layer perceptron, J48, non-nested generalized exemplars, IBk, fuzzy-roughNN, and vaguely quantified nearest neighbor demonstrated that V-Detector is efficient and computationally effective. The experimental outcome can initiate international crude oil market policy making as the V-Detector is able to reach highest detection and lowest false alarm rates.