A New Dual Normalization for Enhancing the Bitcoin Pricing Capability of an Optimized Low Complexity Neural Net with TOPSIS Evaluation

Bitcoin, the largest cryptocurrency, is extremely volatile and hence needs a better model for its pricing. In literature, many researchers have studied effect of data normalization on regression analysis stock price prediction. How has affected Bitcoin prediction? To answer this question, study analyzed prediction accuracy Legendre polynomial-based neural network optimized by mutated climb monkey algorithm using nine existing techniques. A new dual technique was proposed to improve efficiency model. The 10 techniques were evaluated 15 error metrics multi-criteria decision-making (MCDM) approach called order performance similarity ideal solution (TOPSIS). top three along with min–max further Chebyshev, Laguerre, trigonometric networks in different datasets. 16 models (each four techniques) calculated metrics. × TOPSIS conducted rank models. convergence plot ranking indicated that plays significant role capability predictor. This paper can significantly contribute research utilization varied fields research. It also international finance as tool investors well stakeholders