Intelligent Financial Forecasting With an Improved Chemical Reaction Optimization Algorithm Based Dendritic Neuron Model

Abstract

Chemical reaction optimization (CRO) algorithm is a robust metaheuristic by simulating the process of natural chemical reaction and has been applied for solving numerous realistic problems. However, it is suffering from low population diversity, slow convergence, and deprived from local search ability. To boost the search operation of CRO, this article proposes an improved CRO method termed as ICRO. We achieve the improvements in two phases. First, to start the search operation with a better-quality population, we propose a new method to initialize population which helps in enhancing diversification of the search space. Second, to intensify the local search ability we integrate Nelder-Mead simplex method with CRO. The ICRO is then evaluated on a few benchmark functions for optimization and found apposite. Dendritic neuron model (DNM) using additive and multiplicative-based aggregation functions has been emerging as a machine learning approach and found successful in many engineering applications. This study attempts to advance the predictive accuracy of DNM through maintaining a decent steadiness between exploitation and exploration of its search space with the proposed ICRO, termed as ICRO-DNM. The powerful global search ability of ICRO synergies with better approximation capability of DNM thus, able to overcome the limitations of conventional back propagation learning based DNM. ICRO-DNM is evaluated on closing price prediction for four stock index and net asset values of four mutual fund datasets and found efficient. The consequences of this attempt are: (1) Proposed ICRO shows robust parameter optimization ability for benchmark functions and DNM compared to basic CRO, particle swarm optimization (PSO), and genetic algorithm (GA); (2) The learning paradigm formed due to reasonable amalgamation of ICRO and DNM is pretty able to capture the underlying uncertainties coupled with financial data, produces more precise and steady predictions and significantly different from other forecasts.

Modeling And Enhancing Crude Oil Price Forecasting Using Enhanced Set Algebra-Based Heuristic Algorithm-Based Extreme Learning Machine

“…To evaluate the optimization capabilities of our newly developed hybrid learning algorithm, ESAHA, we conducted experiments on six well-established benchmark test functions. These functions include Ackley's function ( (Nayak et al, 2022), Sphere's function(…”

“…In order to carry out the experiment, we utilized a search range of [-100, 100] as specified by Nayak et al in 2022. The study comprises 51 runs for each of the six target functions, with a maximum number of iterations (Max_iter) set at 100,000. The population sizes for ESAHA and SAHA, as well as the PSO swarm and GA, are all standardized at 150 individuals.…”

“…We have applied sigmoid normalization to all the inputs as described in Nayak et al (2022). Following the prediction process, a de-normalization method is employed to restore the data to their original real-time values.…”

“…5/12 was chosen as the butterfly adjusting ratio (BAR) . The PSO and GA parameters were set in the same way as selected by Nayak et al (2022). The GD algorithm's Max_iterations, learning rate, and momentum factor were all set by a trial-and-error process.…”

“…17 to Eq. 22 (Nayak et al, 2022).In addition to ESAHA, our study encompassed an exploration and comparative analysis of four other competitive optimization algorithms, namely SAHA, MBO, PSO, and GA.…”