The stock price varies depending on time, so stock market data is time-series data. The prediction of the trend of a stock price is a more interesting topic for investors to take an investment decision in a specific stock. Prediction of stock price always depends on machine learning algorithms. In this work, optimizing deep neural network (DNN) is used for predicting if the close price is reached to the profit which is determined by the investor or not and improve the prediction accuracy. Particle swarm optimization (PSO) and auto machine learning (AutoML) are used as optimizers with DNNs. The methods are applied to data of nine companies in Indonesia and National Stock Exchange (NSE) of India. The data is got from yahoo finance. Based on the experimental results, AutoML of deep learning proved to have the best accuracy rate, which is varying from 81 percent to 92 percent across all companies, and the accuracy after optimizing DNNs using PSO is varying from 73 percent to 82 percent across all companies.

No abstract

No abstract

This paper proposes venus flytrap optimization (VFO) with constriction factor (VFO-CF) for improving the convergence of the algorithm. The constriction factor has a significant impact on the performance of VFO-CF; its impact was inspected based on benchmark functions. Herein, the property of the constriction factor and the guidelines for determining the optimal parameter values are defined. The proposed method is tested on benchmark functions, and the obtained results are compared with existing VFO results. The water supply rate is tested in the range [4.1, 4.2], which is generally reasonable for the benchmark functions.