ARTICLE
TITLE

Implementation of Neural Network Algorithms with Hyperparameter Optimization for Stock Price Prediction

SUMMARY

Stocks are one of the investment instruments that are currently in demand because they have a greater return value than saving in a bank. It's just that investing in stocks has the risk of decreasing the value of the stock price, which can make investors lose money. Mining stocks are currently the prima donna of investors, because their value continues to rise. However, buying shares at the right time is still an obstacle, therefore a stock price prediction is needed that can help investors determine the right time to buy mining shares. The use of machine learning can be done to predict stock prices. The data used in this research is PTBA stock price data from 2017 – 2022. In this study, the Neural Network algorithm is used with hyperparameter optimization. In this study, the RMSE value was 30.634. A small RMSE value indicates that the Neural Network algorithm can be used to predict PTBA's stock price.

 Articles related

Mohammad Nur Shodiq,Dedy Hidayat Kusuma,Mirza Ghulam Rifqi,Ali Ridho Barakbah,Tri Harsono    

Earthquake is a type of natural disaster. The Indonesian archipelago located in the world's three mega plates; they are Australian plate, Eurasian plate, and Pacific plate. Therefore, it is possible for applied of earthquake risk of mitigation. One of th... see more


Smruti Chourasia,Hrishikesh Bharadwaj Chakrapani,Queenie Das,Krati Agarwal,Lavanya K    

The communication boom in the past few decades has resulted in a large flow of data. This entails the need for having high security and privacy with regards to data confidentiality and authenticity. One method of doing so is by utilizing a synchronized k... see more


Cristian Grava,Alexandru Gacsádi,Ioan Buciu    

In this paper we present an original implementation of a homogeneous algorithm for motion estimation and compensation in image sequences, by using Cellular Neural Networks (CNN). The CNN has been proven their efficiency in real-time image processing, bec... see more


Nesrine Elfelly,Jeans-Yves Dieulot,Pierre Borne    

The multimodel approach was recently developed to deal with the issues of complex processes modeling and control. Despite its success in different fields, it still faced with some design problems, and in particular the determination of the models and of ... see more


Yin Feng,Wang Yao-nan,Yang Yi-min    

Neural networks with their inherent learning ability have been widely applied to solve the robot manipulator inverse kinematics problems. However, there are still two open problems: (1) without knowing inverse kinematic expressions, these solutions have ... see more