Application of Data Mining to Predict Stock Price Movements in MNC Bank Using K-Nears Neighbor

Lyvia Permata Sari

Information Technology, Faculty of Engineering and Informatics, Bina Sarana Informatika University, Jakarta

Abstract

This study applies data mining methods to predict stock price movements in MNC Bank companies using the K-Nearest Neighbor (K-NN) algorithm. Accurate prediction of stock prices is crucial for investment decisions and risk management in the financial sector. The K-NN algorithm was selected due to its effectiveness in classifying data based on proximity to training data.The study begins with collecting and cleaning historical stock price data from PT MNC Bank, removing irrelevant or incomplete entries. Significant features are then extracted from this dataset. The data is split into training and test sets. The K-NN model is trained using the training set to predict stock prices on the test set. Model accuracy is assessed by comparing predictions with actual stock prices, with success measured by the percentage of correct predictions.Results indicate that the K-NN model achieved an accuracy of 83.84% on the PT MNC Bank dataset, demonstrating strong predictive capabilities. However, it is noted that accuracy can be influenced by factors such as the volume of training data, the selected features, and K-NN parameter settings. These findings can serve as a valuable reference for investors and market participants, aiding in more informed investment decisions based on improved stock price predictions.

Keywords: Data mining; K-Nearest Neighbor (K-NN); Prediction algorithms; Stock price movements

How to cite:Sari, L. P., (2024). Application of Data Mining to Predict Stock Price Movements in MNC Bank Using K-Nears Neighbor,Information Technology and Systems (ITS) 1(2), 55-63

Link : https://sanscientific.com/journal/index.php/its/article/view/129