Stock Market Prediction using Bayesian Optimized K-Nearest Neighbor

Journal

International Journal of Digital Applications and Contemporary Research (IJDACR)

ISSN

2319-4863

Volume / Issue

Vol.8 · Issue 11

Published

June 2020

Access

Open Access

Licence

CC BY-NC-SA 4.0

Zahra Malwi Paril Ghori

Stock markets are complex systems due to their non-stationary nature, as the parameters are constantly changing, such as economic conditions and changes in company policy. This paper proposes a model based on Bayesian optimized K-Nearest Neighbor (KNN) for the price prediction of New York stock Exchange. Different configurations of KNN are tested using a six years series (January 2010 to December 2016). Three attributes of dataset; open, high and low values are used for the input of the KNN. The results show a good behaviour of Bayesian optimized KNN with low-performance errors in both learning and prediction.

Bayesian Optimization KNN ORCL

Zahra Malwi, Paril Ghori (2020). Stock Market Prediction using Bayesian Optimized K-Nearest Neighbor. International Journal of Digital Applications and Contemporary Research (IJDACR), Vol.8, Issue 11. ISSN: 2319-4863.

Copy Citation

Full references are available in the PDF version of this paper.

Download Full Paper (PDF) →

Downloads

Full Text Access

Full Paper

PDF Download

Abstract PDF

PDF Download

Article Info

LinkedIn Twitter / X WhatsApp