Open AccessStock price prediction using machine learning on least-squares linear regression basis
Author(s) -
C. C. Emioma,
S.O. Edeki
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1734/1/012058
Subject(s) - stock (firearms) , stock price , econometrics , randomness , computer science , linear regression , closing (real estate) , regression analysis , variables , regression , machine learning , artificial intelligence , economics , statistics , mathematics , series (stratigraphy) , finance , engineering , mechanical engineering , paleontology , biology
Predicting the future of a stock price is a difficult task due to the high level of randomness in the movement of prices. This research aims to use a machine-learning algorithm to estimate the closing stock price of a dataset to help aid in the prediction of stock prices leading to higher accuracy in prediction. The intention of the model is for it to be used as a day trading guide. The algorithm being used is called the least-squares linear regression model. It takes in a dependent variable, in this case, would be our closing price of the stock and an independent variable, which is the day each stock price was recorded.