Implementation of Linear Regression Algorithm to Predict Stock Prices Based on Historical Data

Stock investment is in great demand by investors because it can provide large profits with risks or losses, accordance the principle of low risk return, high return. prices that fluctuate a very short time make difficult for to predict stock future, so must pay more attention and gather as much information possible regarding shares be bought sold. This study aims create data mining model using Linear Regression algorithm daily closing supports transactions. The used historical on 10 companies last 8 years period 25 February 2013 – 2021. Historical price will prepared Noving Average method linear regression generate prediction models. resulting well enough assist making decisions obtain risk.