Micrtsoft_Stock_Price: An Efficient Framework For Microsoft Stock Price Prediction Using Computational Intelligence

Econometrics uses statistical methods to analyze relationships using data. While its name suggests a focus on economics, it's widely used in various social sciences and beyond.One of the challenges in predicting stock prices is data availability since obtaining data can often be quite challenging.Predicting stock prices is difficult because it involves analyzing data with various methods, but it's not always accurate due to many factors involved. These methods help understand trends but aren't foolproof for making investment decisions.In this paper, we have proposed an efficient framework for the prediction of Microsoft stock price using nine different machine learning algorithms (AdaBoost, kNN, Linear Regression, Gradient Boosting, Tree, Neural Network, SVM, Constant, Random Forest) on six different datasets.The best algorithm in the four datasets was adaboost, with the smallest percentage of errors, 0.004, and the best algorithm in the two datasets was linear regression.The best result algorithm in all datasets is AdaBoost.