Open AccessMeasuring Accuracy of Stock Price Prediction Using Machine Learning Based Classifiers
Author(s) -
Ranjeet Kaur,
Yogesh Kumar Sharma,
Devershi Pallavi Bhatt
Publication year - 2021
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/1099/1/012049
Subject(s) - computer science , machine learning , artificial intelligence , speculation , stock price , stock (firearms) , data mining , finance , engineering , mechanical engineering , paleontology , series (stratigraphy) , economics , biology
Stock market prediction means to decide the future development of the stock estimation of a budgetary trade. The exact forecast of offer value development will prompt more benefit speculators can make. The investigation dependent on the past gathered enormous information with the utilization of the AI strategies is appropriate for different fields. The basic aim is to generate the analysis for driving good information which will be useful for the purpose of decision making. The quality of the decisions will definitely be enhanced. There are various machine learning techniques lies with different accuracies. The selection of the best technique such that the highest level of accuracy can be achieved. In the current research there are three techniques with different variant are tested for showing the relative accuracy of the specific technique. The all these techniques are based on supervised learning will requires training for the better accuracy. In current research paper all the techniques with different variants are trained with the different sizes of the training sets. These training sizes are 70:30,50:50 and 30:70. The best variant is the 70:30 for the KNN. The given variant shows the highest accuracy in terms of the prediction.