@article{article_329913, title={Classification Of BIST -100 Index’ Changes Via Machine Learning Methods}, journal={Marmara Üniversitesi İktisadi ve İdari Bilimler Dergisi}, volume={39}, pages={117–129}, year={2017}, DOI={10.14780/muiibd.329913}, author={Filiz, Enes and Öz, Ersoy}, keywords={BIST-100 Index,Machine Learning Methods,Classification}, abstract={<p>The changes in BIST-100 index are economically crucial. In this study, classifications will be made with </p> <p>the assumption that the changes in BIST-100 index are dependent on certain factors. The classifiers to be </p> <p>used are k-nearest neighbor algorithm, naive Bayes Classifier, logistic regression and C4.5 classifier from </p> <p>the machine learning methods. Factors affecting the change of BIST-100 index values are deemed as Euro/ </p> <p>Dollar Parity, Gold value (ounce), Crude Oil Prices, Monthly Interest Rates, Inflation Data and DAX, </p> <p>FTSE, S&P 500 that are widely used in the literature. As a result of the transactions performed via Weka </p> <p>program, the most successful methods in order are C4.5 classifier algorithm (66.2%) and logistic regression </p> <p>analysis (65.9%). </p>}, number={1}, publisher={Marmara Üniversitesi}