@article{article_559016, title={PREDICTION OF TRANSITION PROBABILITIES FROM UNEMPLOYMENT TO EMPLOYMENT FOR TURKEY VIA MACHINE LEARNING AND ECONOMETRICS: A COMPARATIVE STUDY}, journal={Journal of Research in Economics}, volume={3}, pages={58–75}, year={2019}, author={Kütük, Yasin and Güloğlu, Bülent}, keywords={Employment,Transition Probability,Machine Learning,Classification}, abstract={<p>In this study, it is mainly aimed to predict transition probabilities of individuals who are previously </p> <p>unemployed and get employment or stay unemployed. In order to do that, Household Labor Force </p> <p>Surveys conducted in Turkey are merged and matched from 2004 to 2016. Information about </p> <p>individuals only consists of individual characteristics and qualifications since there should not be any </p> <p>informative clue about the present situation. To predict those probabilities, logistic regression analysis </p> <p>as econometric approach, a shallow neural network and machine learning classification algorithms are </p> <p>run in order to compare them. The results indicate that classification in machine learning is slightly </p> <p>better than logistic regression and shallow neural network. While XGBoost classifier and Random </p> <p>Forest get 67% accuracy, logistic regression can predict only 63% of an individual’s transition and </p> <p>shallow neural network forecasts 51%. </p>}, number={1}, publisher={Marmara University}