Endüstri Mühendisliği Bölümü Koleksiyonu

Permanent URI for this collectionhttps://hdl.handle.net/20.500.11779/1942

Browse

Browsing Endüstri Mühendisliği Bölümü Koleksiyonu by Institution Author "Özlem, Şirin"

Filter results by typing the first few letters
Now showing 1 - 2 of 2
  • Thumbnail Image
    Article
    Citation - WoS: 5
    Citation - Scopus: 10
    Predicting Cash Holdings Using Supervised Machine Learning Algorithms
    (Springer, 2022) Özlem, Şirin; Tan, Ömer Faruk
    This study predicts the cash holdings policy of Turkish firms, given the 20 selected features with machine learning algorithm methods. 211 listed firms in the Borsa Istanbul are analyzed over the period between 2006 and 2019. Multiple linear regression (MLR), k-nearest neighbors (KNN), support vector regression (SVR), decision trees (DT), extreme gradient boosting algorithm (XGBoost) and multi-layer neural networks (MLNN) are used for prediction. Results reveal that MLR, KNN, and SVR provide high root mean square error (RMSE) and low R2 values. Meanwhile, more complex algorithms, such as DT and especially XGBoost, derive higher accuracy with a 0.73 R2 value. Therefore, using advanced machine learning algorithms, we may predict cash holdings considerably.
  • Thumbnail Image
    Book Part
    Citation - WoS: 13
    Quantifying the Grounding Probability in Narrow Waterways
    (CRC Press, 2020) Özlem, Ş.; Altan, Y.C.; Otay, E.N.; Or, I.
    The aim of this paper is to estimate the grounding probability of vessels while navigating in narrowwaterways. In this study, the grounding probability is modelled as a combination the geometric probability, defined as vessel being on a grounding course and the causation probability, defined as the probability that the vessel is unable to avoid a grounding while being on a grounding course. A mathematical model is developed to estimate the geometric probability where the causation probability is estimated through a specially designed Bayesian network. The Strait of Istanbul, one of the narrowest waterways in the world, is used as a test case. The resulting grounding and ramming accidents are 2.8 times the ship collisions. The most critical causes of grounding accidents are the machine failure, steering inadequacy and lack of pilot support, respectively. With different input parameters, the proposed approach may be applied to other narrow waterways. © 2020 Taylor and Francis Group, London.