https://hdl.handle.net/20.500.12619/1156 Sat, 11 Apr 2026 17:58:52 GMT 2026-04-11T17:58:52Z https://hdl.handle.net/20.500.12619/100675 Using Machine Learning Algorithms to Analyze Customer Churn in the Software as a Service (SaaS) Industry Levent ÇALLI; Sena KASIM Companies must retain their customers and maintain long-term relationships in industries with intense competition. Customer churn analysis is defined in the literature as identifying customers who may leave a company to take appropriate marketing precautions. While customer churn research is prevalent in B2C (Business to Customer) business models such as the telecoms and retail sectors, customer churn analysis in B2B (business to business) models is a relatively emerging topic. In this regard, the study carried out a customer churn analysis by considering an ERP (enterprise resource planning) company with a software as a service (SaaS) business model. Different machine learning algorithms analyzed ten features determined by selection methods and expert opinions. According to the analysis results, the random forest algorithm gave the best result. Additionally, it has been observed that the number of products and customer features has a relatively higher weight for the prediction of churner. Fri, 30 Sep 2022 00:00:00 GMT https://hdl.handle.net/20.500.12619/100675 2022-09-30T00:00:00Z https://hdl.handle.net/20.500.12619/99814 A Linearization–Based Hybrid Approach for 3D Reconstruction of Objects in a Single Image Kotan, Muhammed; Öz, Cemil; Kahraman, Abdulgani The shape-from-shading (SFS) technique uses the pattern of shading in images in order to obtain 3D view information. By virtue of their ease of implementation, linearization-based SFS algorithms are frequently used in the literature. In this study, Fourier coefficients of central differences obtained from grey-level images are employed, and two basic linearization-based algorithms are combined. By using the functionally generated surfaces and 3D reconstruction datasets, the hybrid algorithm is compared with linearization-based approaches. Five different evaluation metrics are applied to recovered depth maps and the corresponding grey-level images. The results on defective sample surfaces are also included to show the effect of the algorithm on surface reconstruction. The proposed method can prevent erroneous estimates of object boundaries and produce satisfactory 3D reconstruction results in a low number of iterations. Mon, 27 Sep 2021 00:00:00 GMT https://hdl.handle.net/20.500.12619/99814 2021-09-27T00:00:00Z https://hdl.handle.net/20.500.12619/99813 Dynamic Modeling With Integrated Concept Drift Detection for Predicting Real-Time Energy Consumption of Industrial Machines Kahraman, Abdulgani; Kantardzic, Mehmet; Kotan, Muhammed Industrial machinery is a significant energy consumer, and its CO2 emissions have increased dramatically in recent years. Therefore, energy efficiency is becoming crucial for businesses, governments, as well as the planet. Estimating the power consumption of industrial machines with greater accuracy assists management and optimizes machine operation parameters. Real-time industrial machine datasets present several challenges, such as changes in the data over time, unknown running conditions, missing data, etc. Most research publications focus on the accuracy of traditional static models of forecasting; however, prediction performance deteriorates over time because data evolves. We implemented deep learning as a prediction model for three distinct real-world industrial datasets. The proposed method, dynamic modeling with memory (DMWM), improved overall prediction performance compared with conventional approaches by identifying concept drifts and optimizing the number of required models in response to industrial datasets’ recurring machine energy consumption patterns. Wed, 28 Sep 2022 00:00:00 GMT https://hdl.handle.net/20.500.12619/99813 2022-09-28T00:00:00Z https://hdl.handle.net/20.500.12619/99812 Accurate Analysis of the Spatial Pattern of Reflected Light and Surface Orientations Based on Color Illumination Kotan, Muhammed; Öz, Cemil; Bozkurt, Mehmet Recep 3D recovery approaches require a variety of clues to obtain shape information. The shape from shading (SFS) method uses shading variations in images to estimate depth maps. Although shading contains detailed information, it causes some well-known ambiguities such as convex-concave ambiguity. In this study, a system installation using red, green, and blue illumination and an algorithm processing reflections on the surface were proposed to accurately analyze surface orientations and solve ambiguity problems. The algorithm evaluated combinations of light hitting the surface from different directions and detailed surface orientations to avoid erroneous predictions. The proposed system was tested with eight different methods in the literature developed from the earliest times to the present, and the initially erroneously predicted surface orientations were improved. Consequently, the correct orientation of the surface points was determined by removing the ambiguities in images taken without considering the location of illumination, and all the tested methods provided successful results using the proposed system. Wed, 09 Nov 2022 00:00:00 GMT https://hdl.handle.net/20.500.12619/99812 2022-11-09T00:00:00Z