Browsing by Author "Pak, Burcu Kuleli"

Now showing 1 - 4 of 4

Deep Learning Based Employee Attrition Prediction
(SPRINGER LINK, 2023) Gurler, Kerem; Pak, Burcu Kuleli; Gungor, Vehbi Cagri; 0000-0003-0803-8372; AGÜ, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü; Gungor, Vehbi Cagri
Employee attrition is a critical issue for the business sectors as leaving employees cause various types of difficulties for the company. Some studies exist on examining the reasons for this phenomenon and predicting it with Machine Learning algorithms. In this paper, the causes for employee attrition is explored in three datasets, one of them being our own novel dataset and others obtained from Kaggle. Employee attrition was predicted with multiple Machine Learning and Deep Learning algorithms with feature selection and hyperparameter optimization and their performances are evaluated with multiple metrics. Deep Learning methods showed superior performances in all of the datasets we explored. SMOTE Tomek Links were utilized to oversample minority classes and effectively tackle the problem of class imbalance. Best performing methods were Deep Random Forest on HR Dataset from Kaggle and Neural Network for IBM and Adesso datasets with F1 scores of 0.972, 0.642 and 0.853, respectively.
Generating Emergency Evacuation Route Directions Based on Crowd Simulations with Reinforcement Learning
(Institute of Electrical and Electronics Engineers Inc., 2022) Unal, Ahmet Emin; Gezer, Cengiz; Pak, Burcu Kuleli; Gungor, Vehbi Cagri; 0000-0003-0803-8372; AGÜ, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü; Gungor, Vehbi Cagri
In an emergency, it is vital to evacuate individuals from the dangerous environments. Emergency evacuation planning ensures that the evacuation is safe and optimal in terms of evacuation time for all of the people in evacuation. To this end, the computer-enabled evacuation simulation systems are used to generate optimal routes for the evacuees. In this paper, a dynamic emergency evacuation route generator has been proposed based on indoor plans of the building and the locations of the evacuees. To generate the optimal routes in real-time, a reinforcement learning algorithm (proximal policy optimization) is presented. Comparative performance results show that the proposed model is successful for evacuating the individuals from the building in different scenarios.
Linear vs. Non-Linear Embedding Methods in Recommendation Systems
(Institute of Electrical and Electronics Engineers Inc., 2022) Gurler, Kerem; Coskun, Mustafa; Karagenc, Safak; Orun, Gokhan; Pak, Burcu Kuleli; Gungor, Vehbi Cagri; 0000-0003-0803-8372; AGÜ, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü; Coskun, Mustafa; Pak, Burcu Kuleli; Gungor, Vehbi Cagri
Predicting customer interest in items is very crucial in direct marketing as it can potentially boost sales. Data mining techniques are developed to predict which items a particular user might be interested in based on their purchase history or explicit feedback in form of ratings or comments. Recently, non-linear and linear methods have been developed for this purpose. In this study, we applied Neighborhood based Collaborative Filtering (CF), Matrix Factorization (MF), Singular Value Decomposition (SVD), Neural Graph CF (NGCF) and Light Graph Convolutional Network (LightGCN) on explicit user product rating data which is acquired from the online gaming and mobile entertainment platform called HADI. We compared the results of node embedding methods in terms of Precision@k, Recall@k and NDCG@k values. SVD and LightGCN showed the best test performance and SVD was significantly superior to LightGCN in terms of training speed. To further increase predictive performance of SVD, we have applied classification with Logistic Regression and Deep Random Forest on user and item embeddings created by the SVD.
Man-hour Prediction for Complex Industrial Products
(Institute of Electrical and Electronics Engineers Inc., 2023) Unal, Ahmet Emin; Boyar, Halit; Pak, Burcu Kuleli; Cem Yildiz, Mehmet; Erten, Ali Erman; Gungor, Vehbi Cagri; 0000-0003-0803-8372; AGÜ, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü; Gungor, Vehbi Cagri
Accurately predicting the cost is crucial for the success of complex industrial projects. There can be several sources contributing to the cost. Traditional methods for cost estimation may not provide the required accuracy and speed to ensure the success of the project. Recently, machine learning techniques have shown promising results in improving cost estimation in various industrial products. This study investigates the performance of gradient-boosting machine learning models and feature engineering techniques on a private dataset of metal sheet project man-hour costs. A comparison of distinct models is conducted, key aspects influencing cost are identified, and the implications of incorporating domainspecific knowledge, including its advantages and disadvantages, are assessed based on performance outcomes. Experimental results demonstrate that LightGBM and XGBoost outperform other models, and feature selection and synthetic data generation techniques improve the performance. Overall, this study highlights the potential of machine learning in metal sheet sampling projects and emphasizes the importance of feature engineering and domain expertise for better model performance.