Browsing by Author "Sariyer, Gorkem"

Now showing 1 - 20 of 30

Citation - WoS: 10
Citation - Scopus: 16
A hybrid Bayesian approach for assessment of industry 4.0 technologies towards achieving decarbonization in manufacturing industry
(Elsevier Ltd, 2024) Devesh Kumar; Gunjan Soni; Fauzia Jabeen; Neeraj Kumar Tiwari; Gorkem Sariyer; Bharti Ramtiyal; Ramtiyal, Bharti; Jabeen, Fauzia; Soni, Gunjan; Kumar Tiwari, Neeraj; Sariyer, Gorkem; Kumar, Devesh; Tiwari, Neeraj Kumar
Since the 1st Industrial Revolution the Earth's atmosphere has warmed due to human activities like deforestation burning fossil fuels for energy generation and livestock raising. Without preventative measures the Earth's atmosphere would warm by 2 °C before the next Industrial Revolution. Thus it has become crucial to move toward a low-carbon economy. Reaching carbon neutrality means cutting our carbon footprint to zero. Innovative research methods and technologies can play a significant role in supporting the economy in its carbon reduction efforts. Industry 4.0 (I4.0) technologies hold great potential for decarbonizing the economy. However there is a need to explore and utilize this potential effectively. This study aims to address this by developing a methodology that identifies relevant attributes and critical measures from existing literature mapping them with I4.0 technologies. Using a MCDM approach each measure is prioritized based on importance. To better understand the interrelationships between these attributes and I4.0 technologies the Bayesian Network (BN) method is employed. This approach enables the exploration of dependencies and influences among variables. By implementing this four-stage strategy economies can make informed decisions and prioritize actions contributing to carbon neutrality while leveraging the benefits of I4.0 technologies. This approach offers a comprehensive framework for guiding economies on their path towards carbon neutrality considering the potential of I4.0 technologies and the importance of various attributes identified through literature. © 2024 Elsevier B.V. All rights reserved.
Citation - WoS: 20
Citation - Scopus: 26
An analysis of Emergency Medical Services demand: Time of day- day of the week- and location in the city
(ELSEVIER, 2017) Gorkem Sariyer; Mustafa Gokalp Ataman; Serhat Akay; Turhan Sofuoglu; Zeynep Sofuoglu; Ataman, Mustafa Gokalp; Sariyer, Gorkem; Sofuoglu, Turhan; Akay, Serhat; Sofuoglu, Zeynep
Objective: Effective planning of Emergency Medical Services (EMS) which is highly dependent on the analysis of past data trends is important in reducing response time. Thus we aimed to analyze demand for these services based on time and location trends to inform planning for an effective EMS. Materials and methods: Data for this retrospective study were obtained from the Izmir EMS 112 system. All calls reaching these services during first six months of 2013 were descriptively analyzed based on time and location trends as a heat-map form. Results: The analyses showed that demand for EMS varied within different time periods of day and according to day of the week. For the night period demand was higher at the weekend compared to weekdays whereas for daytime hours demand was higher during the week. For weekdays a statistically significant relation was observed between the call distribution of morning and evening periods. It was also observed that the percentage of demand changed according to location. Among 30 locations the five most frequent destinations for ambulances which are also correlated with high population densities accounted for 55.66% of the total. Conclusion: The results of this study shed valuable light on the areas of call center planning and optimal ambulance locations of Izmir which can also be served as an archetype for other cities. Copyright (C) 2016 The Emergency Medicine Association of Turkey. Production and hosting by Elsevier B.V. on behalf of the Owner. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
Citation - WoS: 15
Citation - Scopus: 18
Analyzing main and interaction effects of length of stay determinants in emergency departments
(Kerman University of Medical Sciences j_mahdavi@kmu.ac.ir, 2020) Gorkem Sariyer; Mustafa Gökalp Ataman; İlker Kızıloğlu; Ataman, Mustafa Gokalp; Sariyer, Gorkem; Kiziloglu, Ilker
Background: Measuring and understanding main determinants of length of stay (LOS) in emergency departments (EDs) is critical from an operations perspective since LOS is one of the main performance indicators of ED operations. Therefore this study analyzes both the main and interaction effects of four widely-used independent determinants of ED-LOS. Methods: The analysis was conducted using secondary data from an ED of a large urban hospital in Izmir Turkey. Between-subject factorial analysis of variance (ANOVA) was used to test the main and interaction effects of the corresponding factors. P values <.05 were considered statistically significant. Results: While the main effect of gender was insignificant age mode of arrival and clinical acuity had significant effects whereby ED-LOS was significantly higher for the elderly those arriving by ambulance and clinically-categorized high-acuity patients. Additionally there was an interaction between the age and clinical acuity in that while ED-LOS increased with age for high acuity patients the opposite trend occurred for low acuity patients. When ED-LOS was modeled using gender age and mode of arrival there was a significant interaction between age and mode of arrival. However this interaction was not significant when the model included age mode of arrival and clinical acuity. Conclusion: Significant interactions exist between commonly used ED-LOS determinants. Therefore interaction effects should be considered in analyzing and modelling ED-LOS. © 2020 Elsevier B.V. All rights reserved.
Citation - WoS: 12
Citation - Scopus: 16
Big data analytics and COVID-19: investigating the relationship between government policies and cases in Poland- Turkey and South Korea
(OXFORD UNIV PRESS, 2022) Mert Erkan Sozen; Gorkem Sariyer; Mustafa Gokalp Ataman; Ataman, Mustafa Gökalp; Sarlyer, Görkem; Sariyer, Gorkem; Sözen, Mert Erkan
We used big data analytics for exploring the relationship between government response policies human mobility trends and numbers of coronavirus disease 2019 (COVID-19) cases comparatively in Poland Turkey and South Korea. We collected daily mobility data of retail and recreation grocery and pharmacy parks transit stations workplaces and residential areas. For quantifying the actions taken by governments and making a fairness comparison between these countries we used stringency index values measured with the `Oxford COVID-19 government response tracker'. For the Turkey case we also developed a model by implementing the multilayer perceptron algorithm for predicting numbers of cases based on the mobility data. We finally created scenarios based on the descriptive statistics of the mobility data of these countries and generated predictions on the numbers of cases by using the developed model. Based on the descriptive analysis we pointed out that while Poland and Turkey had relatively closer values and distributions on the study variables South Korea had more stable data compared to Poland and Turkey. We mainly showed that while the stringency index of the current day was associated with mobility data of the same day the current day's mobility was associated with the numbers of cases 1 month later. By obtaining 89.3% prediction accuracy we also concluded that the use of mobility data and implementation of big data analytics technique may enable decision-making in managing uncertain environments created by outbreak situations. We finally proposed implications for policymakers for deciding on the targeted levels of mobility to maintain numbers of cases in a manageable range based on the results of created scenarios.
Citation - WoS: 10
Citation - Scopus: 13
Big data analytics and the effects of government restrictions and prohibitions in the COVID-19 pandemic on emergency department sustainable operations
(SPRINGER, 2023) Gorkem Sariyer; Mustafa Gokalp Ataman; Sachin Kumar Mangla; Yigit Kazancoglu; Manoj Dora; Ataman, Mustafa Gokalp; Dora, Manoj; Sariyer, Gorkem; Mangla, Sachin Kumar; Kazancoglu, Yigit
Grounded in dynamic capabilities this study mainly aims to model emergency departments' (EDs) sustainable operations in the current situation caused by the COVID-19 pandemic by using emerging big data analytics (BDA) technologies. Since government may impose some restrictions and prohibitions in coping with emergencies to protect the functioning of EDs it also aims to investigate how such policies affect ED operations. The proposed model is designed by collecting big data from multiple sources and implementing BDA to transform it into action for providing efficient responses to emergencies. The model is validated in modeling the daily number of patients the average daily length of stay (LOS) and daily numbers of laboratory tests and radiologic imaging tests ordered. It is applied in a case study representing a large-scale ED. The data set covers a seven-month period which collectively means the periods before COVID-19 and during COVID-19 and includes data from 238152 patients. Comparing statistics on daily patient volumes average LOS and resource usage both before and during the COVID-19 pandemic we found that patient characteristics and demographics changed in COVID-19. While 18.92% and 27.22% of the patients required laboratory and radiologic imaging tests before-COVID-19 study period these percentages were increased to 31.52% and 39.46% during-COVID-19 study period. By analyzing the effects of policy-based variables in the model we concluded that policies might cause sharp decreases in patient volumes. While the total number of patients arriving before-COVID-19 was 158347 it decreased to 79805 during-COVID-19. On the other hand while the average daily LOS was 117.53 min before-COVID-19 this value was calculated to be 16503 min during-COVID-19 study period. We finally showed that the model had a prediction accuracy of between 80 to 95%. While proposing an efficient model for sustainable operations management in EDs for dynamically changing environments caused by emergencies it empirically investigates the impact of different policies on ED operations.
Citation - WoS: 16
Citation - Scopus: 21
Clustering of firms based on environmental social and governance ratings: Evidence from BIST sustainability index
(Borsa Istanbul Anonim Sirketi, 2022) Gorkem Sariyer; Dilvin Taşkın; Taskin, Dilvin; Sariyer, Gorkem
In this paper companies listed on the Borsa Istanbul (BIST) Sustainability Index are analyzed by performing a cluster analysis based on their environmental social and governance (ESG) scores. The results prove that firms with higher ESG ratings do not necessarily perform well in all ESG aspects. The outcomes of the cluster analysis reveal that firms with higher environmental and social scores are the cluster with the most prominent firms in terms of size but with low profitability. However the group that scored poorly in environmental and social practices but the highest governance pillar was the highest performing in terms of the return on assets. This paper highlights the significance of forming clusters and linking sustainability practices with performance characteristics. © 2023 Elsevier B.V. All rights reserved.
Citation - WoS: 32
Citation - Scopus: 30
Data analytics for quality management in Industry 4.0 from a MSME perspective
(Springer, 2025) Gorkem Sariyer; Sachin Kumar Kumar Mangla; Yigit Kazancoglu; Ceren Ocal Tasar; Sunil Luthra; Sariyer, Gorkem; Tasar, Ceren Ocal; Luthra, Sunil; Mangla, Sachin Kumar; Kazancoglu, Yigit; Ocal Tasar, Ceren
Advances in smart technologies (Industry 4.0) assist managers of Micro Small and Medium Enterprises (MSME) to control quality in manufacturing using sophisticated data-driven techniques. This study presents a 3-stage model that classifies products depending on defects (defects or non-defects) and defect type according to their levels. This article seeks to detect potential errors to ensure superior quality through machine learning and data mining. The proposed model is tested in a medium enterprise—a kitchenware company in Turkey. Using the main features of data set product customer country production line production volume sample quantity and defect code a Multilayer Perceptron algorithm for product quality level classification was developed with 96% accuracy. Once a defect is detected an estimation is made of how many re-works are required. Thus considering the attributes of product production line production volume sample quantity and product quality level a Multilayer Perceptron algorithm for re-work quantity prediction model was developed with 98% performance. From the findings re-work quantity has the highest relation with product quality level where re-work quantities were higher for major defects compared to minor/moderate defects. Finally this work explores the root causes of defects considering production line and product quality level through association rule mining. The top mined rule achieves a confidence level of 80% where assembly and material were identified as main root causes. © 2025 Elsevier B.V. All rights reserved.
Citation - WoS: 7
Citation - Scopus: 7
Data-driven decision making for modelling covid-19 and its implications: A cross-country study
(Elsevier Inc., 2023) Gorkem Sariyer; Sachin Kumar Kumar Mangla; Yigit Kazancoglu; Vranda Jain; Mustafa Gökalp Ataman; Ataman, Mustafa Gokalp; Sariyer, Gorkem; Jain, Vranda; Mangla, Sachin Kumar; Kazancoglu, Yigit
Grounded in big data analytics capabilities this study aims to model the COVID-19 spread globally by considering various factors such as demographic cultural health system economic technological and policy-based. Classified values on each country's case death and recovery numbers (per 1000000 population) were used to represent COVID-19 spread. Data sets also included 29 input variables for the corresponding six factors containing data from 159 countries. The proposed model used a Multilayer Perceptron algorithm. The results show that each of the pre-mentioned factors significantly affects disease spread. Urban population median age life expectancy numbers of medical doctors and nursing personnel current health expenditure as a % of GDP international health regulations capacity score continent literacy rate governmental response stringency index testing policy internet usage % human development index and GDP per capita were identified as significant. Taking early measures and adopting open public testing policies were recommended to policymakers in fighting pandemic diseases since the created scenarios on policy-based factors revealed their importance. © 2023 Elsevier B.V. All rights reserved.
Citation - WoS: 8
Citation - Scopus: 11
Do past ESG scores efficiently predict future ESG performance?
(ELSEVIER, 2025) Dilvin Taskin; Gorkem Sariyer; Ece Acar; Efe Caglar Cagli; Taskin, Dilvin; Sariyer, Gorkem; Acar, Ece; Cagli, Efe Caglar
Given the effects of Environmental Social and Governance (ESG) scores on financial performance and stock returns the prediction of future ESG scores is highly crucial. ESG scores are calculated using an enormous number of variables related to the sustainability practices of firms, thus it is impractical for investors to come up with predictions of ESG performance. This paper aims to fill this gap by using only the past score-based and rating-based ESG performance as the determinant of future ESG performance using four machine learning-based algorithms, decision tree (DT) random-forest (RF) k-nearest neighbor (KNN) and logistic regression (LR). The proposed model is validated in BIST sustainability index companies. The results suggest that past ESG grade-based and numerical scores can be used as a determinant of future ESG performance. The results prove that a simple indicator could serve to predict future ESG scores rather than complex data alternatives. Using data from BIST sustainability index companies in Turkey the findings demonstrate that past ESG grades and scores are reliable predictors of future ESG performance offering a simple yet effective alternative to complex data-driven methods. This study not only contributes to advancing sustainable finance practices but also provides practical tools for emerging markets like Turkey to align corporate strategies with global sustainability standards. The methodological contributions also have broader relevance for international financial markets.
Citation - WoS: 5
Citation - Scopus: 8
Does ambulance utilization differ between urban and rural regions: a study of 112 services in a populated city- Izmir
(SPRINGER HEIDELBERG, 2017) Gorkem Sariyer; M. Gokalp Ataman; Turhan Sofuoglu; Zeynep Sofuoglu; Ataman, M. Gokalp; Sariyer, Gorkem; Sofuoglu, Turhan; Sofuoglu, Zeynep
Objective Emergency Medical Services (EMS) play an important role in health care systems especially when well planned and well managed. The goal of this research was to characterize ambulance utilization rates and investigate associated factors. Such an analysis could make a contribution to operational planning of these services. Materials and methods The data for this study were taken from the Izmir emergency ambulance service known as the 112 service because of its call number. Total emergency demand made during 2013 was analyzed and the data were categorized according to four sub-categories: gender age rural-urban and reason for the call. For each category an analysis was made in terms of the absolute number of calls and a relative measure. Hypothesis testing and correlation analysis were used to investigate the differences between the demand for each category and to compare demand across categories. Results Although demand rates from males and females were very similar a significant difference was observed in the daily utilization of these services by gender. The absolute number of calls from rural regions was less than for urban regions but the rural regions had a higher proportion of calls (i.e. calls per 1000 people). Similarly the absolute number of calls generated by the elderly was less than that generated by the young but the elderly had a higher value in terms of relative measures. A medical condition was the most frequent reason for calls. A significant and positive relation was observed between male-female and elderly-young citizens and there was a significant but negative relation between rural-urban demand. Conclusion This study confirms that gender age and rural-urban distinctions are major factors that affect demand for these services and should therefore to be taken into consideration in operations management. It also highlights the need for a specific focus on rural regions and elderly citizens.
Effective service design in strategic customer setting
(American Scientific Publishers order@aspbs.com, 2015) Gorkem Sariyer; Sariyer, Gorkem
This paper theoretically analyzes interactive decision making in the service sector in order to evaluate and interpret the optimal actions of the actors involved. The actors of this sector are the strategic customers and the service providers. The decisions of these actors are interactive since they affect each other. The service provider decides on the service design service rate and the price whereas the strategic customer decides whether to receive the service or not. The optimal actions for the service provider and the strategic customer are respectively the ones which maximize their profit and utility functions. Both the short term and long term decisions of the service provider are analyzed. While price is the main decision parameter on both service rate is the decision parameter on only the long term. The analyses emphasize the value of wait time in strategic customers' decision-making which will be the service provider's main criteria for the design of the system. © 2017 Elsevier B.V. All rights reserved.
Event Study Design for Modeling Early Relaxation in Turkish Public with COVID-19 Vaccine
(Cambridge University Press, 2023) Merve Keser; Gorkem Sariyer; Serpil Kahraman; Kahraman, Serpil; Sariyer, Gorkem; Keser, Merve
Objective: Vaccination is crucial to fighting the coronavirus disease (COVID-19) pandemic. A large body of literature investigates the effect of the initiation of the COVID-19 vaccination in case numbers in Turkey including the resistance and willingness to taking the vaccine. The effect of early relaxation in the Turkish public with the initiation of vaccination on new daily cases is unknown. Methods: This study performs an event study analysis to explore the pre-relaxation effect of vaccination on the Turkish public by using daily data of new cases stringency index and residential mobility. Two events are comparatively defined as the vaccination of the health personnel (Event 1) and the citizens age 65 and over (Event 2). The initial dates of these events are January 13 and February 12 2021 respectively. The length of the estimation window is determined as 14 days for the 2 events. To represent only the early stages of the vaccination the study period ends on April 12 2021. Thus whereas the event window of Event 1 includes 90 observations Event 2 covers 60 observations. Results: While average values of residential mobility stringency index and daily numbers of cases are 15.36 71.03 and 11 978.93 in the estimation window for Event 1 these averages are 8.89 70.88 and 17 303.20 in the event window. For Event 2 the same average values are 9.14 69.38 and 7 664.93 in the estimation window and 8.25 71.12 and 22 319.10 in the event window. When 14-day abnormal growth rates of the daily number of cases for Event 1 and Event 2 are compared it is observed that Event 1 has negative growth rates initially and reaches a 7.59% growth at most. On the other hand Event 2 starts with a 1.11% growth rate and having a steady increase it reaches a 23.70% growth in the last 14 days of the study period. Conclusion: The preliminary result shows that despite taking more strict governmental measures while residential mobility decreases the daily number of COVID-19 cases increases in the early stages of vaccination compared to short pre-periods of it. This indicates that the initiation of vaccination leads to early behavioral relaxation in public. Moreover the effect of Event 2 on the case numbers is more significant and immediate compared to that of Event 1 which may be linked to the characteristic of the Turkish culture being more sensitive to the older adult population. © 2023 Elsevier B.V. All rights reserved.
Citation - WoS: 11
Citation - Scopus: 10
Factors Relating to Decision Delay in the Emergency Department: Effects of Diagnostic Tests and Consultations
(Dove Medical Press Ltd, 2023) Mustafa Gökalp Ataman; Gorkem Sariyer; Caner Saǧlam; Arif Karagöz; Erden Erol Ünlüer; Ataman, Mustafa Gokalp; Sariyer, Gorkem; Karagoz, Arif; Unluer, Erden Erol; Saglam, Caner
Purpose: The purpose of this study is to investigate the factors increasing waiting time (WT) and length of stay (LOS) in patients which may cause delays in decision-making in the emergency departments (ED). Patients and Methods: Patients who arrived at a training hospital in the central region of Izmir City Turkey during the first quarter of 2020 were retrospectively analyzed. WT and LOS were the outcome variables of the study and gender age arrival type triage level determined based on the clinical acuity diagnosis encoded based on International Classification of Diseases-10 (ICD-10) the existence of diagnostic tests or consultation status were the identified factors. The significance of the differences in WT and LOS values based on each level of these factors was analyzed using independent sample t-tests and ANOVA. Results: While patients for which no diagnostic testing or consultation was requested had a significantly higher WT in EDs their LOS values were substantially lower than those for which at least one diagnostic test or consultation was ordered (p≤0.001). Besides elderly and red zone patients and those who arrived by ambulance had significantly lower WT and higher LOS values than other levels for all groups of patients for which laboratory-type or imaging-type diagnostic test or consultation was requested (p≤0.001 for each comparison). Conclusion: Besides ordering diagnostic tests or consultation in EDs different factors may extend patients’ WT and LOS values and cause significant decision-making delays. Understanding the patient characteristics associated with longer waiting times and LOS values and thus delayed decisions will enable practitioners to improve operations management in EDs. © 2023 Elsevier B.V. All rights reserved.
Citation - WoS: 10
Citation - Scopus: 16
Fiscal responses to COVID-19 outbreak for healthy economies: Modelling with big data analytics
(ELSEVIER, 2023) Gorkem Sariyer; Serpil Kahraman; Mert Erkan Sozen; Mustafa Gokalp Ataman; Ataman, Mustafa Gokalp; Sariyer, Gorkem; Sözen, Mert Erkan; Kahraman, Serpil
Fiscal responses to the COVID-19 crisis have varied a lot across countries. Using a panel of 127 countries over two separate subperiods between 2020 and 2021 this paper seeks to determine the extent that fiscal responses contributed to the spread and containment of the disease. The study first documents that rich countries which had the largest total and health-related fiscal responses achieved the lowest fatality rates defined as the ratio of COVID-related deaths to cases despite having the largest recorded numbers of cases and fatalities. The next most successful were less developed economies whose smaller total fiscal responses included a larger health-related component than emerging market economies. The study used a promising big data analytics technology the random forest algorithm to determine which factors explained a country's fatality rate. The findings indicate that a country's fatality ratio over the next period can be almost entirely predicted by its economic development level fiscal expenditure (both total and health-related) and initial fatality ratio. Finally the study conducted a counterfactual exercise to show that had less developed economies implemented the same fiscal responses as the rich (as a share of GDP) then their fatality ratios would have declined by 20.47% over the first period and 2.59% over the second one.
Citation - WoS: 18
Citation - Scopus: 29
Highlighting the rules between diagnosis types and laboratory diagnostic tests for patients of an emergency department: Use of association rule mining
(SAGE Publications Ltd info@sagepub.co.uk, 2020) Gorkem Sariyer; Ceren Ocal Tasar; Sariyer, Gorkem; Ocal Tasar, Ceren
Diagnostic tests are widely used in emergency departments to make detailed investigations on diagnosis and treat patients correctly. However since these tests are expensive and time-consuming ordering correct tests for patients is crucial for efficient use of hospital resources. Thus understanding the relation between diagnosis and diagnostic test requirement becomes an important issue in emergency departments. Association rule mining was used to extract hidden patterns and relation between diagnosis and diagnostic test requirement in real-life medical data received from an emergency department. Apriori was used as an association rule mining algorithm. Diagnosis was grouped into 21 categories based on International Classification of Disease and laboratory tests were grouped into four main categories (hemogram biochemistry cardiac enzyme urine and human excrement related). Both positive and negative rules were discovered. Since the nature of the data had the dominance of negative values higher number of negative rules with higher confidences were discovered compared to positive ones. The extracted rules were validated by emergency department experts and practitioners. It was concluded that understanding the association between patient’s diagnosis and diagnostic test requirement can improve decision-making and efficient use of resources in emergency departments. Association rules can also be used for supporting physicians to treat patients. © 2020 Elsevier B.V. All rights reserved.
Citation - WoS: 3
Citation - Scopus: 4
How machine learning facilitates decision making in emergency departments: Modelling diagnostic test orders
(WILEY, 2021) Gorkem Sariyer; Mustafa Gokalp Ataman; Ataman, Mustafa Gokalp; Sariyer, Gorkem
Objectives Since emergency departments (EDs) are responsible for providing initial care for patients who may need urgent medical care they are highly sensitive to increased patient delays. A key factor that increases patient delays is ordering diagnostic tests. Therefore understanding the factors increasing diagnostic test orders and proposing efficient models may facilitate decision making in EDs. Methods Month and week of the year day of the week and daily numbers of patients encoded based on 21 different ICD-10 codes were used as input variables. Daily test frequencies of patients requiring tests from laboratory and imaging services were modelled separately by linear regression models. Although significance of the input variables was identified based on these models obtained forecasts and residuals were further processed by machine learning techniques to obtain hybrid models. Results Day of the week and number of patients with ICD-10 codes of 'A00-B99' 'I00-I99' 'J00-J99' 'M00-M99' and 'R00-R99' were significant in both test types. In addition to these although daily patient frequencies with 'H60-H95' 'N00-N99' and 'O00-O9A' were significant for laboratory services 'L00-L99' 'S00-T88' and 'Z00-Z99' were significant for imaging services. Although prediction accuracies of regression models were respectively as 93.658% and 95.028% for laboratory and imaging services modelling they increased to 99.997% and 99.995% with the machine learning-integrated hybrid model. Conclusion The significant factors identified here can predict increases in use of laboratory and imaging services. This could enable these services to be prepared in advance to reduce ED patient delays thereby reducing ED overcrowding. The proposed model may also be efficiently used for decision making.
Leading indicators of currency crises: Discriminant function analysis vs Early warning signal approach, Опережающие показатели валютного кризиса: дискриминантный анализ и сигналы раннего предупреждения
(Southern Federal University, 2022) Serpil Kahraman; Gorkem Sariyer; Kahraman, Serpil; Sariyer, Gorkem
Money markets play a key role in macroeconomic stability. This study aims to extend discriminant function analysis and apply early warning models to detect the signalling indicators of the currency crises in developing countries for the period between 1987 and 2007. The obtained model based on the data on India Indonesia South Korea Malaysia Mexico Philippines Russia Turkey and Thailand then tested in another set of six developing countries including Argentina Brazil Chile Colombia Uruguay and Venezuela. The theoretical premise of the paper is based on the three-generation currency crisis models. The empirical findings indicate that current account balance / reserves M2 growth (annual %) domestic credit provided by banking sector (%of GDP) bank liquid reserves to bank assets ratio (%) and GDP annual growth are the leading indicators of currency crises. The model provided by DFA has around 60% accuracy in foreseeing the status of crisis in the test data set. The results suggest that discriminant function analysis would be a useful tool to predict the “signal”. © 2023 Elsevier B.V. All rights reserved.
Citation - WoS: 11
Citation - Scopus: 11
Leveraging explainable artificial intelligence in understanding public transportation usage rates for sustainable development
(PERGAMON-ELSEVIER SCIENCE LTD, 2024) Gorkem Sariyer; Sachin Kumar Mangla; Mert Erkan Sozen; Guo Li; Yigit Kazancoglu; Sariyer, Gorkem; Sozen, Mert Erkan; Li, Guo; Mangla, Sachin Kumar; Kazancoglu, Yigit
Public transportation usage prediction is valuable for the sustainable development of transportation systems particularly in crowded megacities. Machine learning technologies are of great interest for predicting public transportation usage. While these technologies outperform many other techniques they suffer from limited interpretability. Explainable artificial intelligence (XAI) tools and techniques that offer post -hoc explanations of the obtained predictions are gaining popularity. This paper proposes an advanced tree-based ensemble algorithm for public transportation usage rate prediction. We aim to explain the predictions both with the most widely used technique of XAI Shapley additive explanation (SHAP) and in the light of the rules presented. To predict the total public transportation usage the proposed model combines all types of public transportation categorized as ferry railway and bus unlike most existing studies focusing on a single kind of public transport. Besides the sort of transportation the day of the week whether the day is special and the daily ratio of passenger types were identified as model features for predicting the daily usage of each type of public transportation. We tested the proposed model using an open data set from Izmir City Turkey. While the model had superior prediction performance the explanations showed that the type of public transportation weekday and the ratio of full-fare passengers have the highest SHAP values and the model features have many interactions. We also validated our results using an online data set showing Google search trends.
Citation - WoS: 2
Citation - Scopus: 2
LLM-based embeddings for clustering and predicting integrated reporting quality levels of companies
(Springer Science and Business Media B.V., 2025) Mert Sarioglu; Gorkem Sariyer; Mert Erkan Sözen; Sarioglu, Mert; Sariyer, Gorkem; Sozen, Mert Erkan
Artificial Intelligence (AI) offers various useful functions and algorithms that provide numerous benefits for firms to enhance their decision-making process. Moreover with the adoption of Integrated Reporting (IR) reporting practices which are critical communication channels for companies have become more practical. Given the importance of subjects it is believed that addressing LLM embeddings based AI methodologies will contribute positively to IR quality (IRQ) to achieve better results. Additionally grouping companies according to their IRQ characteristics will lead time and cost efficiency in decision-making. So that the main purpose of this study is to cluster companies with respect to their IRQ characteristics based on LLM embeddings and to use this grouping in further decision-making. This paper therefore provides significant evidence whether LLM is useful tool of AI techniques in IR practices and LLM-based clustering is an efficient way of generating predictions for decision-making. To do so the sample size of the study consists of 260 published IR in 2019. This study also introduces a novelty to the literature on the applicability of LLM with small data sets considering that the number of integrated reports published in a year is low or when the sample considered will be small. The findings reveal the superiority of LLM while indicating the usefulness of LLM in prediction of IRQ regarding different indicators of firms. Given the empirical evidence shown the techniques and steps should be adapted by firms both in identifying ways to improve IRQ and in different AI applications in the future. © 2025 Elsevier B.V. All rights reserved.
Citation - WoS: 1
Citation - Scopus: 1
Machine Learning Implementations for Multi-class Cardiovascular Risk Prediction in Family Health Units
(Ram Arti Publishers, 2023) Mert Erkan Sözen; Gorkem Sariyer; Mustafa Sözen; Gaurav Kumar Badhotiya; Lokesh Vijavargy; Sariyer, Gorkem; Sozen, Mert Erkan; Vijavargy, Lokesh; Badhotiya, Gaurav Kumar
Cardiovascular disease (CVD) risk prediction plays a significant role in clinical research since it is the key to primary prevention. As family health units follow up on a specific group of patients particularly in the middle-aged and elderly groups CVD risk prediction has additional importance for them. In a retrospectively collected data set from a family health unit in Turkey in 2018 we evaluated the CVD risk levels of patients based on SCORE-Turkey. By identifying additional CVD risk factors for SCORE-Turkey and grouping the study patients into 3-classes "low risk" "moderate risk" and "high risk" patients we proposed a machine learning implemented early warning system for CVD risk prediction in family health units. Body mass index diastolic blood pressures serum glucose creatinine urea uric acid levels and HbA1c were significant additional CVD risk factors to SCORE-Turkey. All of the five implemented algorithms k-nearest neighbour (KNN) random forest (RF) decision tree (DT) logistic regression (LR) and support vector machines (SVM) had high prediction performances for both the K4 and K5 partitioning protocols. With 89.7% and 92.1% accuracies for K4 and K5 protocols KNN outperformed the other algorithms. For the five ML algorithms while for the "low risk" category precision and recall measures varied between 95% to 100% "moderate risk" and "high risk" categories these measures varied between 60% to 92%. Machine learning-based algorithms can be used in CVD risk prediction by enhancing prediction performances and combining various risk factors having complex relationships. © 2023 Elsevier B.V. All rights reserved.