Fatih Abut
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Fatih Abut has a total of 37 co-authors. Here are the top co-authors by number of shared publications:
- Mehmet Fatih Akay
CUKUROVA UNIVERSITY, FACULTY OF ENGINEERING
8 shared publications - Mehmet Kızıldağ
Department of Information Security Technology, Adana Alparslan Trke Science and Technology University, Adana, Trkiye
4 shared publications A Özcan
Department of Computer Engineering, Faculty of Engineering, Akdeniz University, Antalya, Turkey
1 shared publication- Abdülvahap Saygin
Department of Computer Technology, Adana Vocational School, Çukurova University, 01160 Çukurova/Adana, Turkey
1 shared publication - Akasya Akyuz
Trendyol
1 shared publication - Alper Kamil Demir
Adana Alparslan Turkes Sci & Technol Univ, Dept Comp Engn, Adana, Turkiye
1 shared publication
Latest Publications
- Open Access
- 16 September 2026
- Published by Omer Halisdemir Universitesi in Ömer Halisdemir Üniversitesi Mühendislik Bilimleri Dergisi
- Vol. 18
Revisiting available bandwidth estimation tools in contemporary hybrid networks: Gigabit ethernet with last-hop 802.11n Wi-Fi
High-speed and wireless network environments pose substantial challenges to the accuracy and reliability of available-bandwidth (avail-bw) estimation, particularly in hybrid access networks integrating high-capacity wired cores with variable wireless edges. A common deployment combines a Gigabit Ethernet (GigE) backbone with a last-hop IEEE 802.11n Wi-Fi link, providing high nominal capacity while exhibiting significant temporal variability caused by contention, stochastic channel behavior, and non-stationary traffic dynamics. This configuration reflects real-world networks where stable wired infrastructure coexists with wireless technologies subject to variable channel conditions and competing traffic. Despite newer wireless standards, IEEE 802.11n remains widely deployed in end-user devices and continues to support last-hop connectivity. This mixed wired–wireless environment provides a realistic setting for evaluating classical avail-bw estimation tools. Accordingly, this study experimentally evaluates established end-to-end avail-bw estimation tools under realistic mixed-technology conditions. DietTOPP, PTR, and Pathwave are assessed on a real-world testbed integrating GigE with a last-hop 802.11n Wi-Fi link. Using the D-ITG cross-traffic generator, diverse traffic patterns and controlled crossing and contending traffic scenarios are emulated. Results reveal significant accuracy degradation under non-stationary and concurrent loads, highlighting the limitations of existing tools and the need for wireless-aware, traffic-adaptive avail-bw estimation techniques for modern hybrid networks.
- 16 September 2026
- Published by Omer Halisdemir Universitesi in Ömer Halisdemir Üniversitesi Mühendislik Bilimleri Dergisi
- Vol. 18
Open AccessRevisiting available bandwidth estimation tools in contemporary hybrid networks: Gigabit ethernet with last-hop 802.11n Wi-Fi
High-speed and wireless network environments pose substantial challenges to the accuracy and reliability of available-bandwidth (avail-bw) estimation, particularly in hybrid access networks integrating high-capacity wired cores with variable wireless edges. A common deployment combines a Gigabit Ethernet (GigE) backbone with a last-hop IEEE 802.11n Wi-Fi link, providing high nominal capacity while exhibiting significant temporal variability caused by contention, stochastic channel behavior, and non-stationary traffic dynamics. This configuration reflects real-world networks where stable wired infrastructure coexists with wireless technologies subject to variable channel conditions and competing traffic. Despite newer wireless standards, IEEE 802.11n remains widely deployed in end-user devices and continues to support last-hop connectivity. This mixed wired–wireless environment provides a realistic setting for evaluating classical avail-bw estimation tools. Accordingly, this study experimentally evaluates established end-to-end avail-bw estimation tools under realistic mixed-technology conditions. DietTOPP, PTR, and Pathwave are assessed on a real-world testbed integrating GigE with a last-hop 802.11n Wi-Fi link. Using the D-ITG cross-traffic generator, diverse traffic patterns and controlled crossing and contending traffic scenarios are emulated. Results reveal significant accuracy degradation under non-stationary and concurrent loads, highlighting the limitations of existing tools and the need for wireless-aware, traffic-adaptive avail-bw estimation techniques for modern hybrid networks.
- Open Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 102282-102315
Adaptive Dynamic Message Packing for Enhanced Throughput and Resilience in Link 16 Networks
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 102282-102315
Open AccessAdaptive Dynamic Message Packing for Enhanced Throughput and Resilience in Link 16 Networks
- Open Access
- 9 May 2025
- Published by MDPI AG in Electronics
- Vol. 14 (10) , 1930
A New Large Language Model for Attribute Extraction in E-Commerce Product Categorization
In the rapidly evolving field of e-commerce, precise and efficient attribute extraction from product descriptions is crucial for enhancing search functionality, improving customer experience, and streamlining the listing process for sellers. This study proposes a large language model (LLM)-based approach for automated attribute extraction on Trendyol’s e-commerce platform. For comparison purposes, a deep learning (DL) model is also developed, leveraging a transformer-based architecture to efficiently identify explicit attributes. In contrast, the LLM, built on the Mistral architecture, demonstrates superior contextual understanding, enabling the extraction of both explicit and implicit attributes from unstructured text. The models are evaluated on an extensive dataset derived from Trendyol’s Turkish-language product catalog, using performance metrics such as precision, recall, and F1-score. Results indicate that the proposed LLM outperforms the DL model across most metrics, demonstrating superiority not only in direct single-model comparisons but also in average performance across all evaluated categories. This advantage is particularly evident in handling complex linguistic structures and diverse product descriptions. The system has been integrated into Trendyol’s platform with a scalable backend infrastructure, employing Kubernetes and Nvidia Triton Inference Server for efficient bulk processing and real-time attribute suggestions during the product listing process. This study not only advances attribute extraction for Turkish-language e-commerce but also provides a scalable and efficient NLP-based solution applicable to large-scale marketplaces. The findings offer critical insights into the trade-offs between accuracy and computational efficiency in large-scale multilingual NLP applications, contributing to the broader field of automated product classification and information retrieval in e-commerce ecosystems.
- 9 May 2025
- Published by MDPI AG in Electronics
- Vol. 14 (10) , 1930
Open AccessA New Large Language Model for Attribute Extraction in E-Commerce Product Categorization
In the rapidly evolving field of e-commerce, precise and efficient attribute extraction from product descriptions is crucial for enhancing search functionality, improving customer experience, and streamlining the listing process for sellers. This study proposes a large language model (LLM)-based approach for automated attribute extraction on Trendyol’s e-commerce platform. For comparison purposes, a deep learning (DL) model is also developed, leveraging a transformer-based architecture to efficiently identify explicit attributes. In contrast, the LLM, built on the Mistral architecture, demonstrates superior contextual understanding, enabling the extraction of both explicit and implicit attributes from unstructured text. The models are evaluated on an extensive dataset derived from Trendyol’s Turkish-language product catalog, using performance metrics such as precision, recall, and F1-score. Results indicate that the proposed LLM outperforms the DL model across most metrics, demonstrating superiority not only in direct single-model comparisons but also in average performance across all evaluated categories. This advantage is particularly evident in handling complex linguistic structures and diverse product descriptions. The system has been integrated into Trendyol’s platform with a scalable backend infrastructure, employing Kubernetes and Nvidia Triton Inference Server for efficient bulk processing and real-time attribute suggestions during the product listing process. This study not only advances attribute extraction for Turkish-language e-commerce but also provides a scalable and efficient NLP-based solution applicable to large-scale marketplaces. The findings offer critical insights into the trade-offs between accuracy and computational efficiency in large-scale multilingual NLP applications, contributing to the broader field of automated product classification and information retrieval in e-commerce ecosystems.
- Open Access
- 6 January 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (1) , 487
Design and Implementation of a Reconfigurable Test Environment for Network Measurement Tools Based on a Control and Management Framework
To be applicable to real-world networks, a realistic evaluation of network measurement tools requires the conditions of the test network to be as similar as possible to the networks in which they are later deployed. Thus, having an existing real-world network which can be utilized for testing, while also allowing the reconfiguration of certain characteristics and features, is of significant interest to researchers. Providing the researchers with corresponding management tools with which they can introduce artificial conditions and topology changes into the network would help in realizing more realistic testbed setups and scenarios. The purpose of this study is to develop a configurable test environment based on the Control and Management Framework (OMF) to support researchers in a realistic empirical evaluation of network measurement tools. The proposed OMF-enabled test environment has the merit of automatizing the deployments and executions of any measurement experiments, collecting their final estimates, and then transporting them back to a single experiment controller without requiring any physical access to the corresponding experimental nodes used. It is demonstrated how the test environment can be used for the evaluation of network measurement experiments based on four representative case studies. These include validating the accuracy of end-to-end round-trip time and available bandwidth estimation tools, measuring the TCP and UDP throughput, and analyzing the impact of packet loss and jitter on VoIP performance, all conducted over dynamically adjusted testbed configurations. These case studies highlight the versatility and effectiveness of the OMF-enabled test environment, positioning it as a valuable tool for advancing the realistic evaluation of network measurement tools in controlled yet adaptable settings.
- 6 January 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (1) , 487
Open AccessDesign and Implementation of a Reconfigurable Test Environment for Network Measurement Tools Based on a Control and Management Framework
To be applicable to real-world networks, a realistic evaluation of network measurement tools requires the conditions of the test network to be as similar as possible to the networks in which they are later deployed. Thus, having an existing real-world network which can be utilized for testing, while also allowing the reconfiguration of certain characteristics and features, is of significant interest to researchers. Providing the researchers with corresponding management tools with which they can introduce artificial conditions and topology changes into the network would help in realizing more realistic testbed setups and scenarios. The purpose of this study is to develop a configurable test environment based on the Control and Management Framework (OMF) to support researchers in a realistic empirical evaluation of network measurement tools. The proposed OMF-enabled test environment has the merit of automatizing the deployments and executions of any measurement experiments, collecting their final estimates, and then transporting them back to a single experiment controller without requiring any physical access to the corresponding experimental nodes used. It is demonstrated how the test environment can be used for the evaluation of network measurement experiments based on four representative case studies. These include validating the accuracy of end-to-end round-trip time and available bandwidth estimation tools, measuring the TCP and UDP throughput, and analyzing the impact of packet loss and jitter on VoIP performance, all conducted over dynamically adjusted testbed configurations. These case studies highlight the versatility and effectiveness of the OMF-enabled test environment, positioning it as a valuable tool for advancing the realistic evaluation of network measurement tools in controlled yet adaptable settings.
- Open Access
- 31 December 2024
- Published by Cukurova University, Institute of Natural and Applied Sciences in Cukurova University Journal of Natural and Applied Sciences
- Vol. 3 (2) , 36-44
Design and Development of a Fashion Oriented Personalized Search Engine
Finding the desired product in the e-commerce sector in the fastest and easiest way plays a vital role in customer satisfaction and revenue growth. Some interactive search engines have already been proposed in the literature and allow for text or visual queries. Nevertheless, these studies focus on finding items aesthetically similar to the query without considering the query personalization aspects. Query personalization allows that user preferences are provided as a user profile separately from the query and dynamically decide how this profile will affect the query results. In this study, a personalized search engine is proposed, which is fed with the product data of the e-commerce site trendyol.com operating in the fashion-oriented retailing sector. More specifically, a search engine has been developed to recognize and help online shoppers find what they are looking for and discover a broader and more relevant range of products in the trendyol.com catalog. The index, search, and data collection infrastructures and a brand-based user-segmented product listing algorithm have been designed and implemented to realize the search engine. As the outcome of the study, a fashion-oriented and personalized site search has been enabled thar successfully reveals products that have never been thought of before by directly associating the products the customers want. The results show that personalizing the search queries increase the odds of success. With the development of the personalized search engine, it is expected that Trendyol’s revenues will grow in a short time through users visiting the site.
- 31 December 2024
- Published by Cukurova University, Institute of Natural and Applied Sciences in Cukurova University Journal of Natural and Applied Sciences
- Vol. 3 (2) , 36-44
Open AccessDesign and Development of a Fashion Oriented Personalized Search Engine
Finding the desired product in the e-commerce sector in the fastest and easiest way plays a vital role in customer satisfaction and revenue growth. Some interactive search engines have already been proposed in the literature and allow for text or visual queries. Nevertheless, these studies focus on finding items aesthetically similar to the query without considering the query personalization aspects. Query personalization allows that user preferences are provided as a user profile separately from the query and dynamically decide how this profile will affect the query results. In this study, a personalized search engine is proposed, which is fed with the product data of the e-commerce site trendyol.com operating in the fashion-oriented retailing sector. More specifically, a search engine has been developed to recognize and help online shoppers find what they are looking for and discover a broader and more relevant range of products in the trendyol.com catalog. The index, search, and data collection infrastructures and a brand-based user-segmented product listing algorithm have been designed and implemented to realize the search engine. As the outcome of the study, a fashion-oriented and personalized site search has been enabled thar successfully reveals products that have never been thought of before by directly associating the products the customers want. The results show that personalizing the search queries increase the odds of success. With the development of the personalized search engine, it is expected that Trendyol’s revenues will grow in a short time through users visiting the site.
- Open Access
- 2 November 2024
- Published by MDPI AG in Applied Sciences
- Vol. 14 (21) , 10011
Development of New Electricity System Marginal Price Forecasting Models Using Statistical and Artificial Intelligence Methods
The System Marginal Price (SMP) is the cost of the last unit of electricity supplied to the grid, reflecting the supply–demand equilibrium and serving as a key indicator of market conditions. Accurate SMP forecasting is essential for ensuring market stability and economic efficiency. This study addresses the challenges of SMP prediction in Turkey by proposing a comprehensive forecasting framework that integrates machine learning, deep learning, and statistical models. Advanced feature selection techniques, such as Minimum Redundancy Maximum Relevance (mRMR) and Maximum Likelihood Feature Selector (MLFS), are employed to refine model inputs. The framework incorporates time series methods like Multilayer Perceptron (MLP), Long Short-Term Memory (LSTM), Bidirectional LSTM (Bi-LSTM), and Convolutional LSTM (ConvLSTM) to capture complex temporal patterns, alongside models such as Support Vector Machine (SVM), Extreme Gradient Boosting (XGBoost), and Extreme Learning Machine (ELM) for modeling non-linear relationships. Model performance was evaluated using the Mean Absolute Percentage Error (MAPE) across regular weekdays, weekends, and public holidays. XGBoost combined with MLFS consistently achieved the lowest MAPE values, demonstrating exceptional accuracy and robustness. Among all of the models, XGBoost combined with MLFS consistently achieved the lowest MAPE values, demonstrating superior accuracy and robustness. The results highlight the inadequacy of traditional models like ARIMA and SARIMA in capturing non-linear and highly volatile patterns, reinforcing the necessity of using advanced techniques for effective SMP forecasting. Overall, this study presents a novel and comprehensive approach tailored for complex electricity markets, significantly enhancing predictive reliability by incorporating economic indicators and sophisticated feature selection methods.
- 2 November 2024
- Published by MDPI AG in Applied Sciences
- Vol. 14 (21) , 10011
Open AccessDevelopment of New Electricity System Marginal Price Forecasting Models Using Statistical and Artificial Intelligence Methods
The System Marginal Price (SMP) is the cost of the last unit of electricity supplied to the grid, reflecting the supply–demand equilibrium and serving as a key indicator of market conditions. Accurate SMP forecasting is essential for ensuring market stability and economic efficiency. This study addresses the challenges of SMP prediction in Turkey by proposing a comprehensive forecasting framework that integrates machine learning, deep learning, and statistical models. Advanced feature selection techniques, such as Minimum Redundancy Maximum Relevance (mRMR) and Maximum Likelihood Feature Selector (MLFS), are employed to refine model inputs. The framework incorporates time series methods like Multilayer Perceptron (MLP), Long Short-Term Memory (LSTM), Bidirectional LSTM (Bi-LSTM), and Convolutional LSTM (ConvLSTM) to capture complex temporal patterns, alongside models such as Support Vector Machine (SVM), Extreme Gradient Boosting (XGBoost), and Extreme Learning Machine (ELM) for modeling non-linear relationships. Model performance was evaluated using the Mean Absolute Percentage Error (MAPE) across regular weekdays, weekends, and public holidays. XGBoost combined with MLFS consistently achieved the lowest MAPE values, demonstrating exceptional accuracy and robustness. Among all of the models, XGBoost combined with MLFS consistently achieved the lowest MAPE values, demonstrating superior accuracy and robustness. The results highlight the inadequacy of traditional models like ARIMA and SARIMA in capturing non-linear and highly volatile patterns, reinforcing the necessity of using advanced techniques for effective SMP forecasting. Overall, this study presents a novel and comprehensive approach tailored for complex electricity markets, significantly enhancing predictive reliability by incorporating economic indicators and sophisticated feature selection methods.
- Open Access
- 9 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 156050-156064
Harnessing AI for Health: Optimized Neural Network Models for Resting Metabolic Rate Prediction
Resting Metabolic Rate (RMR) is a pivotal metric reflecting the caloric expenditure necessary for fundamental physiological functions during periods of rest, encompassing vital processes such as blood circulation, brain activity, respiration, fuel metabolism, and thermal regulation. The accurate estimation of RMR holds paramount importance in delineating an individual’s daily energy requirements and assessing their susceptibility to various health conditions, including cardiovascular diseases, hypertension, and diabetes. Additionally, RMR serves as a significant indicator of biological age, aiding in the formulation of personalized dietary plans by nutritionists to assist individuals in achieving their health and wellness objectives. This study aims to develop new models for predicting RMR using General Regression Neural Network (GRNN). Additionally, prediction models based on Multi-Layer Perceptron (MLP) will be created for comparison purposes. For model optimization, we developed an innovative web-based software using the DTREG predictive modeling software library. The implementation of this application was executed using Visual Studio and the C# programming language. To ensure the robustness of the prediction models, two distinct self-created datasets comprising data from female and male patients were employed. A total of 260 female patients and 150 male patients were included in the datasets. Separate GRNN-based and MLP-based models were developed for each dataset, leveraging various variables obtained from Tanita, a smart scale capable of comprehensive body scanning. These variables encompass personal information, body analysis, reference analysis, and segmental body composition analysis, providing detailed insights into impedance, fat percentage, fat mass, non-fat mass, muscle mass, and other metrics. The variables derived from Tanita measurements served as input variables for machine learning model creation, while RMR values obtained using FitMate™ served as output variables. Evaluation of these prediction models was based on Correlation Coefficient (R), Root Mean Square Error (RMSE), and Mean Absolute Percentage Error (MAPE) metrics to assess their performance, with the outcomes substantiating the efficacy of the proposed models in RMR prediction. The GRNN-based models performed better than the ones built by MLP, demonstrating its feasibility as a tool for predicting RMR accurately. The results have also been compared with up-to-date prediction equations from related literature, and our optimized models perform significantly better than those. The proposed best performing GRNN model achieved an R value of 0.85, RMSE of 134.91 kcal/day, and MAPE of 10.20%, significantly outperforming traditional predictive equations such as the Harris-Benedict and Mifflin-St Jeor equations, which showed RMSE values above 400 kcal/day and MAPE values exceeding 12.5%.
- 9 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 156050-156064
Open AccessHarnessing AI for Health: Optimized Neural Network Models for Resting Metabolic Rate Prediction
Resting Metabolic Rate (RMR) is a pivotal metric reflecting the caloric expenditure necessary for fundamental physiological functions during periods of rest, encompassing vital processes such as blood circulation, brain activity, respiration, fuel metabolism, and thermal regulation. The accurate estimation of RMR holds paramount importance in delineating an individual’s daily energy requirements and assessing their susceptibility to various health conditions, including cardiovascular diseases, hypertension, and diabetes. Additionally, RMR serves as a significant indicator of biological age, aiding in the formulation of personalized dietary plans by nutritionists to assist individuals in achieving their health and wellness objectives. This study aims to develop new models for predicting RMR using General Regression Neural Network (GRNN). Additionally, prediction models based on Multi-Layer Perceptron (MLP) will be created for comparison purposes. For model optimization, we developed an innovative web-based software using the DTREG predictive modeling software library. The implementation of this application was executed using Visual Studio and the C# programming language. To ensure the robustness of the prediction models, two distinct self-created datasets comprising data from female and male patients were employed. A total of 260 female patients and 150 male patients were included in the datasets. Separate GRNN-based and MLP-based models were developed for each dataset, leveraging various variables obtained from Tanita, a smart scale capable of comprehensive body scanning. These variables encompass personal information, body analysis, reference analysis, and segmental body composition analysis, providing detailed insights into impedance, fat percentage, fat mass, non-fat mass, muscle mass, and other metrics. The variables derived from Tanita measurements served as input variables for machine learning model creation, while RMR values obtained using FitMate™ served as output variables. Evaluation of these prediction models was based on Correlation Coefficient (R), Root Mean Square Error (RMSE), and Mean Absolute Percentage Error (MAPE) metrics to assess their performance, with the outcomes substantiating the efficacy of the proposed models in RMR prediction. The GRNN-based models performed better than the ones built by MLP, demonstrating its feasibility as a tool for predicting RMR accurately. The results have also been compared with up-to-date prediction equations from related literature, and our optimized models perform significantly better than those. The proposed best performing GRNN model achieved an R value of 0.85, RMSE of 134.91 kcal/day, and MAPE of 10.20%, significantly outperforming traditional predictive equations such as the Harris-Benedict and Mifflin-St Jeor equations, which showed RMSE values above 400 kcal/day and MAPE values exceeding 12.5%.
- 2 September 2023
- Published by SAGE Publications in Proceedings of the Institution of Mechanical Engineers, Part P: Journal of Sports Engineering and Technology
- Vol. 240 (1) , 3-16
Non-exercise-based racing time prediction of cross-country skiers using machine learning methods combined with Relief-F feature selection
This study proposes new non-exercise models for estimating the racing time of cross-country skiers. Machine learning methods employed to build the prediction models include General Regression Neural Network (GRNN), Support Vector Machine (SVM), Multilayer Feed-Forward Artificial Neural Network (MFANN), and Radial Basis Function Neural Network (RBFNN), whereas the Relief-F algorithm combined with a ranker search has been utilized as the feature selector. The self-created data set contains samples collected from 370 cross-country skiers with inhomogeneous capabilities. Each sample in the data set contains physiological variables such as sex, age, height, weight, and body mass index (BMI) combined with an immersive set of survey data. The outcomes suggest that generally, the GRNN-based models exhibit the best prediction performance and can be used as a feasible tool for the prediction of the racing time of cross-country skiers with tolerable root mean square errors (RMSEs). It is seen that inclusion of age and assigned starting wave of cross-country skiers in models leads to much lower RMSEs, suggesting that the racing time of cross-country skiers is highly correlated to these two predictor variables. When compared with the exercise-based models, the proposed non-exercise-based models produce consistently comparable prediction performance for all evaluated machine learning methods. The non-exercise-based models have the relevant benefit of practical feasibility, as the models do not require the skiers to complete physical exercises and are also applicable to a wide range of cross-country skiers.
- 2 September 2023
- Published by SAGE Publications in Proceedings of the Institution of Mechanical Engineers, Part P: Journal of Sports Engineering and Technology
- Vol. 240 (1) , 3-16
Non-exercise-based racing time prediction of cross-country skiers using machine learning methods combined with Relief-F feature selection
This study proposes new non-exercise models for estimating the racing time of cross-country skiers. Machine learning methods employed to build the prediction models include General Regression Neural Network (GRNN), Support Vector Machine (SVM), Multilayer Feed-Forward Artificial Neural Network (MFANN), and Radial Basis Function Neural Network (RBFNN), whereas the Relief-F algorithm combined with a ranker search has been utilized as the feature selector. The self-created data set contains samples collected from 370 cross-country skiers with inhomogeneous capabilities. Each sample in the data set contains physiological variables such as sex, age, height, weight, and body mass index (BMI) combined with an immersive set of survey data. The outcomes suggest that generally, the GRNN-based models exhibit the best prediction performance and can be used as a feasible tool for the prediction of the racing time of cross-country skiers with tolerable root mean square errors (RMSEs). It is seen that inclusion of age and assigned starting wave of cross-country skiers in models leads to much lower RMSEs, suggesting that the racing time of cross-country skiers is highly correlated to these two predictor variables. When compared with the exercise-based models, the proposed non-exercise-based models produce consistently comparable prediction performance for all evaluated machine learning methods. The non-exercise-based models have the relevant benefit of practical feasibility, as the models do not require the skiers to complete physical exercises and are also applicable to a wide range of cross-country skiers.
- Open Access
- 15 August 2023
- Published by University of Slavonski Brod in Tehnicki vjesnik - Technical Gazette
- Vol. 30 (4) , 1257-1264
Development of a Neural Network Algorithm for Estimating the Makespan in Jobshop Production Scheduling
Since production scheduling is considered a short-term plan for future production planning, the advantages of effective scheduling and control and their contribution to the production process are numerous. Efficient use of resources improves producti...
- 15 August 2023
- Published by University of Slavonski Brod in Tehnicki vjesnik - Technical Gazette
- Vol. 30 (4) , 1257-1264
Open AccessDevelopment of a Neural Network Algorithm for Estimating the Makespan in Jobshop Production Scheduling
Since production scheduling is considered a short-term plan for future production planning, the advantages of effective scheduling and control and their contribution to the production process are numerous. Efficient use of resources improves producti...
- Open Access
- 30 November 2022
- Published by Kocaeli Journal of Science and Engineering in Kocaeli Journal of Science and Engineering
- Vol. 5 (ICOLES2021) , 32-37
Brand Propensity Prediction with Click-Through Rate as a Target
Personalizing the e-commerce experience is vital since there are enormous amounts of products to offer customers. Each day new products are introduced into the ecosystem, and customer purchase behavior is dynamic as well. This mapping between products and customers needs to be optimized. E-commerce platforms try to funnel those products by a variety of methods like user clustering and product propensity analysis. The brand propensity metric is one of those key features for personalizing products offered to the customer. Once the brand propensity is calculated, it can be used to cluster customers or list products within the same brand. Since customers periodically interact with different products, these interactions (e.g., product visit, favorite, basket, search, and order) are aggregated to predict the next actions of the corresponding customer. Typically, the next action might be an order action or click. In this study, we develop Logistic Regression (LR) models to investigate the effect of the target variable on calculating brand propensity. For comparison purposes, models based on Decision Tree (DT), Random Forest (RF), and XGBoost (XGB) have also been developed. The target variable to be evaluated for the brand propensity model has been set to both order probability and click probability. The “Top N accuracy” metric has been used to evaluate the performance of the models. As the study’s outcome, click as a target variable has been revealed to be more beneficial since it also shows that customers are more likely to explore what is inside that brand. In addition, the LR-based propensity models exhibit the best average performance for both Top 3 and Top 5 accuracies among the machine learning methods.
- 30 November 2022
- Published by Kocaeli Journal of Science and Engineering in Kocaeli Journal of Science and Engineering
- Vol. 5 (ICOLES2021) , 32-37
Open AccessBrand Propensity Prediction with Click-Through Rate as a Target
Personalizing the e-commerce experience is vital since there are enormous amounts of products to offer customers. Each day new products are introduced into the ecosystem, and customer purchase behavior is dynamic as well. This mapping between products and customers needs to be optimized. E-commerce platforms try to funnel those products by a variety of methods like user clustering and product propensity analysis. The brand propensity metric is one of those key features for personalizing products offered to the customer. Once the brand propensity is calculated, it can be used to cluster customers or list products within the same brand. Since customers periodically interact with different products, these interactions (e.g., product visit, favorite, basket, search, and order) are aggregated to predict the next actions of the corresponding customer. Typically, the next action might be an order action or click. In this study, we develop Logistic Regression (LR) models to investigate the effect of the target variable on calculating brand propensity. For comparison purposes, models based on Decision Tree (DT), Random Forest (RF), and XGBoost (XGB) have also been developed. The target variable to be evaluated for the brand propensity model has been set to both order probability and click probability. The “Top N accuracy” metric has been used to evaluate the performance of the models. As the study’s outcome, click as a target variable has been revealed to be more beneficial since it also shows that customers are more likely to explore what is inside that brand. In addition, the LR-based propensity models exhibit the best average performance for both Top 3 and Top 5 accuracies among the machine learning methods.