Pub Date : 2024-07-06DOI: 10.34110/forecasting.1489839
Shuaib Jasim, İbrahim Onaran, Mustafa Al-asadi
This study explores the use of machine learning algorithms to analyze and predict heart attacks, focusing on genetics, lifestyle, medical history, and biometric factors. The data was analyzed using logistic regression, support vector machines, decision trees, and random forests. Support vector machines were found to be the most effective model for predicting heart attack risk, with a high accuracy rate and low error rate. The study highlights the potential of machine learning in assisting healthcare professionals and individuals in determining heart attack risk and taking preventive measures.
{"title":"Heart Attack Analysis and Prediction with Machine Learning Techniques","authors":"Shuaib Jasim, İbrahim Onaran, Mustafa Al-asadi","doi":"10.34110/forecasting.1489839","DOIUrl":"https://doi.org/10.34110/forecasting.1489839","url":null,"abstract":"This study explores the use of machine learning algorithms to analyze and predict heart attacks, focusing on genetics, lifestyle, medical history, and biometric factors. The data was analyzed using logistic regression, support vector machines, decision trees, and random forests. Support vector machines were found to be the most effective model for predicting heart attack risk, with a high accuracy rate and low error rate. The study highlights the potential of machine learning in assisting healthcare professionals and individuals in determining heart attack risk and taking preventive measures.","PeriodicalId":141932,"journal":{"name":"Turkish Journal of Forecasting","volume":"328 5‐6","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141836943","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-06-12DOI: 10.34110/forecasting.1468420
Emine Kölemen
It is seen that artificial neural networks have begun to be used extensively in the literature in solving the time series forecasting problem. In addition to artificial neural networks, classical forecasting methods can often be used to solve this problem. It is seen that classical forecasting methods give successful results for linear time series analysis. However, there is no linear relationship in many time series. Therefore, it can be thought that deep artificial neural networks, which contain more parameters but create more flexible non-linear model structures compared to classical time series forecasting methods, may enable the production of more successful forecasting methods. In this study, the problem of forecasting hazelnut export amounts according to seasons in Turkey with a dendritic neuron model artificial neural network is discussed. In this study, a training algorithm based on the particle swarm optimization algorithm is given for training the dendritic neuron model artificial neural network. The motivation of the study is to investigate Turkey's hazelnut export amounts according to seasons, using a dendritic neuron model artificial neural network. The performance of the proposed method has been compared with artificial neural networks used in the literature.
{"title":"Forecasting of Turkey's Hazelnut Export Amounts According to Seasons with Dendritic Neuron Model Artificial Neural Network","authors":"Emine Kölemen","doi":"10.34110/forecasting.1468420","DOIUrl":"https://doi.org/10.34110/forecasting.1468420","url":null,"abstract":"It is seen that artificial neural networks have begun to be used extensively in the literature in solving the time series forecasting problem. In addition to artificial neural networks, classical forecasting methods can often be used to solve this problem. It is seen that classical forecasting methods give successful results for linear time series analysis. However, there is no linear relationship in many time series. Therefore, it can be thought that deep artificial neural networks, which contain more parameters but create more flexible non-linear model structures compared to classical time series forecasting methods, may enable the production of more successful forecasting methods. In this study, the problem of forecasting hazelnut export amounts according to seasons in Turkey with a dendritic neuron model artificial neural network is discussed. In this study, a training algorithm based on the particle swarm optimization algorithm is given for training the dendritic neuron model artificial neural network. The motivation of the study is to investigate Turkey's hazelnut export amounts according to seasons, using a dendritic neuron model artificial neural network. The performance of the proposed method has been compared with artificial neural networks used in the literature.","PeriodicalId":141932,"journal":{"name":"Turkish Journal of Forecasting","volume":"6 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141354955","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-06-12DOI: 10.34110/forecasting.1468419
Özlem Karahasan
Artificial neural networks are frequently used to solve many problems and give successful results. Artificial neural networks, which we frequently encounter in solving forecasting problems, attract the attention of researchers with the successful results they provide. Pi-sigma artificial neural network, which is a high-order artificial neural network, draws attention with its use of both additive and multiplicative combining functions in its architectural structure. This artificial neural network model offers successful forecasting results thanks to its high-order structures. In this study, the pi-sigma artificial neural network was preferred due to its superior performance properties, and the particle swarm optimization algorithm was used for training the pi-sigma artificial neural network. To evaluate the performance of this preferred artificial neural network, monthly ready-made manufacturer sale shelled hazelnut quantities in Giresun province was used and a comparison was made with many artificial neural network models available in the literature. It has been observed that this tested method has the best performance among other compared methods.
{"title":"Forecasting of Giresun Hazelnut Quantity in Giresun Province Using Pi-Sigma Artificial Neural Networks","authors":"Özlem Karahasan","doi":"10.34110/forecasting.1468419","DOIUrl":"https://doi.org/10.34110/forecasting.1468419","url":null,"abstract":"Artificial neural networks are frequently used to solve many problems and give successful results. Artificial neural networks, which we frequently encounter in solving forecasting problems, attract the attention of researchers with the successful results they provide. Pi-sigma artificial neural network, which is a high-order artificial neural network, draws attention with its use of both additive and multiplicative combining functions in its architectural structure. This artificial neural network model offers successful forecasting results thanks to its high-order structures. In this study, the pi-sigma artificial neural network was preferred due to its superior performance properties, and the particle swarm optimization algorithm was used for training the pi-sigma artificial neural network. To evaluate the performance of this preferred artificial neural network, monthly ready-made manufacturer sale shelled hazelnut quantities in Giresun province was used and a comparison was made with many artificial neural network models available in the literature. It has been observed that this tested method has the best performance among other compared methods.","PeriodicalId":141932,"journal":{"name":"Turkish Journal of Forecasting","volume":"143 19","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141350863","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-17DOI: 10.34110/forecasting.1260073
Bilal Bora, Ahmet Emin Emanet, Enes Elmaci, Derya Kandaz, Muhammed Kürşad Uçar
Biometric authentication systems reveal individuals' physical or behavioral uniqueness and identify them by comparing them with existing records. Today, many biometric recognition systems, such as fingerprint reading, palm reading, and face reading, are being studied and used. The human voice is also among the techniques used for this purpose. Due to this feature, the human voice performs secure transactions and authentication in various fields. Based on these voice features, we used a dataset of 66,569 voice recordings. The voice recordings were revised to include six sentences of at least six words each from 24 different people to get the maximum benefit from the dataset. The voices in the reduced dataset were labeled as sentences belonging to the same person and sentences belonging to different people and converted into matrix form. A biometric recognition study resulted in a correlation score of 0.88. As a result of these processes, the feasibility of a voice biometric recognition system with artificial intelligence has been demonstrated.
{"title":"Hybrid AI-based Voice Authentication","authors":"Bilal Bora, Ahmet Emin Emanet, Enes Elmaci, Derya Kandaz, Muhammed Kürşad Uçar","doi":"10.34110/forecasting.1260073","DOIUrl":"https://doi.org/10.34110/forecasting.1260073","url":null,"abstract":"Biometric authentication systems reveal individuals' physical or behavioral uniqueness and identify them by comparing them with existing records. Today, many biometric recognition systems, such as fingerprint reading, palm reading, and face reading, are being studied and used. The human voice is also among the techniques used for this purpose. Due to this feature, the human voice performs secure transactions and authentication in various fields. Based on these voice features, we used a dataset of 66,569 voice recordings. The voice recordings were revised to include six sentences of at least six words each from 24 different people to get the maximum benefit from the dataset. The voices in the reduced dataset were labeled as sentences belonging to the same person and sentences belonging to different people and converted into matrix form. A biometric recognition study resulted in a correlation score of 0.88. As a result of these processes, the feasibility of a voice biometric recognition system with artificial intelligence has been demonstrated.","PeriodicalId":141932,"journal":{"name":"Turkish Journal of Forecasting","volume":"356 18","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138966759","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-11-26DOI: 10.34110/forecasting.1367369
N. Erilli
Type-II regression models are used to compare more than one method that makes the same measurement. The Passing-Bablok regression method, which is one of them, is non-parametric and can give more successful results than other comparison methods, especially when there are outliers. In this study, innovations in the calculations of slope and intercept parameters used in the traditional Passing-Bablok method are proposed. Instead of the median parameter used in the classical model, the use of the trimean parameter was suggested and the model parameter estimates were adjusted accordingly. The proposed new model and classical model predictions were compared on 15 different data sets, 8 of which were simulations. It has been determined that the proposed new model calculations contain fewer errors than the results of the classical method.
{"title":"Revised Passing-Bablok Regression Method for Model Comparison","authors":"N. Erilli","doi":"10.34110/forecasting.1367369","DOIUrl":"https://doi.org/10.34110/forecasting.1367369","url":null,"abstract":"Type-II regression models are used to compare more than one method that makes the same measurement. The Passing-Bablok regression method, which is one of them, is non-parametric and can give more successful results than other comparison methods, especially when there are outliers. In this study, innovations in the calculations of slope and intercept parameters used in the traditional Passing-Bablok method are proposed. Instead of the median parameter used in the classical model, the use of the trimean parameter was suggested and the model parameter estimates were adjusted accordingly. The proposed new model and classical model predictions were compared on 15 different data sets, 8 of which were simulations. It has been determined that the proposed new model calculations contain fewer errors than the results of the classical method.","PeriodicalId":141932,"journal":{"name":"Turkish Journal of Forecasting","volume":"6 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139235252","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-30DOI: 10.34110/forecasting.1162548
Daud Aser, E. Firuzan
Since forecasting the future values is fundamental for researchers, investors, practitioners, etc., obtaining accurate predictions is critical in time series analysis. The accuracy is reliant on good modeling and good quality data. The latter is affected by unusual observations, changes over time, missing data, and structural breaks among others. Economic crises are the major cause of data instability and therefore, this paper focuses on how structural breaks in conditional heteroscedastic financial and macroeconomic data affect forecasting accuracy on short and long-term horizons. More specifically, we are interested in the impact of the location of the structural break and break size on the predictive performance of two linear (ARIMA and Exponential Smoothing) forecasting models and two nonlinear (ARIMA – ARCH and Artificial Neural Network) models. We conducted Monte Carlo simulations and showed that the forecasting accuracy decreases as the structural break location approaches the end of the sample. In addition, break size and length of the horizon significantly impact the forecasting accuracy. We also showed that ARIMA – ARCH model is the best performing in the absence of structural break while the artificial neural network model outperforms all the competing models in the presence of structural break, especially in large break sizes and long horizons. Last, we applied the above techniques to forecasting daily close prices of Brent oil and Turkish Lira – USD exchange rates out–of–sample and similar results were found.
{"title":"Impact of Structural Break Location on Forecasting Accuracy: Traditional Methods Versus Artificial Neural Network","authors":"Daud Aser, E. Firuzan","doi":"10.34110/forecasting.1162548","DOIUrl":"https://doi.org/10.34110/forecasting.1162548","url":null,"abstract":"Since forecasting the future values is fundamental for researchers, investors, practitioners, etc., obtaining accurate predictions is critical in time series analysis. The accuracy is reliant on good modeling and good quality data. The latter is affected by unusual observations, changes over time, missing data, and structural breaks among others. Economic crises are the major cause of data instability and therefore, this paper focuses on how structural breaks in conditional heteroscedastic financial and macroeconomic data affect forecasting accuracy on short and long-term horizons. More specifically, we are interested in the impact of the location of the structural break and break size on the predictive performance of two linear (ARIMA and Exponential Smoothing) forecasting models and two nonlinear (ARIMA – ARCH and Artificial Neural Network) models. We conducted Monte Carlo simulations and showed that the forecasting accuracy decreases as the structural break location approaches the end of the sample. In addition, break size and length of the horizon significantly impact the forecasting accuracy. We also showed that ARIMA – ARCH model is the best performing in the absence of structural break while the artificial neural network model outperforms all the competing models in the presence of structural break, especially in large break sizes and long horizons. Last, we applied the above techniques to forecasting daily close prices of Brent oil and Turkish Lira – USD exchange rates out–of–sample and similar results were found.","PeriodicalId":141932,"journal":{"name":"Turkish Journal of Forecasting","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126700285","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-29DOI: 10.34110/forecasting.1223653
Buse Özgür, U. Yolcu
The insurance sector can be seen as a sector that directly affects the country's economy and development with its ability to fund financial markets and meet risks. In this respect, predicting the premium sizes, which is the main factor that constitutes the volume of the insurance sector, as accurately and reliably as possible, indirectly means foreseeing the risks that may arise in terms of the economy and development of the country and taking the necessary measures. In this study, the premium production of some insurance companies operating in Turkey is predicted with different artificial neural networks and evaluated the results comparatively. In this context, basically, two different artificial neural networks (ANNs), feed-forward, and feed-back have been used as predictive tools for insurance premium production. Two training algorithms and two different activation functions have been operated in the structure of the ANNs used. Thus, eight different predictive tools for insurance companies' premium production have been created. The prediction performances of ANNs have been evaluated on the test sets using error criteria such as Root Mean Error Squares, Average Absolute Percentile Error, and Median Absolute Percentile Error.
{"title":"Prediction of the Premium Production of Some Insurance Companies Operating in Turkey with Artificial Neural Networks","authors":"Buse Özgür, U. Yolcu","doi":"10.34110/forecasting.1223653","DOIUrl":"https://doi.org/10.34110/forecasting.1223653","url":null,"abstract":"The insurance sector can be seen as a sector that directly affects the country's economy and development with its ability to fund financial markets and meet risks. In this respect, predicting the premium sizes, which is the main factor that constitutes the volume of the insurance sector, as accurately and reliably as possible, indirectly means foreseeing the risks that may arise in terms of the economy and development of the country and taking the necessary measures. In this study, the premium production of some insurance companies operating in Turkey is predicted with different artificial neural networks and evaluated the results comparatively. In this context, basically, two different artificial neural networks (ANNs), feed-forward, and feed-back have been used as predictive tools for insurance premium production. Two training algorithms and two different activation functions have been operated in the structure of the ANNs used. Thus, eight different predictive tools for insurance companies' premium production have been created. The prediction performances of ANNs have been evaluated on the test sets using error criteria such as Root Mean Error Squares, Average Absolute Percentile Error, and Median Absolute Percentile Error.","PeriodicalId":141932,"journal":{"name":"Turkish Journal of Forecasting","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131099897","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-06DOI: 10.34110/forecasting.1190299
Ahmet Furkan Bayram, Caglar Gurkan, Abdulkadir Budak, Hakan Karatas
The pancreas is one of the vital organs in the human body. Early diagnosis of a disease in the pancreas is critical. In this way, the effects of pancreas diseases, especially pancreatic cancer on the person are decreased. With this purpose, artificial intelligence-assisted pancreatic cancer segmentation was performed for early diagnosis in this paper. For this aim, several state-of-the-art segmentation networks, UNet, LinkNet, SegNet, SQ-Net, DABNet, EDANet, and ESNet were used in this study. In the comparative analysis, the best segmentation performance has been achieved by SQ-Net. SQ-Net has achieved a 0.917 dice score, 0.847 IoU score, 0.920 sensitivity, 1.000 specificity, 0.914 precision, and 0.999 accuracy. Considering these results, an artificial intelligence-based decision support system was created in the study.
{"title":"Fully Automatic End-to-End Convolutional Neural Networks-Based Pancreatic Tumor Segmentation on CT Modality","authors":"Ahmet Furkan Bayram, Caglar Gurkan, Abdulkadir Budak, Hakan Karatas","doi":"10.34110/forecasting.1190299","DOIUrl":"https://doi.org/10.34110/forecasting.1190299","url":null,"abstract":"The pancreas is one of the vital organs in the human body. Early diagnosis of a disease in the pancreas is critical. In this way, the effects of pancreas diseases, especially pancreatic cancer on the person are decreased. With this purpose, artificial intelligence-assisted pancreatic cancer segmentation was performed for early diagnosis in this paper. For this aim, several state-of-the-art segmentation networks, UNet, LinkNet, SegNet, SQ-Net, DABNet, EDANet, and ESNet were used in this study. In the comparative analysis, the best segmentation performance has been achieved by SQ-Net. SQ-Net has achieved a 0.917 dice score, 0.847 IoU score, 0.920 sensitivity, 1.000 specificity, 0.914 precision, and 0.999 accuracy. Considering these results, an artificial intelligence-based decision support system was created in the study.","PeriodicalId":141932,"journal":{"name":"Turkish Journal of Forecasting","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124899124","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-04DOI: 10.34110/forecasting.1190289
Ahmet Furkan Bayram, Caglar Gurkan, Abdulkadir Budak, Hakan Karatas
The prevalence of brain tumor is quite high. Brain tumor causes critical diseases. Also, brain tumor causes a variety of symptoms in most people. This study aims to segmentation of the tumor in the brain. For this purpose, state-of-art architectures, such as UNet, Attention UNet, Residual UNet, Attention Residual UNet, Residual UNet++, Inception UNet, LinkNet, and SegNet were used for segmentation. 592 magnetic resonance (MR) images were utilized in the training and testing of segmentation architectures. In the comparative analysis, Attention UNet achieved the best predictive performance with a 0.886 dice score, 0.795 IoU score, 0.881 sensitivity, 0.993 specificity, 0.891 precision, and 0.986 accuracy.
{"title":"Convolutional Neural Networks for MRI-Based Brain Tumor Segmentation: A Comparative Analysis of State-of-the-Art Segmentation Networks","authors":"Ahmet Furkan Bayram, Caglar Gurkan, Abdulkadir Budak, Hakan Karatas","doi":"10.34110/forecasting.1190289","DOIUrl":"https://doi.org/10.34110/forecasting.1190289","url":null,"abstract":"The prevalence of brain tumor is quite high. Brain tumor causes critical diseases. Also, brain tumor causes a variety of symptoms in most people. This study aims to segmentation of the tumor in the brain. For this purpose, state-of-art architectures, such as UNet, Attention UNet, Residual UNet, Attention Residual UNet, Residual UNet++, Inception UNet, LinkNet, and SegNet were used for segmentation. 592 magnetic resonance (MR) images were utilized in the training and testing of segmentation architectures. In the comparative analysis, Attention UNet achieved the best predictive performance with a 0.886 dice score, 0.795 IoU score, 0.881 sensitivity, 0.993 specificity, 0.891 precision, and 0.986 accuracy.","PeriodicalId":141932,"journal":{"name":"Turkish Journal of Forecasting","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122094257","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-01DOI: 10.34110/forecasting.1185545
Murat Simsek, Ahmet Said Daş
As of today entrepreneurs and entrepreneurship are considered to be the integral parts of the economic and technological advancements. Entrepreneurs are promoted in many countries because of their high return on investment opportunities both in terms of income and new inventions. Numerous studies prove that entrepreneurs have many traits in common and these common traits can correlate with each other. Based on these common traits, potential entrepreneurs can be predicted, current entrepreneurs can be improved by realising their weak sides and the ones who wish to be entrepreneurs can be provided with insights. A machine learning approach can light the way for a better rewarding future for entrepreneurship, helping these goals significantly. There exist several studies for the prediction of entrepreneurial competency with the use of machine learning algorithms. Most machine learning methods perform better accuracy and F1-score imbalanced data instead in imbalanced data. This study focuses on utilizing imbalanced class handling methods to increase prediction performance. Random Oversampling, Random Undersampling, SMOTE, and NearMiss methods are used to handling imbalanced data for this purpose in this study. The performance of the machine learning algorithms with Imbalanced Data Handling methods is compared with the machine learning algorithms. Comparisons were made using accuracy, precision, recall, F1-Score as performance parameters. The comparison shows a noticeable performance increase using machine learning algorithms with handling imbalanced dataset methods.
{"title":"The Effect of Handling Imbalanced Datasets Methods on Prediction of Entrepreneurial Competency in University Students","authors":"Murat Simsek, Ahmet Said Daş","doi":"10.34110/forecasting.1185545","DOIUrl":"https://doi.org/10.34110/forecasting.1185545","url":null,"abstract":"As of today entrepreneurs and entrepreneurship are considered to be the integral parts of the economic and technological advancements. Entrepreneurs are promoted in many countries because of their high return on investment opportunities both in terms of income and new inventions. \u0000Numerous studies prove that entrepreneurs have many traits in common and these common traits can correlate with each other. Based on these common traits, potential entrepreneurs can be predicted, current entrepreneurs can be improved by realising their weak sides and the ones who wish to be entrepreneurs can be provided with insights. A machine learning approach can light the way for a better rewarding future for entrepreneurship, helping these goals significantly. \u0000There exist several studies for the prediction of entrepreneurial competency with the use of machine learning algorithms. Most machine learning methods perform better accuracy and F1-score imbalanced data instead in imbalanced data. This study focuses on utilizing imbalanced class handling methods to increase prediction performance. Random Oversampling, Random Undersampling, SMOTE, and NearMiss methods are used to handling imbalanced data for this purpose in this study. The performance of the machine learning algorithms with Imbalanced Data Handling methods is compared with the machine learning algorithms. Comparisons were made using accuracy, precision, recall, F1-Score as performance parameters. The comparison shows a noticeable performance increase using machine learning algorithms with handling imbalanced dataset methods.","PeriodicalId":141932,"journal":{"name":"Turkish Journal of Forecasting","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115003454","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：