Sürdürülebilir Kalkınma Amaçları

• 1

• MakaleAçık Erişim2026Scopus SJRQ2/r/bayburt/11148
  The Effect of Data Types’ on the Performance of Machine Learning Algorithms for Cryptocurrency Prediction

  Tanrikulu, Hulusi Mehmet; Pabuccu, Hakan

  Forecasting cryptocurrencies as a financial issue is crucial as it provides investors with possible financial benefits. A slight improvement in forecasting performance can lead to increased profitability; Therefore, obtaining a realistic forecast is very important for investors. Bitcoin, frequently mentioned in recent due to its volatility and chaotic behavior, has become an investment tool, especially during and after the COVID-19 pandemic. In this study, selected ML techniques were investigated for predicting cryptocurrency movements by using technical indicator-based data sets and measuring the applicability of the techniques to cryptocurrencies that do not have sufficient historical data. In order to measure the effect of data size, Bitcoin’s last 1 year and 7 years of data were used. Following the related literature, Google trends and the number of tweets were used as input features, in addition to the most commonly used twelve technical indicators. Random Forest, K-Nearest Neighbors, Extreme Gradient Boosting (XGBoost-XGB), Support Vector Machine (SVM), Naive Bayes (NB), Artificial Neural Networks (ANN), and Long-Short-Term Memory (LSTM) network were optimized for best results. Accuracy, F1, and area under the ROC curve values were used to compare the model performance. For continuous data, ANN and SVM performed the best with the highest accuracy and outperformed the other ML models for complete and reduced sets. LSTM reached the best accuracy for trend data, but SVM, NB, and XGB models showed similar performance. The research shows that some indicators significantly affect prediction performance, and the data discretization process also improved the model’s accuracy. While the number of samples affects the results of many ML models, correctly optimized and fine-tuned models may also give excellent results even with less data.

  AtıfScopus1·OpenAlex2

  İncele
• MakaleYalnız künye2022Scopus SJRQ2/r/bayburt/13241
  Optimized Machine Learning Algorithms for Investigating the Relationship Between Economic Development and Human Capital

  Ozden, Erdemalp; Guleryuz, Didem

  In Economic Development, human capital was previously seen as production factors but gradually evolved into endogenous growth theories. Most of the previous studies have examined the relationships between economic development and human capital via econometric models. Since this relationship is usually nonlinear and machine learning (ML) models can resolve it better, this study investigates the relationships by employing ML methods to provide a new perspective. For this purpose, the optimized ML methods, namely Bayesian Tuned Support Vector Machine and Bayesian Tuned Gaussian Process Regression (BT-GPR), were performed to develop the prediction model for economic development. The hyperparameters have been optimized with the Bayes method by using different kernel functions to increase SVM and GPR methods' predictive performance. The Multiple Linear Regression model has been employed to make a comparison as an econometric model. The performance of the models is evaluated using three statistical metrics, namely, the root mean square error (RMSE), mean absolute error (MAE), and coefficient of determination (R2). The BT-GPR with the exponential kernel model has superior prediction ability with the highest accuracy (R2: 0.9727, RMSE: 0.4022, MAE: 0.3728 in the testing phase). The study shows that the BT-GPR model increases the accuracy of R2 6.4%, RMSE 10.7%, and MAE 1% compared with other developed models.

  • 
  AtıfScopus27·WoS18·OpenAlex30

  İncele