2026-10-23T17:55:38Zhttps://gumushane-rdlopen.rawdatalibrary.net/oai/request

oai:gumushane-rdlopen.rawdatalibrary.net:gumushane/180732026-10-22T11:39:18Zopenairedrivercom_gumushane_10000col_gumushane_10001

A Comparative Study of Machine Learning and Deep Learning for Time Series Forecasting: A Case Study of Choosing the Best Prediction Model for Turkey Electricity ProductionÜnlü, Ramazan ErkinBilgisayar Bilimleri, Yazılım MühendisliğiOver the last decades, Turkey pays special attention to electricity productionto afford its needs. Researchers applied different methodologies including statisticalbased and artificial intelligence-based to correctly predict the future amount of electricityproduction, consumption, and demand. However,limited researchers focused on Turkey’selectricity production prediction problem as a time series analysis. For this reason, wetackle this problem by considering it as a time series analysis in this study. We haveused different methods including traditional machine learning algorithms Support VectorRegression (SVR) and Multilayer Perceptrons (MLP) and a deep learning algorithm LongShort-Term Memory (LSTM) to create a better model for Turkey monthly electricityproduction dataset. Based on our findings LSTM outperforms SVR and MLP approachesin terms of commonly used statistical error evaluation metrics2019Articlehttps://rdlopen.rawdatalibrary.net/r/gumushane/18073https://doi.org/10.19113/sdufenbed.4943961300-7688enSüleyman Demirel Üniversitesi Fen Bilimleri Enstitüsü Dergisiinfo:eu-repo/semantics/openAccessinfo:eu-repo/semantics/articlehttps://gumushane-rdlopen.rawdatalibrary.net/tr/items/gumushane/18073