The increasing demand for electric vehicles (EVs) requires accurate forecasting to support strategic decisions by manufacturers, policymakers, investors, and infrastructure developers. As EV adoption accelerates due to environmental concerns and technological advances, understanding and predicting this demand becomes critical. In light of these considerations, this study presents an innovative methodology for forecasting EV demand. This model, called EVs-PredNet, is developed using deep learning methods such as LSTM (Long Short-Term Memory) and CNNs (Convolutional Neural Networks). The model comprises convolutional, activation function, max pooling, LSTM, and dense layers. Experimental research has investigated four different categories of electric vehicles: battery electric vehicles (BEV), hybrid electric vehicles (HEV), plug-in hybrid electric vehicles (PHEV), and all electric vehicles (ALL). Performance measures were calculated after conducting experimental studies to assess the model’s ability to predict electric vehicle demand. When the performance measures (mean absolute error, root mean square error, mean squared error, R-Squared) of EVs-PredNet and machine learning regression methods are compared, the proposed model is more effective than the other forecasting methods. The experimental results demonstrate the effectiveness of the proposed approach in forecasting the electric vehicle demand. This model is considered to have significant application potential in assessing the adoption and demand of electric vehicles. This study aims to improve the reliability of forecasting future demand in the electric vehicle market and to develop relevant approaches.

Electric vehicles have gained popularity among both manufacturers and consumers in recent years due to government incentives and climate change. In this study, a new decision support system is proposed to optimise the selection of electric vehicles. The proposed system integrates multi-criteria decision making (MCDM) methods with machine learning (ML) algorithms. A dataset consisting of 15 different electric vehicle alternatives and 20 criteria was created. The criteria were weighted using the CRITIC method and the scores of each alternative were determined using the LOPCOW method. The LOPCOW scores were used as target variables for machine learning models and analyses were performed. In the analysis of the machine learning models, performance metrics such as RMSE, MSE, MAE, MAPE and R² were calculated and the generalisability of the results was tested using the Kfold5 cross-validation method. Finally, the final ranking of the alternatives was performed using the voting regressor model. The decision support system developed in this study combines CRITIC-LOPCOW machine learning algorithms and voting regressor methods to provide a practical and reliable solution for electric vehicle selection. The findings have significant implications for policymakers, investors, and scholars.

Today, green financial products have garnered recognition and are consequently regarded as alternative assets. Green bonds exclusively allocate their funds to environmentally sustainable initiatives. Green bonds facilitate companies in enhancing both their financial and environmental performance by promoting innovations stemming from green initiatives and long-term green investments. This study focused on predicting the price of the green bond index in Japan. The input factors for price prediction in Japan include Nikkei225, USD/JPY, and crude oil price assets, which are seen as alternative investment options for Japanese investors. The study utilized a dataset spanning 693 days, from 06.05.2021 to 02.05.2024. The acquired data is partitioned into two distinct sets: one for training and one for testing. 80% of the data was allocated for training purposes, while the remaining 20% was designated for testing. The study utilized various prediction approaches including RF, MLP, GBR, XGBoost, LSTM, SVR, Catboost, and Linear Regression. The performance of these models was compared using evaluation metrics such as MSE, RMSE, MAE, MAPE, and R2 values. The research revealed that the GBR model exhibited the highest performance on the training data set, whereas the XGBoost and RF models yielded superior prediction results on the test data set.

This study presented an evaluation of the financial performances of six Turkish participation banks with feats of being registered in Borsa Istanbul for the year 2023. The analysis employed 20 different financial ratios using the CAMELS rating. The weighting method of this study was determined to be the CRITIC approach. The financial performances of the 6 participation banks traded in BIST were performed with the weighting method of the CAMELS rating and the CRITIC approach. The performance evaluation was done with the ARAS, TOPSIS, and COPRAS methodologies. As can be observed from the tables, it is clear that EMLAK Katılım Bank has the highest performance in all three methods. Making an evaluation, one can safely argue that the participation banks’ financial performance provides similar results in the three different ways. The similarity, plus the reliability, and the validity of these analyses conducted in this study are that the utilization of the TOPSIS, COPRAS, and ARAS approaches yield similar results.

Bu çalışmada, havayolu şirketlerinin birbirleri arasındaki göreceli lojistik performans düzeylerinin belirlenmesine yönelik bir araştırma gerçekleştirilmiştir. Şirketlerin lojistik performans düzeylerini belirlemek amacıyla, maliyet, verimlilik, servis kalitesi, fiyat ve yönetim boyutları baz alınmış ve bu boyutları temsil eden birim işletme maliyeti, işgücü verimliliği, filo verimliliği, yolcu yük faktörü, zamanında performans, emniyet, uçuş frekansı, ortalama ücret, gelir artışı, net kar marjı, pazar payı alt verileri incelemeye dahil edilmiştir. Veriler, şirketlerin yayınladıkları yıllık finansal tablolardan, Skytrax raporlarından ve açık kaynaklarda yer alan çalışmalardan elde edilmiştir. Kriterlerin ağırlıkları havacılık sektöründe çalışan uzmanlardan alınan görüşler, Shannon Entropi yöntemi ve basit ağırlıklandırma ile belirlenmiştir. Kriterler üç farklı ağırlık oranına göre TOPSIS yöntemi kullanılarak analiz edilmiştir. Araştırma sonucunda, 1. ve 2. sıradaki şirketlerin sadece 0,01 puanlık bir fark ile değişiklik gösterdiği bunun dışında ise uzman görüşü ve entropi yöntemi ile elde edilen sıralamanın aynı olduğu görülmüştür. Ancak her bir kriterin ağırlığı eşit olarak alındığında alternatiflerin sıralamasının değiştiği gözlemlenmiştir.