Hamit Erdal

Bagging ensemble models for bank profitability

Related to the recent studies of the last decade, which concentrate on the banking performance, researchers have employed the linear models profoundly; however, this trend is about to change due to the prediction performance of ML techniques as well as ANN, DVM, Decision Trees and their ensembles. Considering the analysis concentrated on Turkish banking profit analysis, just the linear models with panel data or multiple regression analysis were applied. In the literature, to the best our knowledge there is no other study that uses more developed models like ensemble models and also there is no significant analysis considering the sub-bank group like IaDB in Turkey.From this two important point of view, this research would fill the gap which caused by using not sophisticated models and just concentrating on the whole banking group with different characteristics.We conduct a comparative assessment of the performance of three bagging ensemble models, on prediction of Turkish IaDB profitability. To the best of our knowledge, ensemble methods have not been applied extensively in banks profitability analyses especially in IaDB profitability predictions. The purpose of this study is to find the determinants of the profits for the Development and Investment Banks (IaDB) in Turkey. In Turkish Banking System, the main financial source of the banks is the deposits, which constitute almost%60 of the balance sheet. As being a sub-group of the banking system, IaDB are not allowed to accept deposits in Turkey, which changes the total structure of the profitability compared to other banks. Till today, none of the relevant research was concentrated on the profit structure of the IaDB neither in Turkey nor in any other countries. Such research would fill that unexpectedly disregarded yet highly important gap.Therefore, to address this gap, quarterly financial data (10 balance sheet ratios) of 13 banks in the period of 2002Q4-2014Q3 were utilized. As a profit measurement among all other available measures, Return on Equity was chosen as dependent variable as it was the most used one as well as many other researcher have preferred as well. This study investigates the potential usage of bagging (Bag), which is one of the most popular ensemble learning methods, in building ensemble models, is used to predict the determinants of Turkish IaDB profitability. Three well-known tree-based machine learning (ML) models (i.e., Decision Stump (DStump), Random Tree (RTree), Reduced Error Pruning Tree (REPTree)) are deployed as base learner. This empirical study indicates that bagging ensemble models (i.e., Bag-DStump, Bag-RTree, Bag-MLP and Bag-REPTree) are superior to their base learners and could improve the prediction accuracy of individual ML models (i.e., DStump, RTree, REPTree).

The Analysis of Factors that Affect Innovation Performance of Logistics Enterprises in Turkey

Services have become a compulsory factor that assists primary industries to accomplish global competitiveness (Chapman et al. 2003). There is a common consensus that economic growth, higher incomes, and technological advances have played a part to the economic growth of service‐sector enterprises (Patterson 1995).

Artificial Intelligence-Based Prediction Models for Energy Performance of Residential Buildings

Although energy sources on the environment are limited, in all parts of life, energy requirement increases rapidly which depends on the increasing technology and population. This problem enforces researchers to study on energy efficiency, performance, and optimization. This paper presents artificial intelligence-based (AI) prediction models to estimate energy loads for residential buildings. The model was developed by using eight input parameters (relative compactness, surface area, wall area, roof area, overall height, orientation, glazing area, glazing area distribution) related to two output parameters (heating and cooling loads).

An Assessment on Innovative Activity and Performance of Turkish Logistics Sector

Logistics management is seem in all enterprises to some degree, depending on the nature of the business and the industry, basically interests in the physical distribution of raw materials and, at long last, finished products (Slack et al. 2009).