Purpose: Demand forecasting in the clothing industry is very complex due to the existence of a wide range of product references and the lack of historical sales data. To the authors' knowledge, there is an inadequate number of literature studies to forecast the demand with the adaptive network based fuzzy inference system for the clothing industry. The purpose of this paper is to construct a decision support system for demand forecasting in the clothing industry.Design/methodology/approach: The adaptive‐network‐based fuzzy inference system (ANFIS) is used for forecasting demand in the clothing industry.Findings: The results of the proposed study showed that an ANFIS‐based demand forecasting system can help clothing manufacturers to forecast demand more accurately, effectively and simply.Originality/value: In this study, the demand is forecast in terms of clothing manufacturers by using ANFIS. ANFIS is a new technique for demand forecasting, it combines the learning capability of the neural networks and the generalization capability of the fuzzy logic. The input and output criteria are determined based on clothing manufacturers' requirements and via literature research, and the forecasting horizon is about one month. The study includes the real life application of the proposed system and the proposed system is tested by using real demand values for clothing manufacturers.

All economic sectors are associated with energy use; therefore, government organizations aim to supply sustainable energy for human needs and economic growth. In particular, increased environmental concerns of the public in Turkey have impacted policymaking for renewable energy (RE) management in Turkey. The primary objective for RE sources of the Turkish Ministry of Energy is to ensure that 30% of the share of electricity production is from RE resources in 2023. In this paper, the integrated multi-objective, multi-period linear programming model is presented to determine effective allocation of RE supply for seven different geographical regions in Turkey for the period of 2017 to 2024. The integrated model consists of two different stages. The first stage involves qualitative evaluations of RE sources for seven geographical regions. Analytical Hierarchy Process (AHP) is applied to determine criteria priorities and overall ratings of geographical regions across determined criteria for RE sources are computed. The second stage of the integrated model consists of a multi-objective, multi-period linear programming model. The proposed multi-objective linear programming model is coded in MPL (Mathematical Programming Language) and solved using the GUROBI 5.1.0 solver. The output of the integrated model presents the total supply amount of RE sources for geographical regions in planning period. The ε-constraints method is applied to compute the total supply amount of RE from geographical regions for the period of 2017 to 2024. In this study, a systematic decision-making model is generated to allocate renewable energy sources to the geographical regions. The presented model integrates qualitative evaluations and quantitative parameters of different geographical regions to determine the optimal supply amount of RE. The obtained results are consistent with the potential quantities of RE alternatives in geographical regions, regional specifications, and social requirements.