Browsing by Author "Kup, Eyup Tolunay"

Now showing 1 - 3 of 3

Citation - WoS: 1
Citation - Scopus: 1
Courier Payout Cash-Flow Prediction in Crowdsourced E-Commerce Logistics: a Hybrid Machine Learning Approach
(Springer international Publishing Ag, 2024) Cay, Ahmet; Kup, Eyup Tolunay; Bayram, Baris; Ciltik, Ali
In the rapidly growing sector of crowdsourced e-commerce logistics, where delivery volumes are highly variable, the effective management of courier payouts becomes essential to maintain operational efficiency. This paper introduces a comprehensive hybrid approach, blending clustering methods with multiple advanced regression models, to accurately predict daily courier payout cash-flows. By utilizing real-world data from e-commerce operations, our methodology estimates the daily financial outflows for courier payments, a critical component for adapting to the dynamic and unpredictable nature of crowdsourced logistics. Our approach includes a thorough comparative analysis of several stateof- the-art regression models - namely, XGBoost Regressor, LightGBM Regressor, and Facebook's PROPHET - in conjunction with clustering techniques that categorize similar cross-docks based on distinct characteristics. This integrated, hybrid strategy aims to provide precise daily financial predictions for each cross-dock, which is crucial for robust financial planning and effective resource allocation. The practical implications of this research are significant, offering logistics companies a powerful tool to navigate the complexities of e-commerce environments. By ensuring more accurate cash-flow predictions, companies can optimize their operations, reduce financial uncertainties, and improve overall service quality in the highly competitive and fast-paced world of e-commerce logistics.
Citation - WoS: 0
Citation - Scopus: 0
Evaluation of Business Intelligence Tools for the Logistics Sector With Hesitant Fuzzy Hybrid Mcdm Methods
(Springer international Publishing Ag, 2024) Kup, Eyup Tolunay; Samanlıoğlu, Funda; Demir, Burcu; Gun, Alper; Samanlioglu, Funda; Gencay, Sevval Ece; Kocak, Gokcenur
Business intelligence (BI) tools have become essential for logistics companies due to their ability to facilitate improved decision-making and operational efficiency, as they provide comprehensive data analysis capabilities that contribute to more informed and timely decisions. This study utilizes the critical task of selecting the most suitable BI tool for an e-commerce logistics company, focusing on assessing various alternatives, including open-sourced and proprietary software. The research employs innovative integrated multi-criteria decision-making (MCDM) methods. The integrated approach primarily uses HFAHP to determine related criteria weights. Then, utilizing these determined weights, Hesitant Fuzzy Preference Ranking Organization Method for Enrichment Evaluation II (HF-PROMETHEE II), Hesitant Fuzzy Evaluation Based on Distance from Average Solution (HF-EDAS), and Hesitant Fuzzy Multiple Objective Optimization on the basis of Ratio Analysis plus Full Multiplicative Form (HF-MULTIMOORA) methods are implemented to compare the alternatives. Five different Business intelligence tools were evaluated concerning eleven comprehensive criteria. This exhaustive evaluation, conducted by five business intelligence experts, aims to guide organizations in selecting an optimal BI tool that enhances data analysis, decision-making processes, and overall business efficiency.
Citation - WoS: 1
Citation - Scopus: 1
Ranking Willingness To Reuse Water in Cotton Irrigation With Hybrid Mcdm Methods: Soke Plain Case Study
(Elsevier, 2024) Burak, Selmin; Samanlıoğlu, Funda; Samanlioglu, Funda; Ulker, Duygu; Kup, Eyup Tolunay
Soke Plain, located within the B & uuml;y & uuml;k Menderes River Basin is one of the highest producers of cotton in T & uuml;rkiye. The overall irrigation water supply is based on scarce conventional water resources that are being depleted at an increasing pace due to climate change impacts in B. Menderes. The inclusive objective of this research is to pave the way for a "water efficiency action plan" incorporating non-conventional (alternative) water resources for irrigation in Soke Plain to address adaptive management. Integrated Water Resources Management (IWRM) principles help decision makers (DMs) to identify and apply the most adequate alternatives among other possible ones in resource planning processes. Therefore, the preference ranking of DMs among possible water resource alternatives for irrigation is vital for implementation. This paper marks the first instance of using a multi-criteria decision-making (MCDM) method to evaluate both conventional and non-conventional water resource alternatives for cotton irrigation. The evaluation and ranking of water resource alternatives is processed using the hybrid MCDM method, integration of "Hesitant Fuzzy-Analytic Hierarchy Process" (HF-AHP) and "Hesitant Fuzzy Evaluation based on Distance from Average Solution" (HF-EDAS), namely HF-AHP-EDAS. This procedure implies several possibly contradictory qualitative and quantitative criteria, incorporates ambiguity, vagueness, and hesitancy in decision-makers' decisions, and achieves a consistent, dependable ranking of alternatives. Eight different water resources for irrigation are evaluated by 5 experts, for 15 assessment criteria, in Soke Plain. Conventional water resources blended with drainage water is concluded to be the best irrigation water resource alternative, with HF-AHP-EDAS and also with HF-AHP-PROMETHEE II (Preference Ranking Organization Method for Enriching Evaluations II), that is used for comparison analysis. This choice aligns well with the outlined arguments, culminating in an overall result deemed compliant with the field survey.