Karatay, Melike

Profile URL
https://hdl.handle.net/20.500.14627/1224
Name Variants
Job Title
Dr. Öğr. Üyesi
Email Address
melike.karatay@fbu.edu.tr
Main Affiliation
YÖNETİM BİLİŞİM SİSTEMLERİ BÖLÜMÜ
Status
Current Staff
Website
ORCID ID
0000-0001-6941-4752
Scopus Author ID
Turkish CoHE Profile ID
Google Scholar ID
vMX7BNsAAAAJ
WoS Researcher ID
MIT-8310-2025

Research Topics

Domains
Physical Sciences
Fields
Computer Science
Subfields
Computer Vision and Pattern RecognitionInformation SystemsComputer Science Applications
Specific Research Areas
Face and Expression Recognition
Blockchain Technology Applications and Security
Context-Aware Activity Recognition Systems
Advanced Data Compression Techniques
Online Learning and Analytics

Sustainable Development Goals

SDG data is not available

Publication Collaboration

Affiliation Name Count
Dokuz Eylül University 1
Ondokuz Mayıs University 1
Ege University 1
Izmir University 1
Fenerbahçe University 1
1 / 2
Data obtained from OpenAlex
Scholarly Output

1

Articles

1

WoS Citation Count

0

Scopus Citation Count

0

Filters

20261

Settings

Author of Publication: search.filters.isAuthorOfPublication.4e7cde71-951c-4aac-a716-6f168c11aa71

Scholarly Output Search Results

Now showing 1 - 1 of 1
  • Article
    A Delta-Targeted Hybrid Deep Learning Architecture for Short-Term Scrap Steel Price Forecasting: A Comparative Study
    (MDPI, 2026) Ugurlu, Onur; Cifci, Nihan Sena; Karatay, Melike; Aygul, Yesim; Demirel, Yasemin
    Forecasting scrap steel prices is crucial for the economic sustainability of recycling operations, yet it remains challenging due to inherent volatility and non-stationary behavior. In this study, we develop and evaluate a delta-targeted Hybrid forecasting pipeline for short horizons of 1, 3, and 7 days. We benchmark classical baselines (Naive, Seasonal Autoregressive Integrated Moving Average (SARIMA), and Exponential Smoothing (ETS)) against recurrent deep learning models (Simple Recurrent Neural Network (RNN), Gated Recurrent Unit (GRU), and Long Short-Term Memory (LSTM)) and recent neural forecasting baselines, including Decomposition-Linear (DLinear), Convolutional Kolmogorov-Arnold Network (C-KAN), and Neural Basis Expansion Analysis for Time Series (N-BEATS), using real-world daily scrap steel price data. The results indicate that delta-targeting generally yields more stable predictive performance than direct raw-price forecasting as the prediction horizon increases. For example, at the 7-day horizon, the predictive fit improves from approximately R-2 approximate to 0.87 for raw-price LSTM to around R-2 approximate to 0.90 for delta-trained recurrent models. At the same horizon, a delta-based RNN achieves the lowest Mean Absolute Percentage Error (MAPE) among the evaluated models (approximately 1.39%), while the proposed Hybrid model remains competitive across all tested horizons and maintains a goodness-of-fit of approximately R-2 approximate to 0.90 without uniformly minimizing point error relative to the best-performing recurrent baseline. Attention profiling and permutation-based feature importance analyses indicate that the model places relatively higher weight on calendar-related inputs, consistent with the presence of weekly patterns in the data; these results should be interpreted as sensitivity diagnostics rather than causal evidence. Overall, the findings suggest that delta-transformed targets provide a more suitable prediction space than raw-price targets for short-horizon scrap steel forecasting, while the Hybrid design offers a balanced combination of predictive performance and diagnostic interpretability for operational decision support.