Sale Prediction in Textile Industry with Hybrid Deep Learning Using Time Series Images
Open Access
- 7 June 2022
- journal article
- Published by Orclever Science and Research Group in The European Journal of Research and Development
- Vol. 2 (2), 301-314
- https://doi.org/10.56038/ejrnd.v2i2.67
Abstract
In 2021, exports of 12.9 billion dollars in the field of textiles in Turkey's exports have an important place in all export income. In the reports published on the textile industry, this figure is expected to increase even more in the coming years. As in other sectors, accurate estimation of sales revenues in the textile sector is very important for the future plans of companies. In this study, a deep learning model has been developed for demand and sales forecasting in the textile industry. In the method used, income will be converted to image data with Gramm Angular Fields of time series. Convolutional neural networks were used to classify these images.Keywords
This publication has 13 references indexed in Scilit:
- A Review of Deep Learning Models for Time Series PredictionIEEE Sensors Journal, 2019
- Review of Deep Learning Algorithms and ArchitecturesIEEE Access, 2019
- Assessment and technological forecasting in the textile industry: From first industrial revolution to the Industry 4.0Strategic Design Research Journal, 2018
- Financial Time Series Prediction Based on Deep LearningWireless Personal Communications, 2017
- Improving organizational decision support: Detection of outliers and sales prediction for a pharmaceutical distribution companyProcedia Computer Science, 2017
- Deep learningNature, 2015
- Retail sales prediction and item recommendations using customer demographics at store levelACM SIGKDD Explorations Newsletter, 2008
- Using support vector machines for time series predictionChemometrics and Intelligent Laboratory Systems, 2003
- DENFIS: dynamic evolving neural-fuzzy inference system and its application for time-series predictionIEEE Transactions on Fuzzy Systems, 2002
- Time Series Prediction and Neural NetworksJournal of Intelligent & Robotic Systems, 2001