FORECASTING FASHION TRENDS BASED ON NEURAL NETWORKS
Keywords:
: fashion trends, large-scale dataset, KERN model, forecasting, deep learning, recurrent neural networks, time series analysis
Abstract
Fashion trend forecasting remains a challenging task due to the limited item coverage and simplified models in existing approaches. In this paper, a large-scale FIT dataset containing time series of fashion items and user demographics is presented. To analyze complex time dependencies, a recurrent neural network-based KERN model is proposed that takes into account internal and external domain knowledge. The model demonstrates accurate forecasts even for items with irregular patterns on both semi-annual and annual planning horizons. Of particular interest is the analysis of differences in trends for different user groups; the model successfully captures these features, which significantly improves the accuracy of personalized forecasts. Based on these results, a comprehensive report generation system is developed that covers all aspects of fashion trends from basic categories to specific attributes. Experiments confirm that KERN provides more accurate trend forecasting compared to traditional methods.
References
REFERENCES
1. Decree of the Government of the Russian Federation dated November 6. 2021 N 3142-r Strategic direction in the field of digital transformation of manufacturing industries. http://static.government.ru/media/files.
2. Larionov V.G., Sheremetyeva E.N., Balanovskaya A.V. Vectors of digital transformation of the textile industry. News of higher educational institutions. Technology of the textile industry. 2022. N 2(398). P. 12-20. DOI 10.47367/ /0021-3497_2022_2_12. EDN LQOWEU.
3. Mochalina D.R., Sineva D.V. The use of neural networks in the development of light industry collections. Costumology. 2024. V. 9. N 2. https://kostumologiya.ru/PDF/01TLKL224.pdf.
4. Saidi D.R., Makhmudova F.M. Advantages of light digitalization. Universum: Technical Sciences: electron. scientific Journal 2020, N 1(70). P.108-116.
5. Shumsky A.V. Fashion industry in the digital age: trends and technologies. Copper@llmanakh. 2021. N 4 (105). P. 60-69. DOI: 10.30547/mediaalmanah.4.2021.6069.
6. Akinina P.S. The specifics of fashion discourse. Colloquium-journal. 2019. N 10 (34). P. 111-112. DOI: 10.24411/2520-6990-2019-10285.
7. Yerzhanova M.E., Sugurova L.A., Dzhanuzakova R.Zh., Isakulova Zh.A., Abildaeva A.S. Artificial intelligence in manufacturing and the textile industry. Izvestiya vuzov. Technology of the textile industry. 2020. N 2(386). P. 150-153.
8. Dementieva I.N. Theoretical and methodological approaches to the study of consumer behavior. Problems of territory development. 2018. N 1 (93). P. 122-132.
9. Shchekotin E.V. Digital footprints as a new source of data on quality of life and well-being: an overview of current trends. Vestn. Volume of the State University. 2021. N 467. P. 170-181. DOI: 10.17223/15617793/467/21.
10. Bogdanov M. B., Smirnov I.B. The possibilities and limitations of digital footprints and machine learning methods in sociology. Monitoring. 2021. N 1. P. 304-328. https://doi. org/10.14515/monitoring.2021.1.1760.
11. Polyakova S.A. Methods of fashion forecasting. Current research. 2023. N 3 (133). https://apni.ru/article/5367-metodi-pro gnozirovaniya-modi.
12. Soboleva L.A., Kuzmin A.G., Tyurin I.N., Tashpulatov S Sh., Belgorodsky V S. Technology of virtual fitting in modern fashion retail. Costumology. 2021. V. 6. N 4. https://kostumologiya.ru/PDF/22IVKL421.pdf .
13. Yunshan Ma, Xun Yang, Lizi Liao, Yixin Cao, and Tat-Seng Chua. Automatic Fashion Knowledge Extraction from Social Media. MM '19: Proceedings of the 27th ACM International Conference on Multimedia. 2019. P. 2223-2224. https://doi.org/10.1145/3343031.3350607.
14. Henrique A.S. Classifying Garments from Fashion-MNIST Dataset Through CNNs. Advances in Science, Technology and Engineering Systems Journal. 2021. V. 6. N 1. P.989-994.
15. Zakharova O.I., Shamrin D.A. Comparative analysis of pattern recognition methods. Bulletin of Science. 2024. N 6 (75). P.1517-1524.
16. Panasenko S.V., Bezpalov V.V., Star I.A. Integration of virtual fitting technology capabilities to improve sales in the fashion industry. Bulletin of the Altai Academy of Economics and Law. 2024. N 3 (part 1). P. 106-111.
17. Xintong Han, Zuxuan Wu, Zhe Wu, Ruichi Yu, Larry S. Davis VITON: An Image-Based Virtual Try-On Network. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2018. P. 7543-7552.
18. Utkarsh Mal, Kevin Matzen, Bharath Hariharan, Noah Snavely, Kavita Bala. Geo Style: Discovering Fashion Trends and Events. Proceedings of the IEEE International Conference on Computer Vision. 2019. P. 411-420. DOI Bookmark: 10.1109/ICCV.2019.00050.
19. Fuli Feng, Xiangnan He, Xiang Wang, Cheng Luo, Yiqun Liu, Tat-Seng Chua Temporal Relational Ranking for Stock Prediction. ACM Transactions on Information Systems. 2019. V. 37. N 2. P. 1-30.
20. Ziad Al-Halah, Stiefelhagen R., Grauman K. Fashion Forward: Forecasting Visual Style in Fashion. IEEE International Conference. Art, Computer Science. 2017. P. 388-397. DOI:10.1109/ICCV.2017.50.
21. Yunshan Ma, Xun Yang, Lizi Liao, Yixin Cao, Tat-Seng Chua. Who, where, and what to wear? extracting fashion knowledge from social media. Proceedings of the 27th ACM International Conference on Multimedia. 2019. P. 257-265.
22. Fashion Trend Dataset. Kaggle. https://www.kaggle.com. datasets/ fashionworldda/fashion-trend-dataset
23. Yunshan Ma, Lizi Liao, Tat-Seng Chua. Automatic fashion knowledge extraction from social media. Proceedings of the 27th ACM International Conference on Multimedia. 2019. P. 2223-2224.
24. Bredikhin A.I. Learning algorithms for convolutional neural networks. Bulletin of the SOUTH. 2019. N 1 (52). P. 41-54.
25. Parasich A.V., Parasich V.A., Parasich I.V. Formation of a training sample in machine learning tasks. Review. Information management systems. 2021. N 4 (113). P. 61-70. DOI:10.31799/1684-8853-2021-4-61-70.
26. Joseph Redmon, Ali Farhadi. Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767. 2018. https://arxiv.org/pdf/1804.02767.
27. Sizova O.V., Tezin N.K. Forecasting the traffic of news resource views using artificial intelligence methods. Ivecofin.2023. N 4(58). P. 79-88. DOI 10.6060/ivecofin. 2023584.667.
28. Pavlova E.A. Sizova O.V. Analysis and optimization of on-line sales of a trade organization. Ivecofin.2024. N 4(62). P. 88-97. DOI 10.6060/ivecofin.2024624.706.
29. Ksenofontova O.L., Mirolyubova A.A., Fokin S.A. The use of data mining methods in the banking sector. Modern high technology. Regional application. 2023. N 4(76). P. 76-83. DOI 10.6060/snt.20237604.00010.
30. Bobkov, S.P., Astrakhantseva I.A., Kutuzova A.S. Simulation modeling of subjects' behavior in a complex social system. Modern high technology. Regional application. 2022. N 4(72). P. 33-39. DOI 10.6060/snt.20227204. 0005.
1. Decree of the Government of the Russian Federation dated November 6. 2021 N 3142-r Strategic direction in the field of digital transformation of manufacturing industries. http://static.government.ru/media/files.
2. Larionov V.G., Sheremetyeva E.N., Balanovskaya A.V. Vectors of digital transformation of the textile industry. News of higher educational institutions. Technology of the textile industry. 2022. N 2(398). P. 12-20. DOI 10.47367/ /0021-3497_2022_2_12. EDN LQOWEU.
3. Mochalina D.R., Sineva D.V. The use of neural networks in the development of light industry collections. Costumology. 2024. V. 9. N 2. https://kostumologiya.ru/PDF/01TLKL224.pdf.
4. Saidi D.R., Makhmudova F.M. Advantages of light digitalization. Universum: Technical Sciences: electron. scientific Journal 2020, N 1(70). P.108-116.
5. Shumsky A.V. Fashion industry in the digital age: trends and technologies. Copper@llmanakh. 2021. N 4 (105). P. 60-69. DOI: 10.30547/mediaalmanah.4.2021.6069.
6. Akinina P.S. The specifics of fashion discourse. Colloquium-journal. 2019. N 10 (34). P. 111-112. DOI: 10.24411/2520-6990-2019-10285.
7. Yerzhanova M.E., Sugurova L.A., Dzhanuzakova R.Zh., Isakulova Zh.A., Abildaeva A.S. Artificial intelligence in manufacturing and the textile industry. Izvestiya vuzov. Technology of the textile industry. 2020. N 2(386). P. 150-153.
8. Dementieva I.N. Theoretical and methodological approaches to the study of consumer behavior. Problems of territory development. 2018. N 1 (93). P. 122-132.
9. Shchekotin E.V. Digital footprints as a new source of data on quality of life and well-being: an overview of current trends. Vestn. Volume of the State University. 2021. N 467. P. 170-181. DOI: 10.17223/15617793/467/21.
10. Bogdanov M. B., Smirnov I.B. The possibilities and limitations of digital footprints and machine learning methods in sociology. Monitoring. 2021. N 1. P. 304-328. https://doi. org/10.14515/monitoring.2021.1.1760.
11. Polyakova S.A. Methods of fashion forecasting. Current research. 2023. N 3 (133). https://apni.ru/article/5367-metodi-pro gnozirovaniya-modi.
12. Soboleva L.A., Kuzmin A.G., Tyurin I.N., Tashpulatov S Sh., Belgorodsky V S. Technology of virtual fitting in modern fashion retail. Costumology. 2021. V. 6. N 4. https://kostumologiya.ru/PDF/22IVKL421.pdf .
13. Yunshan Ma, Xun Yang, Lizi Liao, Yixin Cao, and Tat-Seng Chua. Automatic Fashion Knowledge Extraction from Social Media. MM '19: Proceedings of the 27th ACM International Conference on Multimedia. 2019. P. 2223-2224. https://doi.org/10.1145/3343031.3350607.
14. Henrique A.S. Classifying Garments from Fashion-MNIST Dataset Through CNNs. Advances in Science, Technology and Engineering Systems Journal. 2021. V. 6. N 1. P.989-994.
15. Zakharova O.I., Shamrin D.A. Comparative analysis of pattern recognition methods. Bulletin of Science. 2024. N 6 (75). P.1517-1524.
16. Panasenko S.V., Bezpalov V.V., Star I.A. Integration of virtual fitting technology capabilities to improve sales in the fashion industry. Bulletin of the Altai Academy of Economics and Law. 2024. N 3 (part 1). P. 106-111.
17. Xintong Han, Zuxuan Wu, Zhe Wu, Ruichi Yu, Larry S. Davis VITON: An Image-Based Virtual Try-On Network. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2018. P. 7543-7552.
18. Utkarsh Mal, Kevin Matzen, Bharath Hariharan, Noah Snavely, Kavita Bala. Geo Style: Discovering Fashion Trends and Events. Proceedings of the IEEE International Conference on Computer Vision. 2019. P. 411-420. DOI Bookmark: 10.1109/ICCV.2019.00050.
19. Fuli Feng, Xiangnan He, Xiang Wang, Cheng Luo, Yiqun Liu, Tat-Seng Chua Temporal Relational Ranking for Stock Prediction. ACM Transactions on Information Systems. 2019. V. 37. N 2. P. 1-30.
20. Ziad Al-Halah, Stiefelhagen R., Grauman K. Fashion Forward: Forecasting Visual Style in Fashion. IEEE International Conference. Art, Computer Science. 2017. P. 388-397. DOI:10.1109/ICCV.2017.50.
21. Yunshan Ma, Xun Yang, Lizi Liao, Yixin Cao, Tat-Seng Chua. Who, where, and what to wear? extracting fashion knowledge from social media. Proceedings of the 27th ACM International Conference on Multimedia. 2019. P. 257-265.
22. Fashion Trend Dataset. Kaggle. https://www.kaggle.com. datasets/ fashionworldda/fashion-trend-dataset
23. Yunshan Ma, Lizi Liao, Tat-Seng Chua. Automatic fashion knowledge extraction from social media. Proceedings of the 27th ACM International Conference on Multimedia. 2019. P. 2223-2224.
24. Bredikhin A.I. Learning algorithms for convolutional neural networks. Bulletin of the SOUTH. 2019. N 1 (52). P. 41-54.
25. Parasich A.V., Parasich V.A., Parasich I.V. Formation of a training sample in machine learning tasks. Review. Information management systems. 2021. N 4 (113). P. 61-70. DOI:10.31799/1684-8853-2021-4-61-70.
26. Joseph Redmon, Ali Farhadi. Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767. 2018. https://arxiv.org/pdf/1804.02767.
27. Sizova O.V., Tezin N.K. Forecasting the traffic of news resource views using artificial intelligence methods. Ivecofin.2023. N 4(58). P. 79-88. DOI 10.6060/ivecofin. 2023584.667.
28. Pavlova E.A. Sizova O.V. Analysis and optimization of on-line sales of a trade organization. Ivecofin.2024. N 4(62). P. 88-97. DOI 10.6060/ivecofin.2024624.706.
29. Ksenofontova O.L., Mirolyubova A.A., Fokin S.A. The use of data mining methods in the banking sector. Modern high technology. Regional application. 2023. N 4(76). P. 76-83. DOI 10.6060/snt.20237604.00010.
30. Bobkov, S.P., Astrakhantseva I.A., Kutuzova A.S. Simulation modeling of subjects' behavior in a complex social system. Modern high technology. Regional application. 2022. N 4(72). P. 33-39. DOI 10.6060/snt.20227204. 0005.
Published
2025-10-02
How to Cite
Сизова, О., Сироткина, А., & Рычихина, Н. (2025). FORECASTING FASHION TRENDS BASED ON NEURAL NETWORKS. Modern High Technologies. Regional Application, 83(3), 47-55. Retrieved from https://snt-isuct.ru/article/view/6752
Section
Экономические науки
