Main Article Content


Fashion is primarily based on adoption of trends by customers in the textile industry. Fashion trend forecasting is a complex process that aims at identifying future preferences of customers. The textile fashion industry is volatile, trends change very quickly. Fashion trend must be closely followed to increase sales amount. Colour forecasting is considered as one of the significant driving force in the textile fashion industry. If the supply of an item surpasses its demand, it would remain unsold thereby generating loss for the industry. How do we assist the textile manufacturing industries in solving the problem of under/over stocking? Tackling this question from a data driven vision perspective, we developed a model to forecast visual colour trends. In this study, a model for colour demand forecasting in the textile industry developed. This study involves the real life application of the model using real demand values for textile clothing by customers in the south west zone of Nigeria. We forecast future purchases based on historical demand data. Two approaches were combined for forecasting colour trends in the textile industry. The developed model first used the Convolutional Neural Network (CNN) for extracting hidden information/features/patterns from the image dataset. The extracted features were then applied to K- means algorithm for extracting the colours. The study proved that the two approaches used performed excellently well and that accurate colour forecasting can significantly enhance productivity and generate more sales for the textile industry.


Convolutional Neural Network K-means Clustering algorithm Demand Forecasting Colour Forecasting

Article Details

How to Cite
Ajibolu Oyinkansola Gladys and Akinola Solomon Olalekan 2021. A machine learning model for predicting colour trends in the textile fashion industry in south-west Nigeria. International Journal on Integrated Education. 4, 2 (Feb. 2021), 174-188. DOI:


  1. Andrea Fumi, Arriana Pepe, Laura Scarabotti, Massimiliano Schiraldi (2013) “Fourier Analysis for Demand Forecasting in a Fashion Company”. International Journal of Engineering Business Management, Special issues on Innovations in Fashion Industry.
  2. Ferreira Anselmo , Giraldi Gilson(2017), “Convolutional Neural Network approaches to Granite tiles classification”. Expert Systems with Applications,Volume 84, Pages 1-11
  3. Asli Aksoy, Nursel Ozturk, Eric Sucky (2012) “A Decision Support System for Demand
  4. a. Forecasting in the Clothing Industry”. International Journal of Clothing Science and
  5. b. Technology Vol. 24 No. 4, pp. 221-236.
  6. Cagatay Catal, Kaan Ece, Begum Arslan, Akhan Akbulut. (2019) "Benchmarking of Regression and Time Series Analysis Techniques for Sales Forecasting". Balkan Journal of Electrical and Computer Engineering , Vol 7, No. 1 DOI: 10.17694/bajece.494920
  7. Celia Frank, Ashish Garg, Les Sztandera, Amar Raheja (2003) “Forecasting Women’s Apparel Sales Using Mathematical Modelling”. International Journal of Clothing Science and Technology 15(2):107-125 DOI: 10.1108/09556220310470097
  8. Rexhausena Daniel, Pibernik Richard, Kaiser Gernot, (2012) “Customer-facing supply chain
  9. c. Practices: The impact of demand and distribution management on supply chain success”. Journal of Operations Management Volume 30, Issue 4, May 2012, Pages 269-281
  10. Gupta Dishashree (2017), “Architecture of Convolutional Neural Networks”
  12. Elad Harison, Micheal Koren (2019) “Identifying Future Demand in Fashion Goods”. Journal of Textile Science and Fashion Technology, ISSN: 2641-192X DOI: 10.33552/JTSFT.2019.03.000565
  13. Emmanuel S. Silva, Hossein Hassani, Dag O. Madsen, Liz Gee. (2019) "Googling Fashion:
  14. d. Forecasting Fashion Consumer Behaviour Using Google Trends". Social Sciences,
  15. e. MDPI, Open Access Journal, vol. 8(4), pages 1-1, April DOI: 10.3390/socsci8040111
  16. Fashion vs. Style: Key Differences between Fashion and Style,
  18. Fully Connected Layer in Convolutional Neural Networks,, accessed April,
  19. f. 2020.
  20. Zha Hongyuan, He Xiaofeng, Ding Chris & Simon Horst, Gu Ming (2001),” Spectral Relaxation for K-means Clustering” NIPS Proceedings Hartigan J. A. and Wong M. A. (1979), “Algorithm AS 136: A K-Means Clustering Algorithm Journal of the Royal Statistical Society”. Series C (Applied Statistics) Vol. 28, No. 1 (1979)
  21. Kripesh Adhikari, Hamid Bouchachia, Hammadi Nait-Charif (2017), “Activity Recognition for
  22. g. Indoor Fall Detection using Convolutional Neural Network”. Fifteenth IAPR International
  23. h. Conference on Machine Vision Applications (MVA). DOI:
  24. i. 10.23919/MVA.2017.7986795
  25. Li-Xia Chang, Wei-Dong Gao, Xin Zhanget. al (2009) “Discusion on Fashion Colour
  26. j. Forecasting Researches for Textile and Fashion Industries”. Journal of Fiber
  27. k. Bioengineering and Informatics. Vol.2 No.1 DOI: 10.3993/jfbi06200902
  28. Sanuwar Rashid (2013) “The Role of Quick Response for Demand Driven Globalized
  29. l. Apparel Supply Chain Management”. Lecture Notes in Electrical Engineering.
  30. m. 185:643-653DOI: 10.1007/978-1-4471-4600-1_55
  31. Mohammed El Amine Elforaici, Ismail Chaaraoui, Wassim Bouachir, Youssef Ouakrim (2018),
  32. n. “Posture recognition using 3D Body Modelling and Deep Learning Approaches”.
  33. i. IEEE Life Sciences Conferences (LSC). DOI: 10.1109/LSC.2018.8572079
  34. Pawan K. Singh, Aruna Rajan, Yadunath Gupta (2019) “Fashion Retail: Forecasting Demand for
  35. o. new Items”. ArXiv:1907.01960
  36. 2. 3.
  37. 4.
  38. Prashanth Thangavel (2018), “Advanced Feature Engineering - Feature Encoding”
  40. Rokas Balsys (2019),”Convolutional Neural Networks (CNN) explained step by
  41. a. step”
  42. Samaneh Beheshti-Kashi, Hamid Reza Karimi, Klaus-Dieter Thoben, Michael Lütjen, Michael
  43. b. Teucke (2015),” A survey on retail sales forecasting and prediction in fashion markets”
  44. c. Systems Science and Control Engineering Volume 3, 2015 - Issue 1
  45. Samer Hijazi, Rishi Kumar, and Chris Rowen (2015),”Using Convolutional Neural Networks
  46. d. for Image Recognition”
  47. Krig Scott (2016), “Computer Vision Metrics”
  48. e. 5930-5
  49. Sumit Saha (2018), “A Comprehensive Guide to Convolutional Neural Networks”
  51. Tereza Ramirez Ceballos, Roberto Baeza Serrato, Jovani Cardiel Ortega (2018) “Use of
  52. Forecasting Techniques to estimate Demand in Small and Medium sized Companies in the
  53. Textile Sector”. International Journal of Engineering Sciences and Management
  54. f. ISSN 2277-5528
  55. Ye Wang, Bo Wang, Xinyang Zhang (2012), “A New Application of the Support Vector
  56. Regression on the Construction of Financial Conditions Index to CPI Prediction”.
  57. Procedia Computer Science Volume 9, 2012, Pages 1263-1272
  58. Yu Han Liu (2018),”Feature Extraction and Image Recognition with Convolutional Neural
  59. Networks”. Journal of Physics Conference Series 1087(6):062032
  60. DOI: 10.1088/1742-6596/1087/6/062032