Big Data in Fashion Industry: Color Cycle Mining from Runway Data

Lin, Y., Zhou, Y. and Xu, H. (2015). Text-Generated Fashion Influence Model: An Empirical Study on Style.com, Proceedings of 48th Hawaii International Conference on System Sciences (HICSS), Kauai, Hawaii

Abstract

Color is a powerful selling tool, especially in the fashion and textile industry, in which products aim to inspire consumers visually. Color Cycle Analysis studies the recurring cycle of trends. Traditional fashion color cycle analysis and prediction is performed by observing and extrapolating from trends apparent on fashion runways. With the emergence of big data, there is a potential to apply data analytics method in fashion industry. We propose and develop a data-driven methodology to analyze color trends by mining online textual data of global fashion runways collected from the Style.com website. By capturing three important elements in color hue, saturation and brightness, we are able effectively extract their presence and variations in textual data. We illustrate the reoccurrence of seven Color Cycle phases: High Chroma, Multicolored, Subdued, Earth Tones, Achromatic, and Purple Phase from runway review data.

Styles in the Fashion Social Network: An Analysis on Lookbook.nu

Lin Y., Xu H., Zhou Y., Lee WC. (2015) Styles in the Fashion Social Network: An Analysis on Lookbook.nu. In: Agarwal N., Xu K., Osgood N. (eds) Social Computing, Behavioral-Cultural Modeling, and Prediction. SBP 2015. Lecture Notes in Computer Science, vol 9021. Springer, Cham

Abstract

Designers use fabrics and patterns to express their creativity and create trends in fashion. Practically any object and shape can be made into a pattern while fabrics has a more specific range of terms. Designers showcase their latest creations at spring and fall season shows set in large cities around the world. Countless reports and reviews are written by the media to report on those shows and the trends featured. Text analysis using Python, k-means, and topic modeling LDA clustering, is done on those write-ups to mine valuable insight into grouping designers and fabrics favored by designers.

The Hidden Influence Network in the Fashion Industry

Lin, Y., Zhou, Y. and Xu, H. (2014). The Hidden Influence Network in the Fashion Industry, The 24th Annual Workshop on Information Technologies and Systems (WITS), Auckland, New Zealand

Abstract:

In this era of big data, even though there exists an abundance of data documenting fashion and fashion trends, there has barely been any quantitative research conducted on the topic of influence or leadership. Unlike many other innovation domains such as patents where citations are explicit, a fashion designer hardly claims that s/he is influenced by others. To trace the hidden fashion influence network, we propose a novel approach to analyze the design influence in fashion industry by comparing similarity between designers in adopting same fashion symbols. Based on text processing techniques, we develop a quantitative model to extract fashion influences from 14-year historical data on fashion reviews. A total of 6,629 fashion runway reviews from the year 2000 to 2014 have been collected for analysis. We compared the performance of our proposed model with the globally published “most influential” lists and calculated a performance of 92.81% area under curve (AUC). A small world network test was conducted to demonstrate that by systematically constructing the fashion influence network, we are able to show that the fashion industry fits within a small network model.

Cluster Analysis of Runway Reviews Based on Fabric and Pattern

Abstract

Designers use fabrics and patterns to express their creativity and create trends in fashion. Practically any object and shape can be made into a pattern while fabrics has a more specific range of terms. Designers showcase their latest creations at spring and fall season shows set in large cities around the world. Countless reports and reviews are written by the media to report on those shows and the trends featured. Text analysis using Python, k-means, and topic modeling LDA clustering, is done on those write-ups to mine valuable insight into grouping designers and fabrics favored by designers.