Predicting The Style and Size Each Consumer Will Love and Keep - Unique Research
Recent advances in technology such as computer vision, deep learning, and recommender systems are being used to enable new shopping experiences. Examples include filtering large catalogues to make a manageable set of personalised recommendations to individual consumers, recommending similar items, and recommending items that other shoppers also viewed.
However, technology alone without an understanding of shoppers, fashion, and retail falls short of solving shopping recommendation problems. Details matter, especially for modelling individual fashion preferences.
In this session, True Fit will open up data from its Fashion Genome, the largest fashion and retail dataset, and demonstrate key learnings around influencing fashion recommendations. It will explore how data allows retailers to better understand their customers and enable them to make future recommendations based on what knowledge they have of them.
By leveraging extensive fashion details of products, to combine fashion and technology, retailers have the tools to create personalised and meaningful recommendations to their customers.
True Fit – Tech research:
Based on new research, Rhonda Textor, True Fit’s Head of Data Science will quantify some important trends that are able to be identified through data analysis and the impact they have on recommendation performance, in particular:
- The prevalence of new or guest shoppers without much sales history versus fully engaged shoppers with a rich profile and sales history
- Catalogue turnover/prevalence of new items without a sales history
Rhonda will discuss and explain which attributes are important for making recommendations, based on user surveys and various data analyses. She will also showcase the results from numerous experiments that highlight how the amount and type of data impacts the quality of recommendations.
- Gain unique insights into new consumer trends through a piece of exclusive research from True Fit
- Learn how data can be used as a tool to really understand your customer and then how to use it to provide a truly personalised experience